diff options
Diffstat (limited to 'tools/perf/pmu-events/arch')
101 files changed, 7454 insertions, 2459 deletions
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json index afcdad58ef89..324104438e78 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json @@ -113,7 +113,7 @@ { "MetricName": "load_store_spec_rate", "MetricExpr": "((LDST_SPEC / INST_SPEC) * 100)", - "BriefDescription": "The rate of load or store instructions speculatively executed to overall instructions speclatively executed", + "BriefDescription": "The rate of load or store instructions speculatively executed to overall instructions speculatively executed", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" }, @@ -132,7 +132,7 @@ { "MetricName": "pc_write_spec_rate", "MetricExpr": "((PC_WRITE_SPEC / INST_SPEC) * 100)", - "BriefDescription": "The rate of software change of the PC speculatively executed to overall instructions speclatively executed", + "BriefDescription": "The rate of software change of the PC speculatively executed to overall instructions speculatively executed", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" }, @@ -195,14 +195,14 @@ { "MetricName": "stall_frontend_cache_rate", "MetricExpr": "((STALL_FRONTEND_CACHE / CPU_CYCLES) * 100)", - "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and cache miss", + "BriefDescription": "Proportion of cycles stalled and no operations delivered from frontend and cache miss", "MetricGroup": "Stall", "ScaleUnit": "1percent of cycles" }, { "MetricName": "stall_frontend_tlb_rate", "MetricExpr": "((STALL_FRONTEND_TLB / CPU_CYCLES) * 100)", - "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and TLB miss", + "BriefDescription": "Proportion of cycles stalled and no operations delivered from frontend and TLB miss", "MetricGroup": "Stall", "ScaleUnit": "1percent of cycles" }, diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json index 5228f94a793f..6817cac149e0 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json @@ -113,7 +113,7 @@ { "MetricName": "load_store_spec_rate", "MetricExpr": "LDST_SPEC / INST_SPEC", - "BriefDescription": "The rate of load or store instructions speculatively executed to overall instructions speclatively executed", + "BriefDescription": "The rate of load or store instructions speculatively executed to overall instructions speculatively executed", "MetricGroup": "Operation_Mix", "ScaleUnit": "100percent of operations" }, @@ -132,7 +132,7 @@ { "MetricName": "pc_write_spec_rate", "MetricExpr": "PC_WRITE_SPEC / INST_SPEC", - "BriefDescription": "The rate of software change of the PC speculatively executed to overall instructions speclatively executed", + "BriefDescription": "The rate of software change of the PC speculatively executed to overall instructions speculatively executed", "MetricGroup": "Operation_Mix", "ScaleUnit": "100percent of operations" }, @@ -195,14 +195,14 @@ { "MetricName": "stall_frontend_cache_rate", "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES", - "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and cache miss", + "BriefDescription": "Proportion of cycles stalled and no operations delivered from frontend and cache miss", "MetricGroup": "Stall", "ScaleUnit": "100percent of cycles" }, { "MetricName": "stall_frontend_tlb_rate", "MetricExpr": "STALL_FRONTEND_TLB / CPU_CYCLES", - "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and TLB miss", + "BriefDescription": "Proportion of cycles stalled and no operations delivered from frontend and TLB miss", "MetricGroup": "Stall", "ScaleUnit": "100percent of cycles" }, @@ -391,7 +391,7 @@ "ScaleUnit": "100percent of cache acceses" }, { - "MetricName": "l1d_cache_access_prefetces", + "MetricName": "l1d_cache_access_prefetches", "MetricExpr": "L1D_CACHE_PRFM / L1D_CACHE", "BriefDescription": "L1D cache access - prefetch", "MetricGroup": "Cache", diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index 377dfecd96bd..cae7c0cf02f2 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -1,56 +1,56 @@ [ { "BriefDescription": "C10 residency percent per package", - "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c10\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C10_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C1 residency percent per core", - "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricExpr": "cstate_core@c1\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C1_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C8 residency percent per package", - "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c8\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C8_Pkg_Residency", "ScaleUnit": "100%" @@ -552,7 +552,7 @@ }, { "BriefDescription": "Average CPU Utilization", - "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.REF_TSC@ / TSC", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.REF_TSC@ / msr@tsc\\,cpu=cpu_atom@", "MetricName": "tma_info_system_cpu_utilization", "Unit": "cpu_atom" }, @@ -751,7 +751,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -790,11 +790,20 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ", + "Unit": "cpu_core" + }, + { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "MetricName": "tma_bottleneck_data_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full", "Unit": "cpu_core" }, @@ -802,23 +811,14 @@ "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "MetricName": "tma_bottleneck_data_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_bottleneck_compute_bound_est", - "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ", - "Unit": "cpu_core" - }, - { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20", @@ -826,7 +826,7 @@ }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -862,7 +862,7 @@ }, { "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_data_cache_memory_bandwidth + tma_bottleneck_data_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", @@ -879,7 +879,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", @@ -992,7 +992,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(25 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + 24 * tma_info_system_core_frequency * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", @@ -1109,7 +1108,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1238,7 +1237,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", @@ -1851,7 +1850,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute", @@ -1912,7 +1911,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc\\,cpu=cpu_core@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency", "Unit": "cpu_core" @@ -1926,7 +1925,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.REF_TSC@ / TSC", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.REF_TSC@ / msr@tsc\\,cpu=cpu_core@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized", "Unit": "cpu_core" @@ -1936,7 +1935,7 @@ "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full", "Unit": "cpu_core" }, { @@ -1980,7 +1979,6 @@ }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.RD + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.RD", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", @@ -2032,6 +2030,13 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]", + "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time", + "MetricGroup": "SoC", + "MetricName": "tma_info_system_uncore_frequency", + "Unit": "cpu_core" + }, + { "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "Pipeline", @@ -2150,12 +2155,12 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "BriefDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (cpu_core@MEM_INST_RETIRED.ALL_LOADS@ - cpu_core@MEM_LOAD_RETIRED.FB_HIT@ - cpu_core@MEM_LOAD_RETIRED.L1_MISS@) * 20 / 100, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2171,7 +2176,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "3 * tma_info_system_core_frequency * cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", @@ -2192,12 +2196,11 @@ }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "9 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_data_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2279,6 +2282,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(16 * max(0, cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ - cpu_core@L2_RQSTS.ALL_RFO@) + cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@ * (10 * cpu_core@L2_RQSTS.RFO_HIT@ + min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", @@ -2314,7 +2318,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2324,13 +2328,13 @@ "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -2341,7 +2345,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", @@ -2400,7 +2403,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", - "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2", + "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2.4", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -2439,6 +2442,7 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", @@ -2507,6 +2511,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", @@ -2517,6 +2522,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_THRESHOLD_AND_NMI", "MetricExpr": "(cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + max(cpu_core@RS.EMPTY_RESOURCE@ - cpu_core@RESOURCE_STALLS.SCOREBOARD@, 0)) / tma_info_thread_clks * (cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", @@ -2527,6 +2533,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_THRESHOLD_AND_NMI", "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", @@ -2537,7 +2544,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", @@ -2548,7 +2554,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", @@ -2560,7 +2565,7 @@ { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2591,7 +2596,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", @@ -2626,7 +2630,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%", "Unit": "cpu_core" }, diff --git a/tools/perf/pmu-events/arch/x86/alderlake/cache.json b/tools/perf/pmu-events/arch/x86/alderlake/cache.json index 5461576dafc7..4cd535baf703 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/cache.json @@ -4,7 +4,6 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.HWPF_MISS", - "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20", "Unit": "cpu_core" @@ -14,7 +13,7 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.REPLACEMENT", - "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -24,7 +23,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -36,7 +35,7 @@ "EdgeDetect": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS", - "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", + "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -47,7 +46,6 @@ "Deprecated": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALL", - "PublicDescription": "This event is deprecated. Refer to new event L1D_PEND_MISS.L2_STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -57,7 +55,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALLS", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -67,7 +65,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -78,7 +76,7 @@ "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -88,7 +86,7 @@ "Counter": "0,1,2,3", "EventCode": "0x25", "EventName": "L2_LINES_IN.ALL", - "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", "SampleAfterValue": "100003", "UMask": "0x1f", "Unit": "cpu_core" @@ -98,7 +96,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.NON_SILENT", - "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_core" @@ -108,7 +106,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", "SampleAfterValue": "200003", "UMask": "0x1", "Unit": "cpu_core" @@ -118,7 +116,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.USELESS_HWPF", - "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", "SampleAfterValue": "200003", "UMask": "0x4", "Unit": "cpu_core" @@ -137,7 +135,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.ALL", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]", "SampleAfterValue": "200003", "UMask": "0xff", "Unit": "cpu_core" @@ -167,7 +165,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", "SampleAfterValue": "200003", "UMask": "0x3f", "Unit": "cpu_core" @@ -177,7 +175,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", - "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0", + "PublicDescription": "Counts the total number of L2 code requests.", "SampleAfterValue": "200003", "UMask": "0xe4", "Unit": "cpu_core" @@ -187,7 +185,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", "SampleAfterValue": "200003", "UMask": "0xe1", "Unit": "cpu_core" @@ -197,7 +195,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_MISS", - "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts demand requests that miss L2 cache.", "SampleAfterValue": "200003", "UMask": "0x27", "Unit": "cpu_core" @@ -207,7 +205,6 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_HWPF", - "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf0", "Unit": "cpu_core" @@ -217,7 +214,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_RFO", - "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", "SampleAfterValue": "200003", "UMask": "0xe2", "Unit": "cpu_core" @@ -227,7 +224,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", - "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", "SampleAfterValue": "200003", "UMask": "0xc4", "Unit": "cpu_core" @@ -237,7 +234,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", - "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", "SampleAfterValue": "200003", "UMask": "0x24", "Unit": "cpu_core" @@ -247,7 +244,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", "SampleAfterValue": "200003", "UMask": "0xc1", "Unit": "cpu_core" @@ -257,7 +254,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", - "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", + "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", "SampleAfterValue": "200003", "UMask": "0x21", "Unit": "cpu_core" @@ -267,7 +264,6 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HWPF_MISS", - "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x30", "Unit": "cpu_core" @@ -277,7 +273,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", "SampleAfterValue": "200003", "UMask": "0x3f", "Unit": "cpu_core" @@ -287,7 +283,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.REFERENCES", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]", "SampleAfterValue": "200003", "UMask": "0xff", "Unit": "cpu_core" @@ -297,7 +293,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", "SampleAfterValue": "200003", "UMask": "0xc2", "Unit": "cpu_core" @@ -307,7 +303,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", "SampleAfterValue": "200003", "UMask": "0x22", "Unit": "cpu_core" @@ -317,7 +313,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_HIT", - "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", + "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", "SampleAfterValue": "200003", "UMask": "0xc8", "Unit": "cpu_core" @@ -327,7 +323,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_MISS", - "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", + "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", "SampleAfterValue": "200003", "UMask": "0x28", "Unit": "cpu_core" @@ -337,7 +333,7 @@ "Counter": "0,1,2,3", "EventCode": "0x23", "EventName": "L2_TRANS.L2_WB", - "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts L2 writebacks that access L2 cache.", "SampleAfterValue": "200003", "UMask": "0x40", "Unit": "cpu_core" @@ -357,7 +353,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", - "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", "SampleAfterValue": "100003", "UMask": "0x41", "Unit": "cpu_core" @@ -377,7 +373,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", "SampleAfterValue": "100003", "UMask": "0x4f", "Unit": "cpu_core" @@ -552,7 +548,7 @@ "Counter": "0,1,2,3", "EventCode": "0x43", "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY", - "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0", + "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)", "SampleAfterValue": "1000003", "UMask": "0xfd", "Unit": "cpu_core" @@ -853,7 +849,6 @@ "Counter": "0,1,2,3", "EventCode": "0x44", "EventName": "MEM_STORE_RETIRED.L2_HIT", - "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1", "Unit": "cpu_core" @@ -1050,7 +1045,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe5", "EventName": "MEM_UOP_RETIRED.ANY", - "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0", + "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" @@ -1068,6 +1063,30 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts writebacks of modified cachelines that hit in the L3 or were snooped from another core's caches.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.COREWB_M.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1F803C0008", + "PublicDescription": "Counts writebacks of modified cachelines that hit in the L3 or were snooped from another core's caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts writebacks of non-modified cachelines that hit in the L3 or were snooped from another core's caches.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.COREWB_NONM.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1F803C1000", + "PublicDescription": "Counts writebacks of non-modified cachelines that hit in the L3 or were snooped from another core's caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", @@ -1308,6 +1327,18 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts all data read, code read, RFO and ITOM requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1F803C4477", + "PublicDescription": "Counts all data read, code read, RFO and ITOM requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", @@ -1372,7 +1403,6 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", - "PublicDescription": "OFFCORE_REQUESTS.ALL_REQUESTS Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -1382,7 +1412,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DATA_RD", - "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -1392,7 +1422,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", - "PublicDescription": "Counts both cacheable and non-cacheable code read requests. Available PDIST counters: 0", + "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -1402,7 +1432,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", - "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1412,7 +1442,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", - "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -1424,7 +1454,6 @@ "Errata": "ADL038", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", - "PublicDescription": "This event is deprecated. Refer to new event OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1436,7 +1465,6 @@ "Errata": "ADL038", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1447,7 +1475,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1458,7 +1486,6 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", - "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1469,7 +1496,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1480,7 +1507,6 @@ "Errata": "ADL038", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", - "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1490,7 +1516,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1500,7 +1526,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1510,7 +1536,7 @@ "Counter": "0,1,2,3", "EventCode": "0x2c", "EventName": "SQ_MISC.BUS_LOCK", - "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -1520,7 +1546,6 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.ANY", - "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xf", "Unit": "cpu_core" @@ -1530,7 +1555,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.NTA", - "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1540,7 +1565,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", - "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHW instructions executed.", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -1550,7 +1575,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T0", - "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -1560,7 +1585,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T1_T2", - "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json b/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json index d01f1b163ed8..62fd70f220e5 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json @@ -14,7 +14,6 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.FPDIV_ACTIVE", - "PublicDescription": "ARITH.FPDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -33,7 +32,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.FP", - "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0", + "PublicDescription": "Counts all microcode Floating Point assists.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -43,7 +42,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.SSE_AVX_MIX", - "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -53,7 +51,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_0", - "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -63,7 +60,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_1", - "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -73,7 +69,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_5", - "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -83,7 +78,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V0", - "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -93,7 +87,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V1", - "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -103,7 +96,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V2", - "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -113,7 +105,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -123,7 +115,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -133,7 +125,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -143,7 +135,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -153,7 +145,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x18", "Unit": "cpu_core" @@ -163,7 +155,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", - "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" @@ -173,7 +165,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -183,7 +175,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -193,7 +185,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.VECTOR", - "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "1000003", "UMask": "0xfc", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json index dae3174a74fb..ff3b30c2619a 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json @@ -14,7 +14,7 @@ "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "BACLEARS.ANY", - "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -24,7 +24,7 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.LCP", - "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", "SampleAfterValue": "500009", "UMask": "0x1", "Unit": "cpu_core" @@ -34,7 +34,6 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.MS_BUSY", - "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x2", "Unit": "cpu_core" @@ -44,7 +43,7 @@ "Counter": "0,1,2,3", "EventCode": "0x61", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -302,7 +301,7 @@ "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALLS", - "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.", "SampleAfterValue": "500009", "UMask": "0x4", "Unit": "cpu_core" @@ -314,7 +313,6 @@ "EdgeDetect": "1", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALL_PERIODS", - "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x4", "Unit": "cpu_core" @@ -324,7 +322,7 @@ "Counter": "0,1,2,3", "EventCode": "0x83", "EventName": "ICACHE_TAG.STALLS", - "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", "SampleAfterValue": "200003", "UMask": "0x4", "Unit": "cpu_core" @@ -335,7 +333,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -346,7 +344,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -356,7 +354,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.DSB_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -367,7 +365,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -378,7 +376,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -388,7 +386,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -399,7 +397,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES_ANY", - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", "SampleAfterValue": "2000003", "UMask": "0x20", "Unit": "cpu_core" @@ -411,7 +409,7 @@ "EdgeDetect": "1", "EventCode": "0x79", "EventName": "IDQ.MS_SWITCHES", - "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -421,7 +419,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", - "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Available PDIST counters: 0", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS).", "SampleAfterValue": "1000003", "UMask": "0x20", "Unit": "cpu_core" @@ -431,7 +429,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -442,7 +440,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -454,7 +452,7 @@ "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -464,7 +462,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -475,7 +473,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -487,7 +485,7 @@ "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/memory.json b/tools/perf/pmu-events/arch/x86/alderlake/memory.json index 07f5786bdbc0..a0260d5b8619 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/memory.json @@ -5,7 +5,6 @@ "CounterMask": "6", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", - "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x6", "Unit": "cpu_core" @@ -79,7 +78,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -90,7 +89,6 @@ "CounterMask": "2", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS", - "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -101,7 +99,6 @@ "CounterMask": "3", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS", - "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" @@ -112,7 +109,7 @@ "CounterMask": "5", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS", - "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", + "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_core" @@ -123,7 +120,7 @@ "CounterMask": "9", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS", - "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", + "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", "SampleAfterValue": "1000003", "UMask": "0x9", "Unit": "cpu_core" @@ -417,7 +414,6 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -427,7 +423,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0", + "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/other.json b/tools/perf/pmu-events/arch/x86/alderlake/other.json index 5f64138edfe4..af46cde26b54 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/other.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/other.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.HARDWARE", - "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count. Available PDIST counters: 0", + "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -14,7 +14,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.PAGE_FAULT", - "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -24,7 +23,6 @@ "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "CORE_POWER.LICENSE_1", - "PublicDescription": "CORE_POWER.LICENSE_1 Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_core" @@ -34,7 +32,6 @@ "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "CORE_POWER.LICENSE_2", - "PublicDescription": "CORE_POWER.LICENSE_2 Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4", "Unit": "cpu_core" @@ -44,7 +41,6 @@ "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "CORE_POWER.LICENSE_3", - "PublicDescription": "CORE_POWER.LICENSE_3 Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x8", "Unit": "cpu_core" @@ -113,7 +109,7 @@ "CounterMask": "1", "EventCode": "0x2d", "EventName": "XQ.FULL_CYCLES", - "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json index 48ef2a8cc49a..33d1f39e441f 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json @@ -6,7 +6,6 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.DIVIDER_ACTIVE", - "PublicDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9", "Unit": "cpu_core" @@ -27,7 +26,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.DIV_ACTIVE", - "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", "SampleAfterValue": "1000003", "UMask": "0x9", "Unit": "cpu_core" @@ -57,7 +56,6 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.FP_DIVIDER_ACTIVE", - "PublicDescription": "This event is deprecated. Refer to new event ARITH.FPDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -78,7 +76,6 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.IDIV_ACTIVE", - "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -108,7 +105,6 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.INT_DIVIDER_ACTIVE", - "PublicDescription": "This event is deprecated. Refer to new event ARITH.IDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -118,7 +114,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.ANY", - "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.", "SampleAfterValue": "100003", "UMask": "0x1b", "Unit": "cpu_core" @@ -549,7 +545,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C01", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -559,7 +555,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C02", - "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", + "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", "SampleAfterValue": "2000003", "UMask": "0x20", "Unit": "cpu_core" @@ -569,7 +565,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C0_WAIT", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", "SampleAfterValue": "2000003", "UMask": "0x70", "Unit": "cpu_core" @@ -597,7 +593,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED", - "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", + "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -607,7 +603,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0", + "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.", "SampleAfterValue": "25003", "UMask": "0x2", "Unit": "cpu_core" @@ -617,7 +613,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE", - "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40", "Unit": "cpu_core" @@ -629,7 +624,6 @@ "EdgeDetect": "1", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", - "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40", "Unit": "cpu_core" @@ -649,7 +643,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED", - "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", + "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -687,7 +681,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -724,7 +718,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", "SampleAfterValue": "2000003", "Unit": "cpu_core" }, @@ -734,7 +728,6 @@ "CounterMask": "8", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", - "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -745,7 +738,6 @@ "CounterMask": "1", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", - "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -756,7 +748,6 @@ "CounterMask": "16", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", - "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -767,7 +758,6 @@ "CounterMask": "12", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", - "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xc", "Unit": "cpu_core" @@ -778,7 +768,6 @@ "CounterMask": "5", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", - "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_core" @@ -789,7 +778,6 @@ "CounterMask": "4", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", - "PublicDescription": "Total execution stalls. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -799,7 +787,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -809,7 +797,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL", - "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0xc", "Unit": "cpu_core" @@ -819,7 +806,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -829,7 +816,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", - "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -839,7 +826,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", - "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -850,7 +837,6 @@ "CounterMask": "5", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", - "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x21", "Unit": "cpu_core" @@ -861,7 +847,7 @@ "CounterMask": "2", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", - "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", "SampleAfterValue": "1000003", "UMask": "0x40", "Unit": "cpu_core" @@ -871,7 +857,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", - "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0", + "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", "SampleAfterValue": "1000003", "UMask": "0x80", "Unit": "cpu_core" @@ -881,7 +867,7 @@ "Counter": "0,1,2,3", "EventCode": "0x75", "EventName": "INST_DECODED.DECODERS", - "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -927,7 +913,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", - "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -937,7 +922,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions Available PDIST counters: 0", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -956,7 +941,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -968,7 +953,7 @@ "EdgeDetect": "1", "EventCode": "0xad", "EventName": "INT_MISC.CLEARS_COUNT", - "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", "SampleAfterValue": "500009", "UMask": "0x1", "Unit": "cpu_core" @@ -978,7 +963,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", - "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", "SampleAfterValue": "500009", "UMask": "0x80", "Unit": "cpu_core" @@ -988,7 +973,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.RECOVERY_CYCLES", - "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", "SampleAfterValue": "500009", "UMask": "0x1", "Unit": "cpu_core" @@ -1000,7 +985,6 @@ "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", "MSRIndex": "0x3F7", "MSRValue": "0x7", - "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40", "Unit": "cpu_core" @@ -1010,7 +994,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.UOP_DROPPING", - "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1020,7 +1004,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.128BIT", - "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x13", "Unit": "cpu_core" @@ -1030,7 +1013,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.256BIT", - "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xac", "Unit": "cpu_core" @@ -1040,7 +1022,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_128", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" @@ -1050,7 +1032,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_256", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", "SampleAfterValue": "1000003", "UMask": "0xc", "Unit": "cpu_core" @@ -1060,7 +1042,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.MUL_256", - "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80", "Unit": "cpu_core" @@ -1070,7 +1051,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.SHUFFLES", - "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40", "Unit": "cpu_core" @@ -1080,7 +1060,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_128", - "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1090,7 +1069,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_256", - "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20", "Unit": "cpu_core" @@ -1119,7 +1097,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", - "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -1138,7 +1116,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.NO_SR", - "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", "SampleAfterValue": "100003", "UMask": "0x88", "Unit": "cpu_core" @@ -1148,7 +1126,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", "SampleAfterValue": "100003", "UMask": "0x82", "Unit": "cpu_core" @@ -1158,7 +1136,7 @@ "Counter": "0,1,2,3", "EventCode": "0x4c", "EventName": "LOAD_HIT_PREFETCH.SWPF", - "PublicDescription": "Counts all software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0", + "PublicDescription": "Counts all software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1169,7 +1147,7 @@ "CounterMask": "1", "EventCode": "0xa8", "EventName": "LSD.CYCLES_ACTIVE", - "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1180,7 +1158,7 @@ "CounterMask": "6", "EventCode": "0xa8", "EventName": "LSD.CYCLES_OK", - "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1190,7 +1168,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa8", "EventName": "LSD.UOPS", - "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1202,7 +1180,7 @@ "EdgeDetect": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.COUNT", - "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0", + "PublicDescription": "Counts the number of machine clears (nukes) of any type.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1258,7 +1236,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SMC", - "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -1268,7 +1246,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe0", "EventName": "MISC2_RETIRED.LFENCE", - "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0", + "PublicDescription": "number of LFENCE retired instructions", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -1288,7 +1266,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcc", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -1298,7 +1276,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SB", - "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -1308,7 +1286,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SCOREBOARD", - "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -1318,7 +1295,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", "EventName": "RS.EMPTY", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", "SampleAfterValue": "1000003", "UMask": "0x7", "Unit": "cpu_core" @@ -1331,7 +1308,7 @@ "EventCode": "0xa5", "EventName": "RS.EMPTY_COUNT", "Invert": "1", - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", "SampleAfterValue": "100003", "UMask": "0x7", "Unit": "cpu_core" @@ -1341,7 +1318,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", "EventName": "RS.EMPTY_RESOURCE", - "PublicDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1355,7 +1331,6 @@ "EventCode": "0xa5", "EventName": "RS_EMPTY.COUNT", "Invert": "1", - "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x7", "Unit": "cpu_core" @@ -1366,7 +1341,6 @@ "Deprecated": "1", "EventCode": "0xa5", "EventName": "RS_EMPTY.CYCLES", - "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x7", "Unit": "cpu_core" @@ -1395,7 +1369,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", - "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources. Available PDIST counters: 0", + "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.", "SampleAfterValue": "10000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1405,7 +1379,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BAD_SPEC_SLOTS", - "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0", + "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.", "SampleAfterValue": "10000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1415,7 +1389,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", - "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", "SampleAfterValue": "10000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1425,7 +1399,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", - "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1444,7 +1417,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.SLOTS_P", - "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", "SampleAfterValue": "10000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1661,7 +1634,6 @@ "Counter": "0,1,2,3", "EventCode": "0x76", "EventName": "UOPS_DECODED.DEC0_UOPS", - "PublicDescription": "UOPS_DECODED.DEC0_UOPS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1671,7 +1643,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_0", - "PublicDescription": "Number of uops dispatch to execution port 0. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution port 0.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1681,7 +1653,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_1", - "PublicDescription": "Number of uops dispatch to execution port 1. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution port 1.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1691,7 +1663,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_2_3_10", - "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1701,7 +1673,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_4_9", - "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 4 and 9", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1711,7 +1683,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_5_11", - "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 5 and 11", "SampleAfterValue": "2000003", "UMask": "0x20", "Unit": "cpu_core" @@ -1721,7 +1693,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_6", - "PublicDescription": "Number of uops dispatch to execution port 6. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution port 6.", "SampleAfterValue": "2000003", "UMask": "0x40", "Unit": "cpu_core" @@ -1731,7 +1703,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_7_8", - "PublicDescription": "Number of uops dispatch to execution ports 7 and 8. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 7 and 8.", "SampleAfterValue": "2000003", "UMask": "0x80", "Unit": "cpu_core" @@ -1742,7 +1714,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1753,7 +1725,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1764,7 +1736,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1775,7 +1747,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1786,7 +1758,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_1", - "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1797,7 +1769,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_2", - "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1808,7 +1780,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_3", - "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1819,7 +1791,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_4", - "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1831,7 +1803,7 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALLS", "Invert": "1", - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1844,7 +1816,6 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALL_CYCLES", "Invert": "1", - "PublicDescription": "This event is deprecated. Refer to new event UOPS_EXECUTED.STALLS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1854,7 +1825,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.THREAD", - "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1864,7 +1834,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.X87", - "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of x87 uops executed.", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1883,7 +1853,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xae", "EventName": "UOPS_ISSUED.ANY", - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1894,7 +1864,6 @@ "CounterMask": "1", "EventCode": "0xae", "EventName": "UOPS_ISSUED.CYCLES", - "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1913,7 +1882,7 @@ "CounterMask": "1", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.CYCLES", - "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where at least one uop has retired.", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1923,7 +1892,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.HEAVY", - "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0", + "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1954,7 +1923,6 @@ "EventName": "UOPS_RETIRED.MS", "MSRIndex": "0x3F7", "MSRValue": "0x8", - "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1964,7 +1932,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.SLOTS", - "PublicDescription": "Counts the retirement slots used each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the retirement slots used each cycle.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1976,7 +1944,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALLS", "Invert": "1", - "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0", + "PublicDescription": "This event counts cycles without actually retired uops.", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1989,7 +1957,6 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALL_CYCLES", "Invert": "1", - "PublicDescription": "This event is deprecated. Refer to new event UOPS_RETIRED.STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/alderlake/uncore-interconnect.json index 7c0779c74154..b5604c7534e1 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/uncore-interconnect.json @@ -65,7 +65,6 @@ "Counter": "0,1", "EventCode": "0x81", "EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD", - "Experimental": "1", "PerPkg": "1", "UMask": "0x2", "Unit": "ARB" @@ -103,7 +102,6 @@ "Counter": "0,1", "EventCode": "0x81", "EventName": "UNC_ARB_TRK_REQUESTS.RD", - "Experimental": "1", "PerPkg": "1", "UMask": "0x2", "Unit": "ARB" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json index ffbbd08acc68..132ce48af6d9 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", - "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -15,7 +15,7 @@ "CounterMask": "1", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -35,7 +35,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" @@ -45,7 +45,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -55,7 +55,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -65,7 +65,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -75,7 +75,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -85,7 +85,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.STLB_HIT", - "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -96,7 +96,7 @@ "CounterMask": "1", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -116,7 +116,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" @@ -126,7 +126,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -136,7 +136,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -146,7 +146,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -156,7 +156,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -184,7 +184,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.STLB_HIT", - "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -195,7 +195,7 @@ "CounterMask": "1", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -215,7 +215,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" @@ -225,7 +225,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -235,7 +235,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -245,7 +245,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index ce93648043ef..0f72c9192df6 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -1,56 +1,56 @@ [ { "BriefDescription": "C10 residency percent per package", - "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c10\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C10_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C1 residency percent per core", - "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricExpr": "cstate_core@c1\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C1_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C8 residency percent per package", - "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c8\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C8_Pkg_Residency", "ScaleUnit": "100%" @@ -460,12 +460,12 @@ }, { "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricName": "tma_info_system_cpu_utilization" }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE_P@k / CPU_CLK_UNHALTED.CORE", + "MetricExpr": "CPU_CLK_UNHALTED.CORE_P:k / CPU_CLK_UNHALTED.CORE", "MetricGroup": "Summary", "MetricName": "tma_info_system_kernel_utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/alderlaken/uncore-interconnect.json index 7c0779c74154..b5604c7534e1 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/uncore-interconnect.json @@ -65,7 +65,6 @@ "Counter": "0,1", "EventCode": "0x81", "EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD", - "Experimental": "1", "PerPkg": "1", "UMask": "0x2", "Unit": "ARB" @@ -103,7 +102,6 @@ "Counter": "0,1", "EventCode": "0x81", "EventName": "UNC_ARB_TRK_REQUESTS.RD", - "Experimental": "1", "PerPkg": "1", "UMask": "0x2", "Unit": "ARB" diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json b/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json index b22a02450e6c..4f1f77404943 100644 --- a/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json @@ -1,56 +1,56 @@ [ { "BriefDescription": "C10 residency percent per package", - "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c10\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C10_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C1 residency percent per core", - "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricExpr": "cstate_core@c1\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C1_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C8 residency percent per package", - "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c8\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C8_Pkg_Residency", "ScaleUnit": "100%" @@ -567,7 +567,7 @@ }, { "BriefDescription": "Average CPU Utilization", - "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.REF_TSC@ / TSC", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.REF_TSC@ / msr@tsc\\,cpu=cpu_atom@", "MetricName": "tma_info_system_cpu_utilization", "Unit": "cpu_atom" }, @@ -774,7 +774,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -786,7 +786,7 @@ { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "cpu_core@topdown\\-bad\\-spec@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-bad\\-spec@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -813,35 +813,35 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ", + "Unit": "cpu_core" + }, + { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_early_blk + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "MetricName": "tma_bottleneck_data_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_capacity / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_early_blk + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_capacity / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_early_blk + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_early_blk + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_early_blk + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "MetricName": "tma_bottleneck_data_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_bottleneck_compute_bound_est", - "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ", - "Unit": "cpu_core" - }, - { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20", @@ -849,7 +849,7 @@ }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -858,7 +858,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_early_blk + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -885,7 +885,7 @@ }, { "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_data_cache_memory_bandwidth + tma_bottleneck_data_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", @@ -902,7 +902,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", @@ -1042,7 +1042,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@R, 25 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", @@ -1095,7 +1094,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(cpu_core@IDQ.DSB_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ + cpu_core@IDQ.DSB_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", + "MetricExpr": "(cpu_core@IDQ.DSB_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / 2 + cpu_core@IDQ.DSB_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.STARVATION_CYCLES@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", @@ -1149,7 +1148,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1166,7 +1165,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -1216,7 +1215,7 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)", + "MetricExpr": "cpu_core@FP_ARITH_OPS_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", @@ -1226,7 +1225,7 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)", + "MetricExpr": "cpu_core@FP_ARITH_OPS_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", @@ -1236,7 +1235,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", + "MetricExpr": "(cpu_core@FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_OPS_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -1246,7 +1245,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR\\,umask\\=0x30@ / (tma_retiring * tma_info_thread_slots)", + "MetricExpr": "cpu_core@FP_ARITH_OPS_RETIRED.VECTOR\\,umask\\=0x30@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -1257,7 +1256,7 @@ { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -1278,7 +1277,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", @@ -1456,7 +1455,7 @@ }, { "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / tma_info_thread_clks", + "MetricExpr": "(cpu_core@FP_ARITH_OPS_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_OPS_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE@) / tma_info_thread_clks", "MetricGroup": "Flops;Ret", "MetricName": "tma_info_core_flopc", "Unit": "cpu_core" @@ -1597,7 +1596,7 @@ }, { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + cpu_core@FP_ARITH_INST_RETIRED.VECTOR@)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_OPS_RETIRED.SCALAR@ + cpu_core@FP_ARITH_OPS_RETIRED.VECTOR@)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", @@ -1606,7 +1605,7 @@ }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_OPS_RETIRED.128B_PACKED_SINGLE@)", "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", @@ -1615,7 +1614,7 @@ }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_OPS_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE@)", "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", @@ -1624,7 +1623,7 @@ }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@FP_ARITH_OPS_RETIRED.SCALAR_DOUBLE@", "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", @@ -1633,7 +1632,7 @@ }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@FP_ARITH_OPS_RETIRED.SCALAR_SINGLE@", "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", @@ -1658,7 +1657,7 @@ }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_OPS_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_OPS_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE@)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_ipflop", "MetricThreshold": "tma_info_inst_mix_ipflop < 10", @@ -1713,7 +1712,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * cpu_core@L1D.REPLACEMENT@ / 1e9 / tma_info_system_time", + "MetricExpr": "64 * cpu_core@L1D.L1_REPLACEMENT@ / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw", "Unit": "cpu_core" @@ -1726,6 +1725,13 @@ "Unit": "cpu_core" }, { + "BriefDescription": "L0 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * (cpu_core@MEM_LOAD_RETIRED.L1_MISS@ + cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@) / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l1dl0_mpki", + "Unit": "cpu_core" + }, + { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / cpu_core@INST_RETIRED.ANY@", "MetricGroup": "CacheHits;Mem", @@ -1941,6 +1947,13 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Average number of uops fetched from MS per cycle", + "MetricExpr": "cpu_core@IDQ.MS_UOPS@ / cpu_core@IDQ.MS_UOPS\\,cmask\\=1@", + "MetricGroup": "Fed;FetchLat;MicroSeq", + "MetricName": "tma_info_pipeline_fetch_ms", + "Unit": "cpu_core" + }, + { "BriefDescription": "Instructions per a microcode Assist invocation", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", @@ -1974,7 +1987,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc\\,cpu=cpu_core@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency", "Unit": "cpu_core" @@ -1988,14 +2001,22 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.REF_TSC@ / TSC", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.REF_TSC@ / msr@tsc\\,cpu=cpu_core@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized", "Unit": "cpu_core" }, { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "32 * UNC_M_TOTAL_DATA / 1e9 / tma_info_system_time", + "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full", + "Unit": "cpu_core" + }, + { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / 1e9 / tma_info_system_time", + "MetricExpr": "(cpu_core@FP_ARITH_OPS_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_OPS_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE@) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width", @@ -2062,6 +2083,13 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]", + "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time", + "MetricGroup": "SoC", + "MetricName": "tma_info_system_uncore_frequency", + "Unit": "cpu_core" + }, + { "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "Pipeline", @@ -2182,12 +2210,12 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", - "MetricExpr": "4 * cpu_core@DEPENDENT_LOADS.ANY@ / tma_info_thread_clks", + "BriefDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "MetricExpr": "4 * cpu_core@DEPENDENT_LOADS.ANY\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2203,7 +2231,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@R, 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", @@ -2224,12 +2251,11 @@ }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@R, 9 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_data_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2311,6 +2337,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@MEM_INST_RETIRED.LOCK_LOADS@R / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", @@ -2321,7 +2348,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit", - "MetricExpr": "cpu_core@LSD.UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks", + "MetricExpr": "cpu_core@LSD.UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks / 2", "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", @@ -2346,7 +2373,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2356,13 +2383,13 @@ "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -2373,7 +2400,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", @@ -2412,7 +2438,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / 2 + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", + "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / 2 + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.STARVATION_CYCLES@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", @@ -2432,7 +2458,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", - "MetricExpr": "cpu_core@IDQ.MS_CYCLES_ANY@ / tma_info_thread_clks", + "MetricExpr": "cpu_core@IDQ.MS_CYCLES_ANY@ / tma_info_thread_clks / 1.8", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -2471,7 +2497,8 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", - "MetricExpr": "max(0, tma_light_operations - (tma_x87_use + (cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + cpu_core@FP_ARITH_INST_RETIRED.VECTOR@) / (tma_retiring * tma_info_thread_slots) + (cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@ + cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_thread_slots) + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "max(0, tma_light_operations - (tma_x87_use + (cpu_core@FP_ARITH_OPS_RETIRED.SCALAR@ + cpu_core@FP_ARITH_OPS_RETIRED.VECTOR@) / (tma_retiring * tma_info_thread_slots) + (cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@ + cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_thread_slots) + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6", @@ -2509,6 +2536,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "((cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", @@ -2519,6 +2547,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_THRESHOLD_AND_NMI", "MetricExpr": "cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", @@ -2529,6 +2558,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_THRESHOLD_AND_NMI", "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", @@ -2539,7 +2569,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", @@ -2550,7 +2579,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", @@ -2571,7 +2599,7 @@ { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2586,7 +2614,7 @@ "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", + "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2602,7 +2630,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", @@ -2637,7 +2664,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2652,6 +2679,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "This metric estimates clocks wasted due to loads blocked due to unknown store address (did not do memory disambiguation) or due to unknown store data", + "MetricExpr": "7 * cpu_core@LD_BLOCKS.STORE_EARLY\\,cmask\\=1@ / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_early_blk", + "MetricThreshold": "tma_store_early_blk > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/cache.json b/tools/perf/pmu-events/arch/x86/arrowlake/cache.json index 91929d8bcf47..30dd56b487ba 100644 --- a/tools/perf/pmu-events/arch/x86/arrowlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/arrowlake/cache.json @@ -29,6 +29,16 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Cachelines replaced into the L1 d-cache. Successful replacements only (not blocked) and exclude WB-miss case", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x51", + "EventName": "L1D.L1_REPLACEMENT", + "PublicDescription": "Counts cachelines replaced into the L1 d-cache.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { "BriefDescription": "Cachelines replaced into the L0 and L1 d-cache. Successful replacements only (not blocked) and exclude WB-miss case", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x51", @@ -540,7 +550,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PublicDescription": "Counts Instructions with at least one architecturally visible load retired. Available PDIST counters: 0", + "PublicDescription": "Counts Instructions with at least one architecturally visible load retired. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x81", "Unit": "cpu_core" @@ -551,7 +561,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0", + "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x82", "Unit": "cpu_core" @@ -561,7 +571,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_SWPF", - "PublicDescription": "Counts all retired software prefetch instructions. Available PDIST counters: 0", + "PublicDescription": "Counts all retired software prefetch instructions. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x84", "Unit": "cpu_core" @@ -572,7 +582,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0", + "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x87", "Unit": "cpu_core" @@ -583,7 +593,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x21", "Unit": "cpu_core" @@ -594,7 +604,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0x41", "Unit": "cpu_core" @@ -605,18 +615,29 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0x42", "Unit": "cpu_core" }, { + "BriefDescription": "Retired instructions that hit the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_HIT_ANY", + "PublicDescription": "Number of retired instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0xf", + "Unit": "cpu_core" + }, + { "BriefDescription": "Retired load instructions that hit the STLB.", "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS", - "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0", + "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0x9", "Unit": "cpu_core" @@ -627,18 +648,39 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES", - "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0", + "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0xa", "Unit": "cpu_core" }, { + "BriefDescription": "Retired SWPF instructions that hit the STLB.", + "Counter": "0,1,2,3", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_HIT_SWPF", + "PublicDescription": "Number of retired SWPF instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0xc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that miss the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_ANY", + "PublicDescription": "Retired instructions that miss the STLB. Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x17", + "Unit": "cpu_core" + }, + { "BriefDescription": "Retired load instructions that miss the STLB.", "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", + "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0x11", "Unit": "cpu_core" @@ -649,18 +691,28 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", + "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0x12", "Unit": "cpu_core" }, { + "BriefDescription": "Retired SWPF instructions that miss the STLB.", + "Counter": "0,1,2,3", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_SWPF", + "PublicDescription": "Number of retired SWPF instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x14", + "Unit": "cpu_core" + }, + { "BriefDescription": "Retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$)", "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$) Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$) Available PDIST counters: 0,1", "SampleAfterValue": "20011", "UMask": "0x10", "Unit": "cpu_core" @@ -671,7 +723,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", - "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded. Available PDIST counters: 0,1", "SampleAfterValue": "20011", "UMask": "0x4", "Unit": "cpu_core" @@ -682,7 +734,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0,1", "SampleAfterValue": "20011", "UMask": "0x1", "Unit": "cpu_core" @@ -693,7 +745,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0,1", "SampleAfterValue": "20011", "UMask": "0x2", "Unit": "cpu_core" @@ -704,7 +756,7 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x4", "Unit": "cpu_core" @@ -715,7 +767,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x40", "Unit": "cpu_core" @@ -726,7 +778,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x101", "Unit": "cpu_core" @@ -737,7 +789,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT_L0", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the Level 0 of the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the Level 0 of the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -747,7 +799,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT_L1", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the Level 1 of the L1 data cache. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the Level 1 of the L1 data cache. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "Unit": "cpu_core" }, @@ -757,7 +809,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0,1", "SampleAfterValue": "200003", "UMask": "0x8", "Unit": "cpu_core" @@ -768,7 +820,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0,1", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_core" @@ -779,7 +831,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0,1", "SampleAfterValue": "100021", "UMask": "0x10", "Unit": "cpu_core" @@ -790,7 +842,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0,1", "SampleAfterValue": "100021", "UMask": "0x4", "Unit": "cpu_core" @@ -801,7 +853,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0,1", "SampleAfterValue": "50021", "UMask": "0x20", "Unit": "cpu_core" @@ -1029,7 +1081,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024", @@ -1053,7 +1105,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", @@ -1077,7 +1129,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", @@ -1089,7 +1141,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048", @@ -1113,7 +1165,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", @@ -1137,7 +1189,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", @@ -1161,7 +1213,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", @@ -1185,7 +1237,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", @@ -1209,7 +1261,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", @@ -1233,7 +1285,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", @@ -1384,8 +1436,32 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts writebacks of modified cachelines that hit in the L3 or were snooped from another core's caches.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.COREWB_M.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x7E001E00008", + "PublicDescription": "Counts writebacks of modified cachelines that hit in the L3 or were snooped from another core's caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts writebacks of non-modified cachelines that hit in the L3 or were snooped from another core's caches.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.COREWB_NONM.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x7E001E01000", + "PublicDescription": "Counts writebacks of non-modified cachelines that hit in the L3 or were snooped from another core's caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -1397,7 +1473,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", @@ -1409,7 +1485,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches which forwarded the unmodified data to the requesting core.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -1421,7 +1497,7 @@ }, { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -1433,7 +1509,7 @@ }, { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", @@ -1444,6 +1520,18 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts all data read, code read, RFO and ITOM requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x7E001E04477", + "PublicDescription": "Counts all data read, code read, RFO and ITOM requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Any memory transaction that reached the SQ.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x21", diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json b/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json index 56cf1ec63200..db2ef84ca041 100644 --- a/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json @@ -81,7 +81,7 @@ "EventName": "FRONTEND_RETIRED.ANY_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0", + "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -93,7 +93,7 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -179,7 +179,7 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0", + "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -218,7 +218,7 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -239,7 +239,7 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -251,7 +251,7 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -263,7 +263,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x608006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -275,7 +275,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x601006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -287,7 +287,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x600206", - "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -299,7 +299,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x610006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -311,7 +311,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -323,7 +323,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x602006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -335,7 +335,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x600406", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -347,7 +347,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x620006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -359,7 +359,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x604006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -371,7 +371,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x600806", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -383,7 +383,7 @@ "EventName": "FRONTEND_RETIRED.MISP_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0", + "PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x2", "Unit": "cpu_core" @@ -395,7 +395,7 @@ "EventName": "FRONTEND_RETIRED.MS_FLOWS", "MSRIndex": "0x3F7", "MSRValue": "0x8", - "PublicDescription": "Counts flows delivered by the Microcode Sequencer Available PDIST counters: 0", + "PublicDescription": "Counts flows delivered by the Microcode Sequencer Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -443,7 +443,7 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -455,7 +455,7 @@ "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "MSRIndex": "0x3F7", "MSRValue": "0x17", - "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0", + "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/memory.json b/tools/perf/pmu-events/arch/x86/arrowlake/memory.json index fb8d4ac69bda..aba1e27e5e37 100644 --- a/tools/perf/pmu-events/arch/x86/arrowlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/arrowlake/memory.json @@ -163,7 +163,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "53", "UMask": "0x1", "Unit": "cpu_core" @@ -176,7 +176,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "1009", "UMask": "0x1", "Unit": "cpu_core" @@ -189,7 +189,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "20011", "UMask": "0x1", "Unit": "cpu_core" @@ -202,7 +202,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048", "MSRIndex": "0x3F6", "MSRValue": "0x800", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "23", "UMask": "0x1", "Unit": "cpu_core" @@ -215,7 +215,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "503", "UMask": "0x1", "Unit": "cpu_core" @@ -228,7 +228,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -241,7 +241,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -254,7 +254,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "101", "UMask": "0x1", "Unit": "cpu_core" @@ -267,7 +267,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "2003", "UMask": "0x1", "Unit": "cpu_core" @@ -280,7 +280,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "50021", "UMask": "0x1", "Unit": "cpu_core" @@ -291,7 +291,7 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -334,7 +334,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by DRAM.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -346,7 +346,7 @@ }, { "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", @@ -358,7 +358,7 @@ }, { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/other.json b/tools/perf/pmu-events/arch/x86/arrowlake/other.json index 51bc763a5887..ab7aac14e697 100644 --- a/tools/perf/pmu-events/arch/x86/arrowlake/other.json +++ b/tools/perf/pmu-events/arch/x86/arrowlake/other.json @@ -66,7 +66,7 @@ }, { "BriefDescription": "Counts streaming stores that have any type of response.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json b/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json index 18a22368b99b..0651e2c4561e 100644 --- a/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json @@ -74,13 +74,14 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "Unit": "cpu_core" }, { "BriefDescription": "Counts the total number of branch instructions retired for all branch types.", "Counter": "0,1,2,3,4,5,6,7", + "Errata": "ARL010, ARL011", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", @@ -101,7 +102,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x111", "Unit": "cpu_core" @@ -109,6 +110,7 @@ { "BriefDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches.", "Counter": "0,1,2,3,4,5,6,7", + "Errata": "ARL011", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", "SampleAfterValue": "200003", @@ -120,7 +122,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x10", "Unit": "cpu_core" @@ -139,7 +141,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x101", "Unit": "cpu_core" @@ -158,7 +160,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN_BWD", - "PublicDescription": "Counts taken backward conditional branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts taken backward conditional branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x1", "Unit": "cpu_core" @@ -168,7 +170,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN_FWD", - "PublicDescription": "Counts taken forward conditional branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts taken forward conditional branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x102", "Unit": "cpu_core" @@ -187,7 +189,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x40", "Unit": "cpu_core" @@ -195,6 +197,7 @@ { "BriefDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return.", "Counter": "0,1,2,3,4,5,6,7", + "Errata": "ARL011", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", "SampleAfterValue": "200003", @@ -215,7 +218,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", + "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -223,6 +226,7 @@ { "BriefDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired.", "Counter": "0,1,2,3,4,5,6,7", + "Errata": "ARL011", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", "SampleAfterValue": "200003", @@ -241,6 +245,7 @@ { "BriefDescription": "Counts the number of near indirect CALL branch instructions retired.", "Counter": "0,1,2,3,4,5,6,7", + "Errata": "ARL011", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT_CALL", "SampleAfterValue": "200003", @@ -270,7 +275,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x2", "Unit": "cpu_core" @@ -278,6 +283,7 @@ { "BriefDescription": "Counts the number of near CALL branch instructions retired.", "Counter": "0,1,2,3,4,5,6,7", + "Errata": "ARL010, ARL011", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", "SampleAfterValue": "200003", @@ -298,7 +304,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x8", "Unit": "cpu_core" @@ -317,7 +323,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -325,6 +331,7 @@ { "BriefDescription": "Counts the number of near taken branch instructions retired.", "Counter": "0,1,2,3,4,5,6,7", + "Errata": "ARL011", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", "SampleAfterValue": "200003", @@ -372,7 +379,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -390,7 +397,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST", - "PublicDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x44", "Unit": "cpu_core" @@ -409,7 +416,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x111", "Unit": "cpu_core" @@ -428,7 +435,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_COST", - "PublicDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x151", "Unit": "cpu_core" @@ -438,7 +445,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0", + "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x10", "Unit": "cpu_core" @@ -448,7 +455,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST", - "PublicDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x50", "Unit": "cpu_core" @@ -467,7 +474,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x101", "Unit": "cpu_core" @@ -486,7 +493,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD", - "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x1", "Unit": "cpu_core" @@ -496,7 +503,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD_COST", - "PublicDescription": "number of branch instructions retired that were mispredicted and taken backward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "number of branch instructions retired that were mispredicted and taken backward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x8001", "Unit": "cpu_core" @@ -506,7 +513,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST", - "PublicDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x141", "Unit": "cpu_core" @@ -516,7 +523,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD", - "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -525,7 +532,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD_COST", - "PublicDescription": "number of branch instructions retired that were mispredicted and taken forward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "number of branch instructions retired that were mispredicted and taken forward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x8002", "Unit": "cpu_core" @@ -544,7 +551,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", + "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -572,7 +579,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0", + "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x2", "Unit": "cpu_core" @@ -591,7 +598,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST", - "PublicDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x42", "Unit": "cpu_core" @@ -601,7 +608,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_COST", - "PublicDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0xc0", "Unit": "cpu_core" @@ -620,7 +627,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -639,7 +646,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST", - "PublicDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x60", "Unit": "cpu_core" @@ -649,7 +656,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x8", "Unit": "cpu_core" @@ -677,7 +684,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET_COST", - "PublicDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x48", "Unit": "cpu_core" @@ -1046,7 +1053,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 0", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 0,1", "SampleAfterValue": "2000003", "Unit": "cpu_core" }, @@ -1063,7 +1070,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.BR_FUSED", - "PublicDescription": "retired macro-fused uops when there is a branch in the macro-fused pair (the two instructions that got macro-fused count once in this pmon) Available PDIST counters: 0", + "PublicDescription": "retired macro-fused uops when there is a branch in the macro-fused pair (the two instructions that got macro-fused count once in this pmon) Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1073,7 +1080,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", - "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0", + "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0,1", "SampleAfterValue": "2000003", "UMask": "0x30", "Unit": "cpu_core" @@ -1083,7 +1090,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0,1", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1102,7 +1109,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0,1", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1349,6 +1356,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of times a load got early blocked due to preceding store operation with unknown address or unknown data. Excluding in-line (immediate) wakeups", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_EARLY", + "SampleAfterValue": "100003", + "UMask": "0xa1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of occurrences a retired load gets blocked because its address partially overlaps with an older store (size mismatch) - unknown_sta/bad_forward", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x03", @@ -1563,7 +1579,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xe4", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PublicDescription": "LBR record is inserted Available PDIST counters: 0", + "PublicDescription": "LBR record is inserted Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1929,7 +1945,7 @@ }, { "BriefDescription": "Fixed Counter: Counts the number of retirement slots not consumed due to front end stalls.", - "Counter": "37", + "Counter": "Fixed counter 5", "EventName": "TOPDOWN_FE_BOUND.ALL", "SampleAfterValue": "1000003", "UMask": "0x6", @@ -2126,7 +2142,7 @@ }, { "BriefDescription": "Fixed Counter: Counts the number of consumed retirement slots.", - "Counter": "38", + "Counter": "Fixed counter 6", "EventName": "TOPDOWN_RETIRING.ALL", "SampleAfterValue": "1000003", "UMask": "0x7", diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index 89750117a7f6..1d8e910f5961 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -1,49 +1,49 @@ [ { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricExpr": "cstate_core@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" @@ -80,7 +80,6 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -98,7 +97,6 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", @@ -139,7 +137,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", @@ -640,7 +637,7 @@ "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -653,7 +650,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -665,7 +662,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, @@ -854,7 +851,6 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", @@ -1032,7 +1028,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1041,7 +1037,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1050,7 +1046,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index 81175f0f2603..a5e408ca46a7 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -1,49 +1,49 @@ [ { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricExpr": "cstate_core@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" @@ -80,7 +80,6 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -98,7 +97,6 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", @@ -139,7 +137,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", @@ -632,7 +629,7 @@ "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -645,7 +642,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -657,7 +654,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, @@ -846,7 +843,6 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", @@ -1021,7 +1017,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1030,7 +1026,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1039,7 +1035,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 5d06a3f72be2..5b83b040060c 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -1,49 +1,49 @@ [ { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricExpr": "cstate_core@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" @@ -282,7 +282,6 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -300,7 +299,6 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", @@ -341,7 +339,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", @@ -842,7 +839,7 @@ "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -855,7 +852,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -867,7 +864,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, @@ -907,6 +904,7 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", @@ -1076,7 +1074,6 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", @@ -1086,6 +1083,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", @@ -1263,7 +1261,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1272,7 +1270,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1281,7 +1279,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1308,6 +1306,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 6485b565acbc..2e50a91b6728 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -1,49 +1,49 @@ [ { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricExpr": "cstate_core@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" @@ -319,6 +319,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -356,6 +357,7 @@ }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", @@ -370,31 +372,35 @@ "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" }, { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " + }, + { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "MetricName": "tma_bottleneck_data_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)) + tma_memory_bound * (tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "MetricName": "tma_bottleneck_data_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_bottleneck_compute_bound_est", - "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", @@ -402,6 +408,7 @@ }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", @@ -410,7 +417,8 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -418,7 +426,8 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", @@ -426,6 +435,7 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", @@ -434,7 +444,8 @@ }, { "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_data_cache_memory_bandwidth + tma_bottleneck_data_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", @@ -442,6 +453,7 @@ }, { "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -469,6 +481,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", @@ -539,6 +552,15 @@ "ScaleUnit": "100%" }, { + "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external CXL Memory by loads (e.g", + "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0))) if #has_pmem > 0 else 1)) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", + "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_cxl_mem_bound", + "MetricThreshold": "tma_cxl_mem_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external CXL Memory by loads (e.g. 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory, PMM - Persistent Memory Module [from CLX to SPR] or any other CXL Type3 Memory [EMR onwards]).", + "ScaleUnit": "100%" + }, + { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", @@ -569,7 +591,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound - tma_cxl_mem_bound if #has_pmem > 0 else CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound)", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -630,7 +652,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -693,7 +715,6 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", @@ -768,6 +789,7 @@ }, { "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 4 / BR_MISP_RETIRED.ALL_BRANCHES / 100", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", @@ -803,6 +825,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", @@ -820,6 +843,7 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", @@ -961,7 +985,6 @@ }, { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", @@ -1249,7 +1272,7 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -1267,6 +1290,12 @@ "MetricName": "tma_info_pipeline_fetch_mite" }, { + "BriefDescription": "Average number of uops fetched from MS per cycle", + "MetricExpr": "IDQ.MS_UOPS / cpu@IDQ.MS_UOPS\\,cmask\\=1@", + "MetricGroup": "Fed;FetchLat;MicroSeq", + "MetricName": "tma_info_pipeline_fetch_ms" + }, + { "BriefDescription": "Instructions per a microcode Assist invocation", "MetricExpr": "INST_RETIRED.ANY / (FP_ASSIST.ANY + OTHER_ASSISTS.ANY)", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", @@ -1282,7 +1311,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1294,16 +1323,28 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, { + "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", + "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / tma_info_system_time if #has_pmem > 0 else 0)", + "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", + "MetricName": "tma_info_system_cxl_mem_read_bw" + }, + { + "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / tma_info_system_time if #has_pmem > 0 else 0)", + "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", + "MetricName": "tma_info_system_cxl_mem_write_bw" + }, + { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", @@ -1362,6 +1403,13 @@ "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { + "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", + "MetricExpr": "(1e9 * (UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS) / imc_0@event\\=0x0@ if #has_pmem > 0 else 0)", + "MetricGroup": "MemOffcore;MemoryLat;Server;SoC", + "MetricName": "tma_info_system_mem_pmm_read_latency", + "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" + }, + { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", @@ -1499,12 +1547,13 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "BriefDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1541,7 +1590,7 @@ "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_data_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1565,6 +1614,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", @@ -1591,6 +1641,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", @@ -1599,6 +1650,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", @@ -1607,6 +1659,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", @@ -1624,6 +1677,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", @@ -1648,7 +1702,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1657,7 +1711,7 @@ "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1681,7 +1735,6 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", @@ -1691,6 +1744,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", @@ -1745,6 +1799,7 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", @@ -1754,6 +1809,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", @@ -1762,6 +1818,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", @@ -1842,6 +1899,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", @@ -1956,7 +2014,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -2013,6 +2071,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", @@ -2021,6 +2080,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", @@ -2029,6 +2089,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json index 10bdb193c16f..26568e4b77f7 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json @@ -1,10 +1,72 @@ [ { + "BriefDescription": "Hit snoop reply with data, line invalidated.", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "CORE_SNOOP_RESPONSE.I_FWD_FE", + "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated: removed from this core's cache, after the data is forwarded back to the requestor and indicating the data was found unmodified in the (FE) Forward or Exclusive State in this cores caches cache. A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x20" + }, + { + "BriefDescription": "HitM snoop reply with data, line invalidated.", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "CORE_SNOOP_RESPONSE.I_FWD_M", + "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated: removed from this core's caches, after the data is forwarded back to the requestor, and indicating the data was found modified(M) in this cores caches cache (aka HitM response). A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Hit snoop reply without sending the data, line invalidated.", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "CORE_SNOOP_RESPONSE.I_HIT_FSE", + "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated in this core's caches without forwarded back to the requestor. The line was in Forward, Shared or Exclusive (FSE) state in this cores caches. A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Line not found snoop reply", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "CORE_SNOOP_RESPONSE.MISS", + "PublicDescription": "Counts responses to snoops indicating that the data was not found (IHitI) in this core's caches. A single snoop response from the core counts on all hyperthreads of the Core.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Hit snoop reply with data, line kept in Shared state.", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "CORE_SNOOP_RESPONSE.S_FWD_FE", + "PublicDescription": "Counts responses to snoops indicating the line may be kept on this core in the (S)hared state, after the data is forwarded back to the requestor, initially the data was found in the cache in the (FS) Forward or Shared state. A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x40" + }, + { + "BriefDescription": "HitM snoop reply with data, line kept in Shared state", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "CORE_SNOOP_RESPONSE.S_FWD_M", + "PublicDescription": "Counts responses to snoops indicating the line may be kept on this core in the (S)hared state, after the data is forwarded back to the requestor, initially the data was found in the cache in the (M)odified state. A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Hit snoop reply without sending the data, line kept in Shared state.", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "CORE_SNOOP_RESPONSE.S_HIT_FSE", + "PublicDescription": "Counts responses to snoops indicating the line was kept on this core in the (S)hared state, and that the data was found unmodified but not forwarded back to the requestor, initially the data was found in the cache in the (FSE) Forward, Shared state or Exclusive state. A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { "BriefDescription": "L1D.HWPF_MISS", "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.HWPF_MISS", - "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -13,7 +75,7 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.REPLACEMENT", - "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -22,7 +84,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -33,7 +95,7 @@ "EdgeDetect": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS", - "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", + "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -43,7 +105,6 @@ "Deprecated": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALL", - "PublicDescription": "This event is deprecated. Refer to new event L1D_PEND_MISS.L2_STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -52,7 +113,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALLS", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -61,7 +122,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -71,7 +132,7 @@ "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -80,7 +141,7 @@ "Counter": "0,1,2,3", "EventCode": "0x25", "EventName": "L2_LINES_IN.ALL", - "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", "SampleAfterValue": "100003", "UMask": "0x1f" }, @@ -89,7 +150,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.NON_SILENT", - "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", "SampleAfterValue": "200003", "UMask": "0x2" }, @@ -98,7 +159,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -107,7 +168,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.USELESS_HWPF", - "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", "SampleAfterValue": "200003", "UMask": "0x4" }, @@ -116,7 +177,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.ALL", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]", "SampleAfterValue": "200003", "UMask": "0xff" }, @@ -125,7 +186,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", "SampleAfterValue": "200003", "UMask": "0x3f" }, @@ -134,7 +195,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", - "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0", + "PublicDescription": "Counts the total number of L2 code requests.", "SampleAfterValue": "200003", "UMask": "0xe4" }, @@ -143,7 +204,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", "SampleAfterValue": "200003", "UMask": "0xe1" }, @@ -152,7 +213,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_MISS", - "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts demand requests that miss L2 cache.", "SampleAfterValue": "200003", "UMask": "0x27" }, @@ -161,7 +222,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", - "PublicDescription": "Counts demand requests to L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts demand requests to L2 cache.", "SampleAfterValue": "200003", "UMask": "0xe7" }, @@ -170,7 +231,6 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_HWPF", - "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf0" }, @@ -179,7 +239,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_RFO", - "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", "SampleAfterValue": "200003", "UMask": "0xe2" }, @@ -188,7 +248,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", - "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", "SampleAfterValue": "200003", "UMask": "0xc4" }, @@ -197,7 +257,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", - "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", "SampleAfterValue": "200003", "UMask": "0x24" }, @@ -206,7 +266,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", "SampleAfterValue": "200003", "UMask": "0xc1" }, @@ -215,7 +275,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", - "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", + "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", "SampleAfterValue": "200003", "UMask": "0x21" }, @@ -224,7 +284,6 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HWPF_MISS", - "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x30" }, @@ -233,7 +292,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", "SampleAfterValue": "200003", "UMask": "0x3f" }, @@ -242,7 +301,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.REFERENCES", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]", "SampleAfterValue": "200003", "UMask": "0xff" }, @@ -251,7 +310,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", "SampleAfterValue": "200003", "UMask": "0xc2" }, @@ -260,7 +319,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", "SampleAfterValue": "200003", "UMask": "0x22" }, @@ -269,7 +328,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_HIT", - "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", + "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", "SampleAfterValue": "200003", "UMask": "0xc8" }, @@ -278,7 +337,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_MISS", - "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", + "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", "SampleAfterValue": "200003", "UMask": "0x28" }, @@ -287,7 +346,7 @@ "Counter": "0,1,2,3", "EventCode": "0x23", "EventName": "L2_TRANS.L2_WB", - "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts L2 writebacks that access L2 cache.", "SampleAfterValue": "200003", "UMask": "0x40" }, @@ -296,7 +355,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", - "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", "SampleAfterValue": "100003", "UMask": "0x41" }, @@ -305,7 +364,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", "SampleAfterValue": "100003", "UMask": "0x4f" }, @@ -394,7 +453,7 @@ "Counter": "0,1,2,3", "EventCode": "0x43", "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY", - "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0", + "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)", "SampleAfterValue": "1000003", "UMask": "0xfd" }, @@ -563,7 +622,6 @@ "Counter": "0,1,2,3", "EventCode": "0x44", "EventName": "MEM_STORE_RETIRED.L2_HIT", - "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -572,7 +630,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe5", "EventName": "MEM_UOP_RETIRED.ANY", - "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0", + "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -999,7 +1057,6 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", - "PublicDescription": "OFFCORE_REQUESTS.ALL_REQUESTS Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -1008,7 +1065,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DATA_RD", - "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -1017,7 +1074,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", - "PublicDescription": "Counts both cacheable and non-cacheable code read requests. Available PDIST counters: 0", + "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -1026,7 +1083,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", - "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1035,7 +1092,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", - "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -1045,7 +1102,6 @@ "Deprecated": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", - "PublicDescription": "This event is deprecated. Refer to new event OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -1055,7 +1111,6 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -1065,7 +1120,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1075,7 +1130,6 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", - "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1085,7 +1139,6 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -1094,7 +1147,6 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", - "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -1103,7 +1155,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1112,7 +1164,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -1121,7 +1173,7 @@ "Counter": "0,1,2,3", "EventCode": "0x2c", "EventName": "SQ_MISC.BUS_LOCK", - "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -1130,7 +1182,6 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.ANY", - "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xf" }, @@ -1139,7 +1190,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.NTA", - "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1148,7 +1199,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", - "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHW instructions executed.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -1157,7 +1208,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T0", - "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -1166,7 +1217,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T1_T2", - "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", "SampleAfterValue": "100003", "UMask": "0x4" } diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json index 34e1cbcd722c..433ae5f50704 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json @@ -1,28 +1,28 @@ [ { "BriefDescription": "C1 residency percent per core", - "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricExpr": "cstate_core@c1\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C1_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" @@ -40,6 +40,18 @@ "ScaleUnit": "1per_instr" }, { + "BriefDescription": "The average number of cores that are in cstate C0 as observed by the power control unit (PCU)", + "MetricExpr": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C0 / UNC_P_CLOCKTICKS * #num_packages", + "MetricGroup": "cpu_cstate", + "MetricName": "cpu_cstate_c0" + }, + { + "BriefDescription": "The average number of cores are in cstate C6 as observed by the power control unit (PCU)", + "MetricExpr": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C6 / UNC_P_CLOCKTICKS * #num_packages", + "MetricGroup": "cpu_cstate", + "MetricName": "cpu_cstate_c6" + }, + { "BriefDescription": "CPU operating frequency (in GHz)", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9", "MetricName": "cpu_operating_frequency", @@ -79,6 +91,12 @@ "ScaleUnit": "1MB/s" }, { + "BriefDescription": "Bandwidth of inbound IO reads that are initiated by end device controllers that are requesting memory from the CPU and miss the L3 cache", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_read_l3_miss", + "ScaleUnit": "1MB/s" + }, + { "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read_local", @@ -97,6 +115,12 @@ "ScaleUnit": "1MB/s" }, { + "BriefDescription": "Bandwidth of inbound IO writes that are initiated by end device controllers that are writing memory to the CPU", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_MISS_ITOM + UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR) * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_write_l3_miss", + "ScaleUnit": "1MB/s" + }, + { "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write_local", @@ -111,19 +135,19 @@ { "BriefDescription": "Percentage of inbound full cacheline writes initiated by end device controllers that miss the L3 cache", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM / UNC_CHA_TOR_INSERTS.IO_ITOM", - "MetricName": "io_percent_of_inbound_full_writes_that_miss_l3", + "MetricName": "io_full_write_l3_miss", "ScaleUnit": "100%" }, { "BriefDescription": "Percentage of inbound partial cacheline writes initiated by end device controllers that miss the L3 cache", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_RFO) / (UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_RFO)", - "MetricName": "io_percent_of_inbound_partial_writes_that_miss_l3", + "MetricName": "io_partial_write_l3_miss", "ScaleUnit": "100%" }, { "BriefDescription": "Percentage of inbound reads initiated by end device controllers that miss the L3 cache", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR / UNC_CHA_TOR_INSERTS.IO_PCIRDCUR", - "MetricName": "io_percent_of_inbound_reads_that_miss_l3", + "MetricName": "io_read_l3_miss", "ScaleUnit": "100%" }, { @@ -335,7 +359,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -370,39 +394,39 @@ "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" }, { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " + }, + { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + 0 / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "MetricName": "tma_bottleneck_data_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + 0 / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "MetricName": "tma_bottleneck_data_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_bottleneck_compute_bound_est", - "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -434,7 +458,7 @@ }, { "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_data_cache_memory_bandwidth + tma_bottleneck_data_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", @@ -450,7 +474,7 @@ { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "BadSpec;BrMispredicts;BvMP;Default;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", @@ -551,7 +575,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(76.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 74.6 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", @@ -658,7 +681,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -786,7 +809,7 @@ { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", @@ -1297,19 +1320,19 @@ { "BriefDescription": "Off-core accesses per kilo instruction for modified write requests", "MetricExpr": "1e3 * OCR.MODIFIED_WRITE.ANY_RESPONSE / tma_info_inst_mix_instructions", - "MetricGroup": "Offcore", + "MetricGroup": "Offcore;Server", "MetricName": "tma_info_memory_mix_offcore_mwrite_any_pki" }, { "BriefDescription": "Off-core accesses per kilo instruction for reads-to-core requests (speculative; including in-core HW prefetches)", "MetricExpr": "1e3 * OCR.READS_TO_CORE.ANY_RESPONSE / tma_info_inst_mix_instructions", - "MetricGroup": "CacheHits;Offcore", + "MetricGroup": "CacheHits;Offcore;Server", "MetricName": "tma_info_memory_mix_offcore_read_any_pki" }, { "BriefDescription": "L3 cache misses per kilo instruction for reads-to-core requests (speculative; including in-core HW prefetches)", "MetricExpr": "1e3 * OCR.READS_TO_CORE.L3_MISS / tma_info_inst_mix_instructions", - "MetricGroup": "Offcore", + "MetricGroup": "Offcore;Server", "MetricName": "tma_info_memory_mix_offcore_read_l3m_pki" }, { @@ -1335,21 +1358,21 @@ { "BriefDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket", "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / tma_info_system_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", + "MetricGroup": "HPC;Mem;MemoryBW;Offcore;Server", "MetricName": "tma_info_memory_soc_r2c_dram_bw", "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW." }, { "BriefDescription": "Average L3-cache miss BW for Reads-to-Core (R2C)", "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / tma_info_system_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", + "MetricGroup": "HPC;Mem;MemoryBW;Offcore;Server", "MetricName": "tma_info_memory_soc_r2c_l3m_bw", "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW." }, { "BriefDescription": "Average Off-core access BW for Reads-to-Core (R2C)", "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / tma_info_system_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", + "MetricGroup": "HPC;Mem;MemoryBW;Offcore;Server", "MetricName": "tma_info_memory_soc_r2c_offcore_bw", "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches." }, @@ -1379,7 +1402,7 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -1426,7 +1449,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1438,16 +1461,28 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, { + "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", + "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / tma_info_system_time if #has_pmem > 0 else 0)", + "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", + "MetricName": "tma_info_system_cxl_mem_read_bw" + }, + { + "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / tma_info_system_time if #has_pmem > 0 else 0)", + "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", + "MetricName": "tma_info_system_cxl_mem_write_bw" + }, + { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", @@ -1513,7 +1548,6 @@ }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", @@ -1674,12 +1708,12 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "BriefDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1693,7 +1727,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "4.4 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", @@ -1712,12 +1745,11 @@ }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "32.6 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_data_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1800,6 +1832,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", @@ -1832,7 +1865,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1841,13 +1874,13 @@ "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "Backend;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -1857,7 +1890,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", @@ -1910,7 +1942,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", - "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2", + "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2.4", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -1945,6 +1977,7 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", @@ -2006,6 +2039,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", @@ -2015,6 +2049,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_THRESHOLD_AND_NMI", "MetricExpr": "(EXE_ACTIVITY.EXE_BOUND_0_PORTS + max(RS.EMPTY_RESOURCE - RESOURCE_STALLS.SCOREBOARD, 0)) / tma_info_thread_clks * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", @@ -2024,6 +2059,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_THRESHOLD_AND_NMI", "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", @@ -2033,7 +2069,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", @@ -2043,7 +2078,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", @@ -2072,7 +2106,7 @@ { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2100,7 +2134,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", @@ -2132,7 +2165,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json index 8c9207750c82..bc475e163227 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json @@ -5,7 +5,6 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.FPDIV_ACTIVE", - "PublicDescription": "ARITH.FPDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -14,7 +13,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.FP", - "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0", + "PublicDescription": "Counts all microcode Floating Point assists.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -23,7 +22,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.SSE_AVX_MIX", - "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -32,7 +30,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_0", - "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -41,7 +38,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_1", - "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -50,7 +46,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_5", - "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -59,7 +54,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V0", - "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -68,7 +62,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V1", - "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -77,7 +70,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V2", - "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -86,7 +78,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -95,7 +87,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -104,7 +96,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -113,7 +105,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -122,7 +114,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x18" }, @@ -131,7 +123,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x40" }, @@ -140,7 +132,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -149,7 +141,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x60" }, @@ -158,7 +150,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", - "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -167,7 +159,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -176,7 +168,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -185,7 +177,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.VECTOR", - "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "1000003", "UMask": "0xfc" }, @@ -194,7 +186,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF", - "PublicDescription": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -203,7 +194,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF", - "PublicDescription": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -212,7 +202,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF", - "PublicDescription": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -221,7 +210,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF", - "PublicDescription": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -230,7 +218,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.SCALAR", - "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR Available PDIST counters: 0", + "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR", "SampleAfterValue": "100003", "UMask": "0x3" }, @@ -239,7 +227,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.SCALAR_HALF", - "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -248,7 +235,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.VECTOR", - "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR Available PDIST counters: 0", + "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR", "SampleAfterValue": "100003", "UMask": "0x1c" } diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json index 9fe9d62b867a..793c486ffabe 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "BACLEARS.ANY", - "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -13,7 +13,7 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.LCP", - "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -22,7 +22,6 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.MS_BUSY", - "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x2" }, @@ -31,7 +30,7 @@ "Counter": "0,1,2,3", "EventCode": "0x61", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -249,7 +248,7 @@ "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALLS", - "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.", "SampleAfterValue": "500009", "UMask": "0x4" }, @@ -260,7 +259,6 @@ "EdgeDetect": "1", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALL_PERIODS", - "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x4" }, @@ -269,7 +267,7 @@ "Counter": "0,1,2,3", "EventCode": "0x83", "EventName": "ICACHE_TAG.STALLS", - "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", "SampleAfterValue": "200003", "UMask": "0x4" }, @@ -279,7 +277,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -289,7 +287,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -298,7 +296,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.DSB_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -308,7 +306,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -318,7 +316,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -327,7 +325,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -337,7 +335,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES_ANY", - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -348,7 +346,7 @@ "EdgeDetect": "1", "EventCode": "0x79", "EventName": "IDQ.MS_SWITCHES", - "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -357,7 +355,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", - "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Available PDIST counters: 0", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS).", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -366,7 +364,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -376,7 +374,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -387,7 +385,7 @@ "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -396,7 +394,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -406,7 +404,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -417,7 +415,7 @@ "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", "SampleAfterValue": "1000003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json index 7c3f9b76d367..5e6c1f05c981 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json @@ -5,7 +5,6 @@ "CounterMask": "6", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", - "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x6" }, @@ -14,7 +13,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -24,7 +23,6 @@ "CounterMask": "2", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS", - "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -34,7 +32,6 @@ "CounterMask": "3", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS", - "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -44,7 +41,7 @@ "CounterMask": "5", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS", - "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", + "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -54,7 +51,7 @@ "CounterMask": "9", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS", - "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", + "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -478,7 +475,6 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -487,7 +483,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0", + "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -505,7 +501,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_EVENTS", - "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt). Available PDIST counters: 0", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -514,7 +510,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_MEM", - "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts). Available PDIST counters: 0", + "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -523,7 +519,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", - "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.", "SampleAfterValue": "100003", "UMask": "0x40" }, @@ -532,7 +528,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", - "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -541,7 +537,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.COMMIT", - "PublicDescription": "Counts the number of times RTM commit succeeded. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times RTM commit succeeded.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -550,7 +546,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.START", - "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -559,7 +555,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CAPACITY_READ", - "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads Available PDIST counters: 0", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -568,7 +564,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CAPACITY_WRITE", - "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes. Available PDIST counters: 0", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -577,7 +573,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CONFLICT", - "PublicDescription": "Counts the number of times a TSX line had a cache conflict. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times a TSX line had a cache conflict.", "SampleAfterValue": "100003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json index a58d65556609..21f49f609ed4 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json @@ -4,11 +4,35 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.PAGE_FAULT", - "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, { + "BriefDescription": "HW_INTERRUPTS.MASKED", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcb", + "EventName": "HW_INTERRUPTS.MASKED", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "HW_INTERRUPTS.PENDING_AND_MASKED", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcb", + "EventName": "HW_INTERRUPTS.PENDING_AND_MASKED", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of hardware interrupts received by the processor.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcb", + "EventName": "HW_INTERRUPTS.RECEIVED", + "PublicDescription": "Counts the number of hardware interruptions received by the processor.", + "SampleAfterValue": "203", + "UMask": "0x1" + }, + { "BriefDescription": "Counts streaming stores that have any type of response.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", @@ -25,7 +49,7 @@ "CounterMask": "1", "EventCode": "0x2d", "EventName": "XQ.FULL_CYCLES", - "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", "SampleAfterValue": "1000003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json index 48bec483b49a..1fa7957956df 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json @@ -6,7 +6,6 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.DIVIDER_ACTIVE", - "PublicDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -16,7 +15,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.DIV_ACTIVE", - "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -27,7 +26,6 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.FP_DIVIDER_ACTIVE", - "PublicDescription": "This event is deprecated. Refer to new event ARITH.FPDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -37,7 +35,6 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.IDIV_ACTIVE", - "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -48,7 +45,6 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.INT_DIVIDER_ACTIVE", - "PublicDescription": "This event is deprecated. Refer to new event ARITH.IDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -57,7 +53,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.ANY", - "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.", "SampleAfterValue": "100003", "UMask": "0x1b" }, @@ -217,7 +213,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C01", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -226,7 +222,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C02", - "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", + "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -235,7 +231,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C0_WAIT", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", "SampleAfterValue": "2000003", "UMask": "0x70" }, @@ -244,7 +240,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED", - "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", + "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -253,7 +249,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0", + "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.", "SampleAfterValue": "25003", "UMask": "0x2" }, @@ -262,7 +258,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE", - "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -273,7 +268,6 @@ "EdgeDetect": "1", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", - "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -282,7 +276,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED", - "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", + "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -299,7 +293,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -316,7 +310,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", "SampleAfterValue": "2000003" }, { @@ -325,7 +319,6 @@ "CounterMask": "8", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", - "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -335,7 +328,6 @@ "CounterMask": "1", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", - "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -345,7 +337,6 @@ "CounterMask": "16", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", - "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -355,7 +346,6 @@ "CounterMask": "12", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", - "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xc" }, @@ -365,7 +355,6 @@ "CounterMask": "5", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", - "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -375,7 +364,6 @@ "CounterMask": "4", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", - "PublicDescription": "Total execution stalls. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -384,7 +372,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb7", "EventName": "EXE.AMX_BUSY", - "PublicDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -393,7 +380,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -402,7 +389,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL", - "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0xc" }, @@ -411,7 +397,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -420,7 +406,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", - "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -429,7 +415,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", - "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -439,7 +425,6 @@ "CounterMask": "5", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", - "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x21" }, @@ -449,7 +434,7 @@ "CounterMask": "2", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", - "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -458,7 +443,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", - "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0", + "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", "SampleAfterValue": "1000003", "UMask": "0x80" }, @@ -467,7 +452,7 @@ "Counter": "0,1,2,3", "EventCode": "0x75", "EventName": "INST_DECODED.DECODERS", - "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -492,7 +477,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", - "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -501,7 +485,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions Available PDIST counters: 0", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -518,7 +502,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -529,7 +513,7 @@ "EdgeDetect": "1", "EventCode": "0xad", "EventName": "INT_MISC.CLEARS_COUNT", - "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -538,7 +522,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", - "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", "SampleAfterValue": "500009", "UMask": "0x80" }, @@ -547,7 +531,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.MBA_STALLS", - "PublicDescription": "INT_MISC.MBA_STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -556,7 +539,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.RECOVERY_CYCLES", - "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -567,7 +550,6 @@ "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", "MSRIndex": "0x3F7", "MSRValue": "0x7", - "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -576,7 +558,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.UOP_DROPPING", - "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -585,7 +567,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.128BIT", - "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x13" }, @@ -594,7 +575,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.256BIT", - "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xac" }, @@ -603,7 +583,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_128", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -612,7 +592,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_256", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", "SampleAfterValue": "1000003", "UMask": "0xc" }, @@ -621,7 +601,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.MUL_256", - "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80" }, @@ -630,7 +609,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.SHUFFLES", - "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -639,7 +617,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_128", - "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -648,7 +625,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_256", - "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -657,7 +633,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", - "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -666,7 +642,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.NO_SR", - "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", "SampleAfterValue": "100003", "UMask": "0x88" }, @@ -675,7 +651,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", "SampleAfterValue": "100003", "UMask": "0x82" }, @@ -684,7 +660,7 @@ "Counter": "0,1,2,3", "EventCode": "0x4c", "EventName": "LOAD_HIT_PREFETCH.SWPF", - "PublicDescription": "Counts all software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0", + "PublicDescription": "Counts all software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -694,7 +670,7 @@ "CounterMask": "1", "EventCode": "0xa8", "EventName": "LSD.CYCLES_ACTIVE", - "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -704,7 +680,7 @@ "CounterMask": "6", "EventCode": "0xa8", "EventName": "LSD.CYCLES_OK", - "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -713,7 +689,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa8", "EventName": "LSD.UOPS", - "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -724,7 +700,7 @@ "EdgeDetect": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.COUNT", - "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0", + "PublicDescription": "Counts the number of machine clears (nukes) of any type.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -733,7 +709,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SMC", - "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -742,7 +718,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe0", "EventName": "MISC2_RETIRED.LFENCE", - "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0", + "PublicDescription": "number of LFENCE retired instructions", "SampleAfterValue": "400009", "UMask": "0x20" }, @@ -751,7 +727,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcc", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -760,7 +736,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SB", - "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -769,7 +745,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SCOREBOARD", - "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -778,7 +753,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", "EventName": "RS.EMPTY", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", "SampleAfterValue": "1000003", "UMask": "0x7" }, @@ -790,7 +765,7 @@ "EventCode": "0xa5", "EventName": "RS.EMPTY_COUNT", "Invert": "1", - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", "SampleAfterValue": "100003", "UMask": "0x7" }, @@ -799,7 +774,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", "EventName": "RS.EMPTY_RESOURCE", - "PublicDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -812,7 +786,6 @@ "EventCode": "0xa5", "EventName": "RS_EMPTY.COUNT", "Invert": "1", - "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x7" }, @@ -822,7 +795,6 @@ "Deprecated": "1", "EventCode": "0xa5", "EventName": "RS_EMPTY.CYCLES", - "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x7" }, @@ -831,7 +803,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", - "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources. Available PDIST counters: 0", + "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.", "SampleAfterValue": "10000003", "UMask": "0x2" }, @@ -840,7 +812,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BAD_SPEC_SLOTS", - "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0", + "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.", "SampleAfterValue": "10000003", "UMask": "0x4" }, @@ -849,7 +821,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", - "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", "SampleAfterValue": "10000003", "UMask": "0x8" }, @@ -858,7 +830,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", - "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x10" }, @@ -875,7 +846,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.SLOTS_P", - "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", "SampleAfterValue": "10000003", "UMask": "0x1" }, @@ -884,7 +855,6 @@ "Counter": "0,1,2,3", "EventCode": "0x76", "EventName": "UOPS_DECODED.DEC0_UOPS", - "PublicDescription": "UOPS_DECODED.DEC0_UOPS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -893,7 +863,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_0", - "PublicDescription": "Number of uops dispatch to execution port 0. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution port 0.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -902,7 +872,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_1", - "PublicDescription": "Number of uops dispatch to execution port 1. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution port 1.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -911,7 +881,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_2_3_10", - "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -920,7 +890,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_4_9", - "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 4 and 9", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -929,7 +899,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_5_11", - "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 5 and 11", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -938,7 +908,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_6", - "PublicDescription": "Number of uops dispatch to execution port 6. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution port 6.", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -947,7 +917,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_7_8", - "PublicDescription": "Number of uops dispatch to execution ports 7 and 8. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 7 and 8.", "SampleAfterValue": "2000003", "UMask": "0x80" }, @@ -956,7 +926,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE", - "PublicDescription": "Counts the number of uops executed from any thread. Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops executed from any thread.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -966,7 +936,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -976,7 +946,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -986,7 +956,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -996,7 +966,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -1006,7 +976,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_1", - "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1016,7 +986,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_2", - "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1026,7 +996,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_3", - "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1036,7 +1006,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_4", - "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1047,7 +1017,7 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALLS", "Invert": "1", - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1059,7 +1029,6 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALL_CYCLES", "Invert": "1", - "PublicDescription": "This event is deprecated. Refer to new event UOPS_EXECUTED.STALLS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1068,7 +1037,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.THREAD", - "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1077,7 +1045,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.X87", - "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of x87 uops executed.", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -1086,7 +1054,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xae", "EventName": "UOPS_ISSUED.ANY", - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1096,7 +1064,6 @@ "CounterMask": "1", "EventCode": "0xae", "EventName": "UOPS_ISSUED.CYCLES", - "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1106,7 +1073,7 @@ "CounterMask": "1", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.CYCLES", - "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where at least one uop has retired.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1115,7 +1082,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.HEAVY", - "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0", + "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1126,7 +1093,6 @@ "EventName": "UOPS_RETIRED.MS", "MSRIndex": "0x3F7", "MSRValue": "0x8", - "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -1135,7 +1101,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.SLOTS", - "PublicDescription": "Counts the retirement slots used each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the retirement slots used each cycle.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -1146,7 +1112,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALLS", "Invert": "1", - "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0", + "PublicDescription": "This event counts cycles without actually retired uops.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1158,7 +1124,6 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALL_CYCLES", "Invert": "1", - "PublicDescription": "This event is deprecated. Refer to new event UOPS_RETIRED.STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" } diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-cache.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-cache.json index f453202d80c2..92cf47967f0b 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-cache.json @@ -312,6 +312,17 @@ "Unit": "CHA" }, { + "BriefDescription": "Distress signal asserted : DPT Remote", + "Counter": "0,1,2,3", + "EventCode": "0xaf", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_NONLOCAL", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", + "UMask": "0x8", + "Unit": "CHA" + }, + { "BriefDescription": "Egress Blocking due to Ordering requirements : Down", "Counter": "0,1,2,3", "EventCode": "0xba", diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-memory.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-memory.json index 68be01dad7c9..30044177ccf8 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-memory.json @@ -2770,6 +2770,88 @@ "Unit": "iMC" }, { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.HIGH", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Number of DRAM Refreshes Issued : Counts the number of refreshes issued.", + "UMask": "0x24", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.HIGH_ALL", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x24", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.HIGH_PCH0", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.HIGH_PCH1", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.PANIC", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Number of DRAM Refreshes Issued : Counts the number of refreshes issued.", + "UMask": "0x12", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.PANIC_ALL", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x12", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.PANIC_PCH0", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.PANIC_PCH1", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { "BriefDescription": "ECC Correctable Errors", "Counter": "0,1,2,3", "EventCode": "0x09", @@ -3048,6 +3130,28 @@ "Unit": "iMC" }, { + "BriefDescription": "Throttle Cycles for Rank 0", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Throttle Cycles for Rank 0 : Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1. : Thermal throttling is performed per DIMM. We support 3 DIMMs per channel. This ID allows us to filter by ID.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Throttle Cycles for Rank 0", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Throttle Cycles for Rank 0 : Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1.", + "UMask": "0x2", + "Unit": "iMC" + }, + { "BriefDescription": "Precharge due to read, write, underfill, or PGT.", "Counter": "0,1,2,3", "EventCode": "0x03", diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-power.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-power.json index 9482ddaea4d1..71c35b165a3e 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-power.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-power.json @@ -178,7 +178,6 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C0", - "Experimental": "1", "PerPkg": "1", "PublicDescription": "Number of cores in C0 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" @@ -198,7 +197,6 @@ "Counter": "0,1,2,3", "EventCode": "0x37", "EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C6", - "Experimental": "1", "PerPkg": "1", "PublicDescription": "Number of cores in C6 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json index 3d3f88600e26..609a9549cbf3 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", - "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -14,7 +14,7 @@ "CounterMask": "1", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -23,7 +23,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -32,7 +32,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -41,7 +41,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -50,7 +50,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -59,7 +59,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -68,7 +68,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.STLB_HIT", - "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -78,7 +78,7 @@ "CounterMask": "1", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -87,7 +87,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -96,7 +96,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -105,7 +105,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -114,7 +114,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -123,7 +123,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -132,7 +132,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.STLB_HIT", - "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -142,7 +142,7 @@ "CounterMask": "1", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -151,7 +151,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -160,7 +160,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -169,7 +169,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -178,7 +178,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", "SampleAfterValue": "100003", "UMask": "0x10" } diff --git a/tools/perf/pmu-events/arch/x86/grandridge/cache.json b/tools/perf/pmu-events/arch/x86/grandridge/cache.json index 877052db1490..9abddb06a837 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/cache.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/cache.json @@ -286,7 +286,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024", @@ -297,7 +297,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", @@ -308,7 +308,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", @@ -319,7 +319,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048", @@ -330,7 +330,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", @@ -341,7 +341,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", @@ -352,7 +352,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", @@ -363,7 +363,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", @@ -374,7 +374,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", @@ -385,7 +385,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", diff --git a/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json b/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json index 878b1caf12de..a0d637a24c1b 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json @@ -1,56 +1,56 @@ [ { "BriefDescription": "C10 residency percent per package", - "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c10\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C10_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C1 residency percent per core", - "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricExpr": "cstate_core@c1\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C1_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C8 residency percent per package", - "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c8\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C8_Pkg_Residency", "ScaleUnit": "100%" @@ -633,7 +633,7 @@ }, { "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricName": "tma_info_system_cpu_utilization" }, { @@ -645,7 +645,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE_P@k / CPU_CLK_UNHALTED.CORE", + "MetricExpr": "CPU_CLK_UNHALTED.CORE_P:k / CPU_CLK_UNHALTED.CORE", "MetricGroup": "Summary", "MetricName": "tma_info_system_kernel_utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/cache.json b/tools/perf/pmu-events/arch/x86/graniterapids/cache.json index dbdeade6fe6f..7edb73583b07 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/cache.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/cache.json @@ -4,7 +4,6 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.HWPF_MISS", - "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -13,7 +12,7 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.REPLACEMENT", - "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -22,7 +21,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -33,7 +32,7 @@ "EdgeDetect": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS", - "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", + "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -42,7 +41,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALLS", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -51,7 +50,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -61,7 +60,7 @@ "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -70,7 +69,7 @@ "Counter": "0,1,2,3", "EventCode": "0x25", "EventName": "L2_LINES_IN.ALL", - "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", "SampleAfterValue": "100003", "UMask": "0x1f" }, @@ -79,7 +78,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.NON_SILENT", - "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", "SampleAfterValue": "200003", "UMask": "0x2" }, @@ -88,7 +87,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -97,7 +96,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.USELESS_HWPF", - "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", "SampleAfterValue": "200003", "UMask": "0x4" }, @@ -106,7 +105,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.ALL", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]", "SampleAfterValue": "200003", "UMask": "0xff" }, @@ -115,7 +114,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.HIT", - "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT] Available PDIST counters: 0", + "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT]", "SampleAfterValue": "200003", "UMask": "0xdf" }, @@ -124,7 +123,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", "SampleAfterValue": "200003", "UMask": "0x3f" }, @@ -133,7 +132,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", - "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0", + "PublicDescription": "Counts the total number of L2 code requests.", "SampleAfterValue": "200003", "UMask": "0xe4" }, @@ -142,7 +141,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", "SampleAfterValue": "200003", "UMask": "0xe1" }, @@ -151,7 +150,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_MISS", - "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts demand requests that miss L2 cache.", "SampleAfterValue": "200003", "UMask": "0x27" }, @@ -160,7 +159,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", - "PublicDescription": "Counts demand requests to L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts demand requests to L2 cache.", "SampleAfterValue": "200003", "UMask": "0xe7" }, @@ -169,7 +168,6 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_HWPF", - "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf0" }, @@ -178,7 +176,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_RFO", - "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", "SampleAfterValue": "200003", "UMask": "0xe2" }, @@ -187,7 +185,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", - "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", "SampleAfterValue": "200003", "UMask": "0xc4" }, @@ -196,7 +194,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", - "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", "SampleAfterValue": "200003", "UMask": "0x24" }, @@ -205,7 +203,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", "SampleAfterValue": "200003", "UMask": "0xc1" }, @@ -214,7 +212,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", - "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", + "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", "SampleAfterValue": "200003", "UMask": "0x21" }, @@ -223,7 +221,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HIT", - "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT] Available PDIST counters: 0", + "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT]", "SampleAfterValue": "200003", "UMask": "0xdf" }, @@ -232,7 +230,6 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HWPF_MISS", - "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x30" }, @@ -241,7 +238,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", "SampleAfterValue": "200003", "UMask": "0x3f" }, @@ -250,7 +247,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.REFERENCES", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]", "SampleAfterValue": "200003", "UMask": "0xff" }, @@ -259,7 +256,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", "SampleAfterValue": "200003", "UMask": "0xc2" }, @@ -268,7 +265,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", "SampleAfterValue": "200003", "UMask": "0x22" }, @@ -277,7 +274,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_HIT", - "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", + "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", "SampleAfterValue": "200003", "UMask": "0xc8" }, @@ -286,7 +283,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_MISS", - "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", + "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", "SampleAfterValue": "200003", "UMask": "0x28" }, @@ -295,7 +292,7 @@ "Counter": "0,1,2,3", "EventCode": "0x23", "EventName": "L2_TRANS.L2_WB", - "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts L2 writebacks that access L2 cache.", "SampleAfterValue": "200003", "UMask": "0x40" }, @@ -304,7 +301,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", - "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", "SampleAfterValue": "100003", "UMask": "0x41" }, @@ -313,7 +310,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", "SampleAfterValue": "100003", "UMask": "0x4f" }, @@ -437,7 +434,7 @@ "Counter": "0,1,2,3", "EventCode": "0x43", "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY", - "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0", + "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)", "SampleAfterValue": "1000003", "UMask": "0xfd" }, @@ -504,6 +501,15 @@ "UMask": "0x1" }, { + "BriefDescription": "Retired load instructions with remote cxl mem as the data source where the data request missed all caches.", + "Counter": "0,1,2,3", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_CXL_MEM", + "PublicDescription": "Counts retired load instructions with remote cxl mem as the data source and the data request missed L3. Available PDIST counters: 0", + "SampleAfterValue": "100007", + "UMask": "0x10" + }, + { "BriefDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", "Counter": "0,1,2,3", "Data_LA": "1", @@ -629,11 +635,20 @@ "UMask": "0x20" }, { + "BriefDescription": "Retired load instructions with local cxl mem as the data source where the data request missed all caches.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.LOCAL_CXL_MEM", + "PublicDescription": "Counts retired load instructions with local cxl mem as the data source and the data request missed L3. Available PDIST counters: 0", + "SampleAfterValue": "1000003", + "UMask": "0x80" + }, + { "BriefDescription": "MEM_STORE_RETIRED.L2_HIT", "Counter": "0,1,2,3", "EventCode": "0x44", "EventName": "MEM_STORE_RETIRED.L2_HIT", - "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -642,7 +657,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe5", "EventName": "MEM_UOP_RETIRED.ANY", - "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0", + "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -691,6 +706,17 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that were supplied by CXL MEM (Type 2 or Type 3).", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.CXL_MEM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703C00001", + "PublicDescription": "Counts demand data reads that were supplied by CXL MEM (Type 2 or Type 3). Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that hit in the L3 or were snooped from another core's caches on the same socket.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", @@ -735,6 +761,17 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that were supplied by CXL MEM (Type 2 and Type 3) attached to local socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_CXL_MEM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x700C00001", + "PublicDescription": "Counts demand data reads that were supplied by CXL MEM (Type 2 and Type 3) attached to local socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", @@ -757,6 +794,17 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that were supplied by CXL MEM (Type 2 or Type 3) attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CXL_MEM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703000001", + "PublicDescription": "Counts demand data reads that were supplied by CXL MEM (Type 2 or Type 3) attached to another socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", @@ -790,6 +838,17 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by CXL MEM (Type 2 or Type 3).", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.CXL_MEM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703C00002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by CXL MEM (Type 2 or Type 3). Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", @@ -812,6 +871,28 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by CXL MEM (Type 2 and Type 3) attached to local socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.LOCAL_CXL_MEM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x700C00002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by CXL MEM (Type 2 and Type 3) attached to local socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by CXL MEM (Type 2 or Type 3) attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.REMOTE_CXL_MEM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703000002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by CXL MEM (Type 2 or Type 3) attached to another socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", @@ -834,6 +915,17 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by CXL MEM (Type 2 or Type 3).", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.CXL_MEM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703C04477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by CXL MEM (Type 2 or Type 3). Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches on the same socket.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", @@ -856,6 +948,17 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by CXL MEM (Type 2 and Type 3) attached to local socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.LOCAL_CXL_MEM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x700C04477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by CXL MEM (Type 2 and Type 3) attached to local socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", @@ -900,6 +1003,17 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by CXL MEM (Type 2 or Type 3) attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_CXL_MEM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by CXL MEM (Type 2 or Type 3) attached to another socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", @@ -937,7 +1051,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", - "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc.. Available PDIST counters: 0", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -946,7 +1060,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DATA_RD", - "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -955,7 +1069,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", - "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests. Available PDIST counters: 0", + "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -964,7 +1078,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", - "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -973,7 +1087,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", - "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -982,7 +1096,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.MEM_UC", - "PublicDescription": "This event counts noncacheable memory data read transactions. Available PDIST counters: 0", + "PublicDescription": "This event counts noncacheable memory data read transactions.", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -992,7 +1106,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -1002,7 +1116,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1012,7 +1126,6 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", - "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1022,7 +1135,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -1031,7 +1144,6 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", - "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -1040,7 +1152,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1049,7 +1161,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -1058,7 +1170,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", - "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion. Available PDIST counters: 0", + "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -1067,7 +1179,7 @@ "Counter": "0,1,2,3", "EventCode": "0x2c", "EventName": "SQ_MISC.BUS_LOCK", - "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -1076,7 +1188,6 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.ANY", - "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xf" }, @@ -1085,7 +1196,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.NTA", - "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1094,7 +1205,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", - "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHW instructions executed.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -1103,7 +1214,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T0", - "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -1112,7 +1223,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T1_T2", - "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", "SampleAfterValue": "100003", "UMask": "0x4" } diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json b/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json index 1832dd952f66..59789eee060c 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json @@ -5,7 +5,6 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.FPDIV_ACTIVE", - "PublicDescription": "This event counts the cycles the floating point divider is busy. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -14,7 +13,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.FP", - "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0", + "PublicDescription": "Counts all microcode Floating Point assists.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -23,7 +22,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.SSE_AVX_MIX", - "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -32,7 +30,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_0", - "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -41,7 +38,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_1", - "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -50,7 +46,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_5", - "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -59,7 +54,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V0", - "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -68,7 +62,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V1", - "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -77,7 +70,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V2", - "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -86,7 +78,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -95,7 +87,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -104,7 +96,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -113,7 +105,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -122,7 +114,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x18" }, @@ -131,7 +123,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x40" }, @@ -140,7 +132,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -149,7 +141,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x60" }, @@ -158,7 +150,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", - "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -167,7 +159,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -176,7 +168,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -185,7 +177,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.VECTOR", - "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "1000003", "UMask": "0xfc" }, @@ -194,7 +186,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF", - "PublicDescription": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -203,7 +194,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF", - "PublicDescription": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -212,7 +202,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF", - "PublicDescription": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -221,7 +210,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF", - "PublicDescription": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -230,7 +218,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.SCALAR", - "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR Available PDIST counters: 0", + "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR", "SampleAfterValue": "100003", "UMask": "0x3" }, @@ -239,7 +227,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.SCALAR_HALF", - "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -248,7 +235,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.VECTOR", - "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR Available PDIST counters: 0", + "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR", "SampleAfterValue": "100003", "UMask": "0x1c" } diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json b/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json index b7cd92fbecd5..d580d305c926 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "BACLEARS.ANY", - "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -13,7 +13,7 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.LCP", - "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -22,7 +22,6 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.MS_BUSY", - "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x2" }, @@ -31,7 +30,7 @@ "Counter": "0,1,2,3", "EventCode": "0x61", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -303,7 +302,7 @@ "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALLS", - "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.", "SampleAfterValue": "500009", "UMask": "0x4" }, @@ -314,7 +313,6 @@ "EdgeDetect": "1", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALL_PERIODS", - "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x4" }, @@ -323,7 +321,7 @@ "Counter": "0,1,2,3", "EventCode": "0x83", "EventName": "ICACHE_TAG.STALLS", - "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", "SampleAfterValue": "200003", "UMask": "0x4" }, @@ -333,7 +331,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -343,7 +341,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -352,7 +350,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.DSB_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -362,7 +360,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -372,7 +370,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -381,7 +379,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -391,7 +389,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES_ANY", - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -402,7 +400,7 @@ "EdgeDetect": "1", "EventCode": "0x79", "EventName": "IDQ.MS_SWITCHES", - "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -411,7 +409,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", - "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -420,7 +418,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CORE", - "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0", + "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -430,7 +428,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -441,7 +439,7 @@ "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -450,7 +448,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -460,7 +458,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -471,7 +469,7 @@ "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", "SampleAfterValue": "1000003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json b/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json index 9a620e1b8de8..cc3c834ca286 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json @@ -1,28 +1,28 @@ [ { "BriefDescription": "C1 residency percent per core", - "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricExpr": "cstate_core@c1\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C1_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" @@ -381,7 +381,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -416,39 +416,39 @@ "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" }, { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " + }, + { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "MetricName": "tma_bottleneck_data_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + 0 / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency) + tma_memory_bound * (tma_l3_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "MetricName": "tma_bottleneck_data_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_bottleneck_compute_bound_est", - "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -456,7 +456,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -464,7 +464,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", @@ -480,7 +480,7 @@ }, { "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_data_cache_memory_bandwidth + tma_bottleneck_data_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", @@ -496,7 +496,7 @@ { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "BadSpec;BrMispredicts;BvMP;Default;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", @@ -613,7 +613,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * min(MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS:R, 74.6 * tma_info_system_core_frequency) + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * min(MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R, 76.6 * tma_info_system_core_frequency) * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", @@ -633,6 +632,15 @@ "ScaleUnit": "100%" }, { + "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external CXL Memory by loads (e.g", + "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_CXL_MEM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_CXL_MEM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0))) if #has_pmem > 0 else 1)) * (MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_CXL_MEM + MEM_LOAD_RETIRED.LOCAL_CXL_MEM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", + "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_cxl_mem_bound", + "MetricThreshold": "tma_cxl_mem_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external CXL Memory by loads (e.g. 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory, PMM - Persistent Memory Module [from CLX to SPR] or any other CXL Type3 Memory [EMR onwards]).", + "ScaleUnit": "100%" + }, + { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * min(MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD:R, 74.6 * tma_info_system_core_frequency) + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * min(MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R, 74.6 * tma_info_system_core_frequency) * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", @@ -662,7 +670,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks", + "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks - tma_cxl_mem_bound if #has_pmem > 0 else MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks)", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -720,7 +728,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -848,7 +856,7 @@ { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", @@ -1395,19 +1403,19 @@ { "BriefDescription": "Off-core accesses per kilo instruction for modified write requests", "MetricExpr": "1e3 * OCR.MODIFIED_WRITE.ANY_RESPONSE / tma_info_inst_mix_instructions", - "MetricGroup": "Offcore", + "MetricGroup": "Offcore;Server", "MetricName": "tma_info_memory_mix_offcore_mwrite_any_pki" }, { "BriefDescription": "Off-core accesses per kilo instruction for reads-to-core requests (speculative; including in-core HW prefetches)", "MetricExpr": "1e3 * OCR.READS_TO_CORE.ANY_RESPONSE / tma_info_inst_mix_instructions", - "MetricGroup": "CacheHits;Offcore", + "MetricGroup": "CacheHits;Offcore;Server", "MetricName": "tma_info_memory_mix_offcore_read_any_pki" }, { "BriefDescription": "L3 cache misses per kilo instruction for reads-to-core requests (speculative; including in-core HW prefetches)", "MetricExpr": "1e3 * OCR.READS_TO_CORE.L3_MISS / tma_info_inst_mix_instructions", - "MetricGroup": "Offcore", + "MetricGroup": "Offcore;Server", "MetricName": "tma_info_memory_mix_offcore_read_l3m_pki" }, { @@ -1433,21 +1441,21 @@ { "BriefDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket", "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / tma_info_system_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", + "MetricGroup": "HPC;Mem;MemoryBW;Offcore;Server", "MetricName": "tma_info_memory_soc_r2c_dram_bw", "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW." }, { "BriefDescription": "Average L3-cache miss BW for Reads-to-Core (R2C)", "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / tma_info_system_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", + "MetricGroup": "HPC;Mem;MemoryBW;Offcore;Server", "MetricName": "tma_info_memory_soc_r2c_l3m_bw", "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW." }, { "BriefDescription": "Average Off-core access BW for Reads-to-Core (R2C)", "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / tma_info_system_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", + "MetricGroup": "HPC;Mem;MemoryBW;Offcore;Server", "MetricName": "tma_info_memory_soc_r2c_offcore_bw", "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches." }, @@ -1491,7 +1499,7 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -1538,7 +1546,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1550,16 +1558,28 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, { + "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", + "MetricExpr": "(64 * UNC_CXLCM_RxC_PACK_BUF_INSERTS.MEM_DATA / 1e9 / tma_info_system_time if #has_pmem > 0 else 0)", + "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", + "MetricName": "tma_info_system_cxl_mem_read_bw" + }, + { + "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "(64 * UNC_CXLDP_TxC_AGF_INSERTS.M2S_DATA / 1e9 / tma_info_system_time if #has_pmem > 0 else 0)", + "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", + "MetricName": "tma_info_system_cxl_mem_write_bw" + }, + { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", "MetricExpr": "64 * (UNC_M_CAS_COUNT_SCH0.RD + UNC_M_CAS_COUNT_SCH1.RD + UNC_M_CAS_COUNT_SCH0.WR + UNC_M_CAS_COUNT_SCH1.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", @@ -1771,12 +1791,12 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "BriefDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1790,7 +1810,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * min(MEM_LOAD_RETIRED.L2_HIT:R, 4.4 * tma_info_system_core_frequency) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", @@ -1809,12 +1828,11 @@ }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_LOAD_RETIRED.L3_HIT * min(MEM_LOAD_RETIRED.L3_HIT:R, 32.6 * tma_info_system_core_frequency) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_data_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1897,6 +1915,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_INST_RETIRED.LOCK_LOADS * MEM_INST_RETIRED.LOCK_LOADS:R / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", @@ -1929,7 +1948,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1938,13 +1957,13 @@ "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "Backend;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -1954,7 +1973,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", @@ -2007,7 +2025,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", - "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2", + "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2.4", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -2042,6 +2060,7 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", @@ -2103,6 +2122,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", @@ -2112,6 +2132,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_THRESHOLD_AND_NMI", "MetricExpr": "max(EXE_ACTIVITY.EXE_BOUND_0_PORTS - RESOURCE_STALLS.SCOREBOARD, 0) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", @@ -2121,6 +2142,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_THRESHOLD_AND_NMI", "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", @@ -2130,7 +2152,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", @@ -2140,7 +2161,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", @@ -2150,7 +2170,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "(MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM:R + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD:R) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * PEBS + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * PEBS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -2159,7 +2179,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM:R * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * PEBS * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -2177,7 +2197,7 @@ { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2205,7 +2225,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", @@ -2237,7 +2256,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/memory.json b/tools/perf/pmu-events/arch/x86/graniterapids/memory.json index 4db39f304c2c..96f40390becf 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/memory.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/memory.json @@ -5,7 +5,6 @@ "CounterMask": "2", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", - "PublicDescription": "Cycles while L3 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -15,7 +14,6 @@ "CounterMask": "6", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", - "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x6" }, @@ -24,7 +22,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -34,7 +32,6 @@ "CounterMask": "2", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS", - "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -44,7 +41,6 @@ "CounterMask": "3", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS", - "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -54,7 +50,7 @@ "CounterMask": "5", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS", - "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", + "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -64,7 +60,7 @@ "CounterMask": "9", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS", - "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", + "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -412,7 +408,6 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -422,7 +417,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ. Available PDIST counters: 0", + "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -431,7 +426,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0", + "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -449,7 +444,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_EVENTS", - "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt). Available PDIST counters: 0", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -458,7 +453,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_MEM", - "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts). Available PDIST counters: 0", + "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -467,7 +462,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", - "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.", "SampleAfterValue": "100003", "UMask": "0x40" }, @@ -476,7 +471,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", - "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -485,7 +480,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.COMMIT", - "PublicDescription": "Counts the number of times RTM commit succeeded. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times RTM commit succeeded.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -494,7 +489,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.START", - "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -503,7 +498,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CAPACITY_READ", - "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads Available PDIST counters: 0", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -512,7 +507,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CAPACITY_WRITE", - "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes. Available PDIST counters: 0", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -521,7 +516,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CONFLICT", - "PublicDescription": "Counts the number of times a TSX line had a cache conflict. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times a TSX line had a cache conflict.", "SampleAfterValue": "100003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/other.json b/tools/perf/pmu-events/arch/x86/graniterapids/other.json index 8b7aa4caec46..c0747750b1a8 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/other.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/other.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.HARDWARE", - "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count. Available PDIST counters: 0", + "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -13,11 +13,35 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.PAGE_FAULT", - "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, { + "BriefDescription": "HW_INTERRUPTS.MASKED", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcb", + "EventName": "HW_INTERRUPTS.MASKED", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "HW_INTERRUPTS.PENDING_AND_MASKED", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcb", + "EventName": "HW_INTERRUPTS.PENDING_AND_MASKED", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of hardware interrupts received by the processor.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcb", + "EventName": "HW_INTERRUPTS.RECEIVED", + "PublicDescription": "Counts the number of hardware interruptions received by the processor.", + "SampleAfterValue": "203", + "UMask": "0x1" + }, + { "BriefDescription": "Counts streaming stores that have any type of response.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", @@ -34,7 +58,7 @@ "CounterMask": "1", "EventCode": "0x2d", "EventName": "XQ.FULL_CYCLES", - "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", "SampleAfterValue": "1000003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json b/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json index 27af3bd6bacf..0fef8fd61974 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json @@ -5,7 +5,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.DIV_ACTIVE", - "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -15,7 +15,6 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.IDIV_ACTIVE", - "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -24,7 +23,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.ANY", - "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.", "SampleAfterValue": "100003", "UMask": "0x1b" }, @@ -271,7 +270,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C01", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -280,7 +279,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C02", - "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", + "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -289,7 +288,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C0_WAIT", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", "SampleAfterValue": "2000003", "UMask": "0x70" }, @@ -298,7 +297,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED", - "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", + "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -307,7 +306,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0", + "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.", "SampleAfterValue": "25003", "UMask": "0x2" }, @@ -316,7 +315,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE", - "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -327,7 +325,6 @@ "EdgeDetect": "1", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", - "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -336,7 +333,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED", - "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", + "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -344,7 +341,7 @@ "BriefDescription": "Reference cycles when the core is not in halt state.", "Counter": "Fixed counter 2", "EventName": "CPU_CLK_UNHALTED.REF_TSC", - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003", "UMask": "0x3" }, @@ -353,7 +350,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -361,7 +358,7 @@ "BriefDescription": "Core cycles when the thread is not in halt state", "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.THREAD", - "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Available PDIST counters: 0", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -370,7 +367,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", "SampleAfterValue": "2000003" }, { @@ -379,7 +376,6 @@ "CounterMask": "8", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", - "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -389,7 +385,6 @@ "CounterMask": "1", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", - "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -399,7 +394,6 @@ "CounterMask": "16", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", - "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -409,7 +403,6 @@ "CounterMask": "12", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", - "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xc" }, @@ -419,7 +412,6 @@ "CounterMask": "5", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", - "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -429,7 +421,6 @@ "CounterMask": "4", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", - "PublicDescription": "Total execution stalls. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -438,7 +429,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb7", "EventName": "EXE.AMX_BUSY", - "PublicDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -447,7 +437,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -456,7 +446,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL", - "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0xc" }, @@ -465,7 +454,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -474,7 +463,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", - "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -483,7 +472,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", - "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -493,7 +482,6 @@ "CounterMask": "5", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", - "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x21" }, @@ -503,7 +491,7 @@ "CounterMask": "2", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", - "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -512,7 +500,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", - "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0", + "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", "SampleAfterValue": "1000003", "UMask": "0x80" }, @@ -521,7 +509,7 @@ "Counter": "0,1,2,3", "EventCode": "0x75", "EventName": "INST_DECODED.DECODERS", - "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -546,7 +534,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", - "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -555,7 +542,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -572,7 +559,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -583,7 +570,7 @@ "EdgeDetect": "1", "EventCode": "0xad", "EventName": "INT_MISC.CLEARS_COUNT", - "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -592,7 +579,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", - "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", "SampleAfterValue": "500009", "UMask": "0x80" }, @@ -601,7 +588,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.MBA_STALLS", - "PublicDescription": "INT_MISC.MBA_STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -610,7 +596,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.RECOVERY_CYCLES", - "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -621,7 +607,6 @@ "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", "MSRIndex": "0x3F7", "MSRValue": "0x7", - "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -630,7 +615,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.UOP_DROPPING", - "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -639,7 +624,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.128BIT", - "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x13" }, @@ -648,7 +632,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.256BIT", - "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xac" }, @@ -657,7 +640,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_128", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -666,7 +649,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_256", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", "SampleAfterValue": "1000003", "UMask": "0xc" }, @@ -675,7 +658,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.MUL_256", - "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80" }, @@ -684,7 +666,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.SHUFFLES", - "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -693,7 +674,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_128", - "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -702,7 +682,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_256", - "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -711,7 +690,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", - "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -720,7 +699,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.NO_SR", - "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", "SampleAfterValue": "100003", "UMask": "0x88" }, @@ -729,7 +708,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", "SampleAfterValue": "100003", "UMask": "0x82" }, @@ -738,7 +717,7 @@ "Counter": "0,1,2,3", "EventCode": "0x4c", "EventName": "LOAD_HIT_PREFETCH.SWPF", - "PublicDescription": "Counts all software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0", + "PublicDescription": "Counts all software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -748,7 +727,7 @@ "CounterMask": "1", "EventCode": "0xa8", "EventName": "LSD.CYCLES_ACTIVE", - "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -758,7 +737,7 @@ "CounterMask": "6", "EventCode": "0xa8", "EventName": "LSD.CYCLES_OK", - "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -767,7 +746,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa8", "EventName": "LSD.UOPS", - "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -778,7 +757,7 @@ "EdgeDetect": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.COUNT", - "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0", + "PublicDescription": "Counts the number of machine clears (nukes) of any type.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -787,7 +766,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SMC", - "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -796,7 +775,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe0", "EventName": "MISC2_RETIRED.LFENCE", - "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0", + "PublicDescription": "number of LFENCE retired instructions", "SampleAfterValue": "400009", "UMask": "0x20" }, @@ -805,7 +784,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcc", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -814,7 +793,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SB", - "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -823,7 +802,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SCOREBOARD", - "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -832,7 +810,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", "EventName": "RS.EMPTY", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", "SampleAfterValue": "1000003", "UMask": "0x7" }, @@ -844,7 +822,7 @@ "EventCode": "0xa5", "EventName": "RS.EMPTY_COUNT", "Invert": "1", - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", "SampleAfterValue": "100003", "UMask": "0x7" }, @@ -853,7 +831,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", "EventName": "RS.EMPTY_RESOURCE", - "PublicDescription": "Cycles when RS was empty and a resource allocation stall is asserted Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -862,7 +839,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", - "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0", + "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", "SampleAfterValue": "10000003", "UMask": "0x2" }, @@ -871,7 +848,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BAD_SPEC_SLOTS", - "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0", + "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.", "SampleAfterValue": "10000003", "UMask": "0x4" }, @@ -880,7 +857,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", - "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", "SampleAfterValue": "10000003", "UMask": "0x8" }, @@ -889,7 +866,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", - "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x10" }, @@ -897,7 +873,7 @@ "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event", "Counter": "Fixed counter 3", "EventName": "TOPDOWN.SLOTS", - "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3). Available PDIST counters: 0", + "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).", "SampleAfterValue": "10000003", "UMask": "0x4" }, @@ -906,7 +882,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.SLOTS_P", - "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", "SampleAfterValue": "10000003", "UMask": "0x1" }, @@ -915,7 +891,7 @@ "Counter": "0,1,2,3", "EventCode": "0x76", "EventName": "UOPS_DECODED.DEC0_UOPS", - "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0. Available PDIST counters: 0", + "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0.", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -924,7 +900,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_0", - "PublicDescription": "Number of uops dispatch to execution port 0. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution port 0.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -933,7 +909,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_1", - "PublicDescription": "Number of uops dispatch to execution port 1. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution port 1.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -942,7 +918,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_2_3_10", - "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -951,7 +927,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_4_9", - "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 4 and 9", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -960,7 +936,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_5_11", - "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 5 and 11", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -969,7 +945,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_6", - "PublicDescription": "Number of uops dispatch to execution port 6. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution port 6.", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -978,7 +954,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_7_8", - "PublicDescription": "Number of uops dispatch to execution ports 7 and 8. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 7 and 8.", "SampleAfterValue": "2000003", "UMask": "0x80" }, @@ -987,7 +963,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE", - "PublicDescription": "Counts the number of uops executed from any thread. Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops executed from any thread.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -997,7 +973,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -1007,7 +983,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -1017,7 +993,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -1027,7 +1003,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -1037,7 +1013,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_1", - "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1047,7 +1023,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_2", - "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1057,7 +1033,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_3", - "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1067,7 +1043,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_4", - "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1078,7 +1054,7 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALLS", "Invert": "1", - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1087,7 +1063,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.THREAD", - "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1096,7 +1071,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.X87", - "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of x87 uops executed.", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -1105,7 +1080,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xae", "EventName": "UOPS_ISSUED.ANY", - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1115,7 +1090,6 @@ "CounterMask": "1", "EventCode": "0xae", "EventName": "UOPS_ISSUED.CYCLES", - "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1125,7 +1099,7 @@ "CounterMask": "1", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.CYCLES", - "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where at least one uop has retired.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1134,7 +1108,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.HEAVY", - "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0", + "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1145,7 +1119,6 @@ "EventName": "UOPS_RETIRED.MS", "MSRIndex": "0x3F7", "MSRValue": "0x8", - "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -1154,7 +1127,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.SLOTS", - "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0", + "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -1165,7 +1138,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALLS", "Invert": "1", - "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0", + "PublicDescription": "This event counts cycles without actually retired uops.", "SampleAfterValue": "1000003", "UMask": "0x2" } diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json index 6667fbc50452..5eb1145f204f 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json @@ -833,12 +833,20 @@ "Counter": "0,1,2,3", "EventCode": "0x1F", "EventName": "UNC_I_MISC1.LOST_FWD", - "Experimental": "1", "PerPkg": "1", "UMask": "0x10", "Unit": "IRP" }, { + "BriefDescription": "Misc Events - Set 1 : Received Invalid : Secondary received a transfer that did not have sufficient MESI state", + "Counter": "0,1,2,3", + "EventCode": "0x1F", + "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { "BriefDescription": "Snoop Hit E/S responses", "Counter": "0,1,2,3", "EventCode": "0x12", diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-io.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-io.json index f4f956966e16..2ea2637df3fb 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-io.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-io.json @@ -1321,7 +1321,6 @@ "FCMask": "0x01", "PerPkg": "1", "PortMask": "0x0FF", - "PublicDescription": "-", "UMask": "0x4", "Unit": "IIO" }, diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json index b991f6e1afbe..f559e27e2815 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json @@ -60,6 +60,33 @@ "BriefDescription": "CAS count for SubChannel 0 regular reads", "Counter": "0,1,2,3", "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT_SCH0.RD_NON_UNDERFILL", + "PerPkg": "1", + "UMask": "0xc3", + "Unit": "IMC" + }, + { + "BriefDescription": "CAS count for SubChannel 0 auto-precharge reads", + "Counter": "0,1,2,3", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT_SCH0.RD_PRE_REG", + "PerPkg": "1", + "UMask": "0xc2", + "Unit": "IMC" + }, + { + "BriefDescription": "CAS count for SubChannel 0 auto-precharge underfill reads", + "Counter": "0,1,2,3", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT_SCH0.RD_PRE_UNDERFILL", + "PerPkg": "1", + "UMask": "0xc8", + "Unit": "IMC" + }, + { + "BriefDescription": "CAS count for SubChannel 0 regular reads", + "Counter": "0,1,2,3", + "EventCode": "0x05", "EventName": "UNC_M_CAS_COUNT_SCH0.RD_REG", "PerPkg": "1", "UMask": "0xc1", @@ -75,6 +102,15 @@ "Unit": "IMC" }, { + "BriefDescription": "CAS count for SubChannel 0 underfill reads", + "Counter": "0,1,2,3", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT_SCH0.RD_UNDERFILL_ALL", + "PerPkg": "1", + "UMask": "0xcc", + "Unit": "IMC" + }, + { "BriefDescription": "CAS count for SubChannel 0, all writes", "Counter": "0,1,2,3", "EventCode": "0x05", @@ -125,6 +161,33 @@ "BriefDescription": "CAS count for SubChannel 1 regular reads", "Counter": "0,1,2,3", "EventCode": "0x06", + "EventName": "UNC_M_CAS_COUNT_SCH1.RD_NON_UNDERFILL", + "PerPkg": "1", + "UMask": "0xc3", + "Unit": "IMC" + }, + { + "BriefDescription": "CAS count for SubChannel 1 auto-precharge reads", + "Counter": "0,1,2,3", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_COUNT_SCH1.RD_PRE_REG", + "PerPkg": "1", + "UMask": "0xc2", + "Unit": "IMC" + }, + { + "BriefDescription": "CAS count for SubChannel 1 auto-precharge underfill reads", + "Counter": "0,1,2,3", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_COUNT_SCH1.RD_PRE_UNDERFILL", + "PerPkg": "1", + "UMask": "0xc8", + "Unit": "IMC" + }, + { + "BriefDescription": "CAS count for SubChannel 1 regular reads", + "Counter": "0,1,2,3", + "EventCode": "0x06", "EventName": "UNC_M_CAS_COUNT_SCH1.RD_REG", "PerPkg": "1", "UMask": "0xc1", @@ -140,6 +203,15 @@ "Unit": "IMC" }, { + "BriefDescription": "CAS count for SubChannel 1 underfill reads", + "Counter": "0,1,2,3", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_COUNT_SCH1.RD_UNDERFILL_ALL", + "PerPkg": "1", + "UMask": "0xcc", + "Unit": "IMC" + }, + { "BriefDescription": "CAS count for SubChannel 1, all writes", "Counter": "0,1,2,3", "EventCode": "0x06", @@ -189,13 +261,52 @@ "Unit": "IMC" }, { + "BriefDescription": "PMMNT is sending REF* commands while being in specified Refresh rate", + "Counter": "0,1,2,3", + "EventCode": "0x72", + "EventName": "UNC_M_MNTCMD_REFRATE.REFAB1X", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "PMMNT is sending REF* commands while being in specified Refresh rate", + "Counter": "0,1,2,3", + "EventCode": "0x72", + "EventName": "UNC_M_MNTCMD_REFRATE.REFAB2X", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IMC" + }, + { + "BriefDescription": "PMMNT is sending REF* commands while being in specified Refresh rate", + "Counter": "0,1,2,3", + "EventCode": "0x72", + "EventName": "UNC_M_MNTCMD_REFRATE.REFSB1X", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "PMMNT is sending REF* commands while being in specified Refresh rate", + "Counter": "0,1,2,3", + "EventCode": "0x72", + "EventName": "UNC_M_MNTCMD_REFRATE.REFSB2X", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IMC" + }, + { "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh", "Counter": "0,1,2,3", "EventCode": "0xA7", "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -206,7 +317,6 @@ "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, @@ -217,7 +327,6 @@ "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x4", "Unit": "IMC" }, @@ -228,7 +337,6 @@ "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x8", "Unit": "IMC" }, @@ -239,7 +347,6 @@ "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -250,7 +357,6 @@ "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, @@ -261,7 +367,6 @@ "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x4", "Unit": "IMC" }, @@ -272,7 +377,6 @@ "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x8", "Unit": "IMC" }, @@ -283,7 +387,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -294,7 +397,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, @@ -305,7 +407,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK2", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x4", "Unit": "IMC" }, @@ -316,7 +417,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK3", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x8", "Unit": "IMC" }, @@ -327,7 +427,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x10", "Unit": "IMC" }, @@ -338,7 +437,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x20", "Unit": "IMC" }, @@ -349,7 +447,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK2", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x40", "Unit": "IMC" }, @@ -360,7 +457,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK3", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x80", "Unit": "IMC" }, @@ -371,7 +467,6 @@ "EventName": "UNC_M_POWER_CHANNEL_PPD_CYCLES", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "Unit": "IMC" }, { @@ -381,7 +476,6 @@ "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -392,7 +486,6 @@ "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, @@ -423,7 +516,6 @@ "EventName": "UNC_M_POWER_THROTTLE_CYCLES.MR4BLKEN", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x8", "Unit": "IMC" }, @@ -434,7 +526,6 @@ "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RAPLBLK", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x4", "Unit": "IMC" }, @@ -615,7 +706,6 @@ "EventName": "UNC_M_SELF_REFRESH.ENTER_SUCCESS", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "UNC_M_SELF_REFRESH.ENTER_SUCCESS", "UMask": "0x2", "Unit": "IMC" }, @@ -626,7 +716,6 @@ "EventName": "UNC_M_SELF_REFRESH.ENTER_SUCCESS_CYCLES", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -637,7 +726,6 @@ "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -648,7 +736,6 @@ "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, @@ -659,7 +746,6 @@ "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -670,7 +756,6 @@ "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, @@ -681,7 +766,6 @@ "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -692,7 +776,6 @@ "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, @@ -703,7 +786,6 @@ "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -714,7 +796,6 @@ "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json b/tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json index 3d3f88600e26..609a9549cbf3 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", - "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -14,7 +14,7 @@ "CounterMask": "1", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -23,7 +23,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -32,7 +32,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -41,7 +41,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -50,7 +50,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -59,7 +59,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -68,7 +68,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.STLB_HIT", - "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -78,7 +78,7 @@ "CounterMask": "1", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -87,7 +87,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -96,7 +96,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -105,7 +105,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -114,7 +114,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -123,7 +123,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -132,7 +132,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.STLB_HIT", - "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -142,7 +142,7 @@ "CounterMask": "1", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -151,7 +151,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -160,7 +160,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -169,7 +169,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -178,7 +178,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", "SampleAfterValue": "100003", "UMask": "0x10" } diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index b26ea70a3628..aebd82ced1cf 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -1,49 +1,49 @@ [ { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricExpr": "cstate_core@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" @@ -80,7 +80,6 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -98,7 +97,6 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", @@ -139,7 +137,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", @@ -509,7 +506,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -521,7 +518,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, @@ -696,7 +693,6 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", @@ -746,7 +742,7 @@ { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -856,7 +852,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", + "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -865,7 +861,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -874,7 +870,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -883,7 +879,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index 8245a98ad4b9..b8845f8a28b9 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -1,49 +1,49 @@ [ { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricExpr": "cstate_core@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" @@ -282,7 +282,6 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -300,7 +299,6 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", @@ -341,7 +339,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", @@ -711,7 +708,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -723,7 +720,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, @@ -756,6 +753,7 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", @@ -918,7 +916,6 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", @@ -928,6 +925,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", @@ -977,7 +975,7 @@ { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -1087,7 +1085,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", + "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -1096,7 +1094,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1105,7 +1103,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1114,7 +1112,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1141,6 +1139,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json index c5bfdb2f288b..cf9ed3edb694 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json @@ -1,63 +1,63 @@ [ { "BriefDescription": "C10 residency percent per package", - "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c10\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C10_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C8 residency percent per package", - "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c8\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C8_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C9 residency percent per package", - "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c9\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C9_Pkg_Residency", "ScaleUnit": "100%" @@ -85,7 +85,6 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", @@ -134,6 +133,7 @@ }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", @@ -148,39 +148,44 @@ "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" }, { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " + }, + { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "MetricName": "tma_bottleneck_data_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "MetricName": "tma_bottleneck_data_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_bottleneck_compute_bound_est", - "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -188,6 +193,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", @@ -196,6 +202,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", @@ -204,6 +211,7 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", @@ -212,7 +220,8 @@ }, { "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_data_cache_memory_bandwidth + tma_bottleneck_data_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", @@ -220,6 +229,7 @@ }, { "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -427,7 +437,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -619,6 +629,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", @@ -1068,7 +1079,7 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -1092,6 +1103,12 @@ "MetricName": "tma_info_pipeline_fetch_mite" }, { + "BriefDescription": "Average number of uops fetched from MS per cycle", + "MetricExpr": "IDQ.MS_UOPS / cpu@IDQ.MS_UOPS\\,cmask\\=1@", + "MetricGroup": "Fed;FetchLat;MicroSeq", + "MetricName": "tma_info_pipeline_fetch_ms" + }, + { "BriefDescription": "Instructions per a microcode Assist invocation", "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", @@ -1107,7 +1124,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1119,7 +1136,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, @@ -1128,7 +1145,7 @@ "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", @@ -1296,12 +1313,12 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "BriefDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1325,7 +1342,6 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -1339,7 +1355,7 @@ "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_data_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1445,7 +1461,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1454,7 +1470,7 @@ "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1522,7 +1538,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", - "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 2", + "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 3.3", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -1656,7 +1672,7 @@ { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1693,7 +1709,6 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", @@ -1707,7 +1722,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -1721,7 +1736,6 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index a886a0cfee07..f58eec2a1788 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -1,28 +1,28 @@ [ { "BriefDescription": "C1 residency percent per core", - "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricExpr": "cstate_core@c1\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C1_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" @@ -79,6 +79,12 @@ "ScaleUnit": "1MB/s" }, { + "BriefDescription": "Bandwidth of inbound IO reads that are initiated by end device controllers that are requesting memory from the CPU and miss the L3 cache", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_read_l3_miss", + "ScaleUnit": "1MB/s" + }, + { "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read_local", @@ -97,6 +103,12 @@ "ScaleUnit": "1MB/s" }, { + "BriefDescription": "Bandwidth of inbound IO writes that are initiated by end device controllers that are writing memory to the CPU", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_MISS_ITOM + UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR) * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_write_l3_miss", + "ScaleUnit": "1MB/s" + }, + { "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write_local", @@ -109,6 +121,24 @@ "ScaleUnit": "1MB/s" }, { + "BriefDescription": "The percent of inbound full cache line writes initiated by IO that miss the L3 cache", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM / UNC_CHA_TOR_INSERTS.IO_ITOM", + "MetricName": "io_full_write_l3_miss", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "The percent of inbound partial writes initiated by IO that miss the L3 cache", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_RFO) / (UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_RFO)", + "MetricName": "io_partial_write_l3_miss", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "The percent of inbound reads initiated by IO that miss the L3 cache", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR / UNC_CHA_TOR_INSERTS.IO_PCIRDCUR", + "MetricName": "io_read_l3_miss", + "ScaleUnit": "100%" + }, + { "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "itlb_2nd_level_large_page_mpi", @@ -331,7 +361,6 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", @@ -380,6 +409,7 @@ }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", @@ -394,39 +424,44 @@ "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" }, { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " + }, + { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "MetricName": "tma_bottleneck_data_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "MetricName": "tma_bottleneck_data_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_bottleneck_compute_bound_est", - "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms))) - tma_bottleneck_big_code", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -434,7 +469,8 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -442,7 +478,8 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", @@ -450,6 +487,7 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", @@ -458,7 +496,8 @@ }, { "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_data_cache_memory_bandwidth + tma_bottleneck_data_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", @@ -466,6 +505,7 @@ }, { "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -585,6 +625,15 @@ "ScaleUnit": "100%" }, { + "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external CXL Memory by loads (e.g", + "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0))) if #has_pmem > 0 else 1)) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", + "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_cxl_mem_bound", + "MetricThreshold": "tma_cxl_mem_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external CXL Memory by loads (e.g. 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory, PMM - Persistent Memory Module [from CLX to SPR] or any other CXL Type3 Memory [EMR onwards]).", + "ScaleUnit": "100%" + }, + { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "43.5 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", @@ -615,7 +664,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound - tma_cxl_mem_bound if #has_pmem > 0 else CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound)", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -673,7 +722,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -865,6 +914,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite + tma_ms)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", @@ -1320,7 +1370,7 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -1338,6 +1388,12 @@ "MetricName": "tma_info_pipeline_fetch_mite" }, { + "BriefDescription": "Average number of uops fetched from MS per cycle", + "MetricExpr": "IDQ.MS_UOPS / cpu@IDQ.MS_UOPS\\,cmask\\=1@", + "MetricGroup": "Fed;FetchLat;MicroSeq", + "MetricName": "tma_info_pipeline_fetch_ms" + }, + { "BriefDescription": "Instructions per a microcode Assist invocation", "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", @@ -1353,7 +1409,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1365,16 +1421,28 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, { + "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", + "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / tma_info_system_time if #has_pmem > 0 else 0)", + "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", + "MetricName": "tma_info_system_cxl_mem_read_bw" + }, + { + "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / tma_info_system_time if #has_pmem > 0 else 0)", + "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", + "MetricName": "tma_info_system_cxl_mem_write_bw" + }, + { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", @@ -1433,12 +1501,20 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { + "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", + "MetricExpr": "(1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / cha_0@event\\=0x0@ if #has_pmem > 0 else 0)", + "MetricGroup": "MemOffcore;MemoryLat;Server;SoC", + "MetricName": "tma_info_system_mem_pmm_read_latency", + "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" + }, + { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", @@ -1590,12 +1666,12 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "BriefDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1619,7 +1695,6 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -1633,7 +1708,7 @@ "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_data_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1739,7 +1814,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1748,7 +1823,7 @@ "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1816,7 +1891,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", - "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 2", + "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 3.3", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -1968,7 +2043,7 @@ { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2005,7 +2080,6 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", @@ -2019,7 +2093,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -2033,7 +2107,6 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index de651ff9f846..969cb519eec1 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -1,49 +1,49 @@ [ { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricExpr": "cstate_core@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" @@ -80,7 +80,6 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5) / (3 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -98,7 +97,6 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", @@ -139,7 +137,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", @@ -561,7 +558,7 @@ "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -574,7 +571,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -586,7 +583,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, @@ -775,7 +772,6 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", @@ -926,7 +922,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -935,7 +931,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -944,7 +940,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 714d5e6d21e7..1cdd197ac883 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -1,49 +1,49 @@ [ { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricExpr": "cstate_core@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" @@ -80,7 +80,6 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5) / (3 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -98,7 +97,6 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", @@ -139,7 +137,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", @@ -561,7 +558,7 @@ "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -574,7 +571,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -586,7 +583,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, @@ -626,6 +623,7 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", @@ -795,7 +793,6 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", @@ -805,6 +802,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "200 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", @@ -955,7 +953,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -964,7 +962,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -973,7 +971,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1000,6 +998,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "310 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index 6f636ea0f216..250c73b21385 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -1,49 +1,49 @@ [ { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricExpr": "cstate_core@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" @@ -71,7 +71,6 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", @@ -296,7 +295,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -308,7 +307,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, @@ -348,6 +347,7 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/cache.json b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json index ff37d49611c3..402ca8fc50b6 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json @@ -29,6 +29,16 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Cachelines replaced into the L1 d-cache. Successful replacements only (not blocked) and exclude WB-miss case", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x51", + "EventName": "L1D.L1_REPLACEMENT", + "PublicDescription": "Counts cachelines replaced into the L1 d-cache.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { "BriefDescription": "Cachelines replaced into the L0 and L1 d-cache. Successful replacements only (not blocked) and exclude WB-miss case", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x51", @@ -592,7 +602,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PublicDescription": "Counts Instructions with at least one architecturally visible load retired. Available PDIST counters: 0", + "PublicDescription": "Counts Instructions with at least one architecturally visible load retired. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x81", "Unit": "cpu_core" @@ -603,7 +613,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0", + "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x82", "Unit": "cpu_core" @@ -613,7 +623,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_SWPF", - "PublicDescription": "Counts all retired software prefetch instructions. Available PDIST counters: 0", + "PublicDescription": "Counts all retired software prefetch instructions. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x84", "Unit": "cpu_core" @@ -624,7 +634,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0", + "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x87", "Unit": "cpu_core" @@ -635,7 +645,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x21", "Unit": "cpu_core" @@ -646,7 +656,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0x41", "Unit": "cpu_core" @@ -657,18 +667,29 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0x42", "Unit": "cpu_core" }, { + "BriefDescription": "Retired instructions that hit the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_HIT_ANY", + "PublicDescription": "Number of retired instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0xf", + "Unit": "cpu_core" + }, + { "BriefDescription": "Retired load instructions that hit the STLB.", "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS", - "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0", + "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0x9", "Unit": "cpu_core" @@ -679,18 +700,39 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES", - "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0", + "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0xa", "Unit": "cpu_core" }, { + "BriefDescription": "Retired SWPF instructions that hit the STLB.", + "Counter": "0,1,2,3", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_HIT_SWPF", + "PublicDescription": "Number of retired SWPF instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0xc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that miss the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_ANY", + "PublicDescription": "Retired instructions that miss the STLB. Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x17", + "Unit": "cpu_core" + }, + { "BriefDescription": "Retired load instructions that miss the STLB.", "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", + "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0x11", "Unit": "cpu_core" @@ -701,18 +743,28 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", + "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0x12", "Unit": "cpu_core" }, { + "BriefDescription": "Retired SWPF instructions that miss the STLB.", + "Counter": "0,1,2,3", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_SWPF", + "PublicDescription": "Number of retired SWPF instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x14", + "Unit": "cpu_core" + }, + { "BriefDescription": "Retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$)", "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$) Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$) Available PDIST counters: 0,1", "SampleAfterValue": "20011", "UMask": "0x10", "Unit": "cpu_core" @@ -723,7 +775,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", - "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded. Available PDIST counters: 0,1", "SampleAfterValue": "20011", "UMask": "0x4", "Unit": "cpu_core" @@ -734,7 +786,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0,1", "SampleAfterValue": "20011", "UMask": "0x1", "Unit": "cpu_core" @@ -745,7 +797,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0,1", "SampleAfterValue": "20011", "UMask": "0x2", "Unit": "cpu_core" @@ -756,7 +808,7 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.MEMSIDE_CACHE", - "PublicDescription": "Retired load instructions which data source is memory side cache. Available PDIST counters: 0", + "PublicDescription": "Retired load instructions which data source is memory side cache. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "Unit": "cpu_core" }, @@ -766,7 +818,7 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x4", "Unit": "cpu_core" @@ -777,7 +829,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x40", "Unit": "cpu_core" @@ -788,7 +840,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x101", "Unit": "cpu_core" @@ -799,7 +851,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT_L0", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the Level 0 of the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the Level 0 of the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -809,7 +861,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT_L1", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the Level 1 of the L1 data cache. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the Level 1 of the L1 data cache. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "Unit": "cpu_core" }, @@ -819,7 +871,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0,1", "SampleAfterValue": "200003", "UMask": "0x8", "Unit": "cpu_core" @@ -830,7 +882,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0,1", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_core" @@ -841,7 +893,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0,1", "SampleAfterValue": "100021", "UMask": "0x10", "Unit": "cpu_core" @@ -852,7 +904,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0,1", "SampleAfterValue": "100021", "UMask": "0x4", "Unit": "cpu_core" @@ -863,7 +915,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0,1", "SampleAfterValue": "50021", "UMask": "0x20", "Unit": "cpu_core" @@ -1254,6 +1306,18 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts writebacks of modified cachelines that were supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.COREWB_M.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x7E001E00008", + "PublicDescription": "Counts writebacks of modified cachelines that were supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts writebacks of non-modified cachelines that have any type of response.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", @@ -1266,6 +1330,18 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts writebacks of non-modified cachelines that were supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.COREWB_NONM.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x7E001E01000", + "PublicDescription": "Counts writebacks of non-modified cachelines that were supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", @@ -1303,7 +1379,7 @@ }, { "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -1315,7 +1391,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", @@ -1327,7 +1403,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches which forwarded the unmodified data to the requesting core.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -1363,7 +1439,7 @@ }, { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -1375,7 +1451,7 @@ }, { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", @@ -1386,6 +1462,18 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts all data read, code read, RFO and ITOM requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x7E001E04477", + "PublicDescription": "Counts all data read, code read, RFO and ITOM requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Any memory transaction that reached the SQ.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x21", diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json b/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json index e2facc4086e9..b21d602e9f1a 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json @@ -108,7 +108,7 @@ "EventName": "FRONTEND_RETIRED.ANY_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0", + "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -120,7 +120,7 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -169,7 +169,7 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0", + "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -199,7 +199,7 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -211,7 +211,7 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -223,7 +223,7 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -235,7 +235,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x608006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -247,7 +247,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x601006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -259,7 +259,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x600206", - "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -271,7 +271,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x610006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -283,7 +283,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -295,7 +295,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x602006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -307,7 +307,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x600406", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -319,7 +319,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x620006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -331,7 +331,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x604006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -343,7 +343,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x600806", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -355,7 +355,7 @@ "EventName": "FRONTEND_RETIRED.MISP_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0", + "PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x2", "Unit": "cpu_core" @@ -367,7 +367,7 @@ "EventName": "FRONTEND_RETIRED.MS_FLOWS", "MSRIndex": "0x3F7", "MSRValue": "0x8", - "PublicDescription": "Counts flows delivered by the Microcode Sequencer Available PDIST counters: 0", + "PublicDescription": "Counts flows delivered by the Microcode Sequencer Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -397,7 +397,7 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -409,7 +409,7 @@ "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "MSRIndex": "0x3F7", "MSRValue": "0x17", - "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0", + "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json b/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json index 3c740962e63e..06390a72110d 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json @@ -1,75 +1,47 @@ [ { "BriefDescription": "C10 residency percent per package", - "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c10\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C10_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C1 residency percent per core", - "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricExpr": "cstate_core@c1\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C1_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", - "ScaleUnit": "100%" - }, - { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "C8 residency percent per package", - "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C8_Pkg_Residency", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "C9 residency percent per package", - "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C9_Pkg_Residency", - "ScaleUnit": "100%" - }, - { "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", "MetricGroup": "smi", @@ -555,7 +527,7 @@ }, { "BriefDescription": "Average CPU Utilization", - "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.REF_TSC@ / TSC", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.REF_TSC@ / msr@tsc\\,cpu=cpu_atom@", "MetricName": "tma_info_system_cpu_utilization", "Unit": "cpu_atom" }, @@ -725,6 +697,13 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ", + "Unit": "cpu_core" + }, + { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricExpr": "cpu_core@UOPS_DISPATCHED.ALU@ / (6 * tma_info_thread_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", @@ -755,7 +734,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -767,7 +746,7 @@ { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "cpu_core@topdown\\-bad\\-spec@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-bad\\-spec@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -794,35 +773,35 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ", + "Unit": "cpu_core" + }, + { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_early_blk + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "MetricName": "tma_bottleneck_data_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_capacity / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_early_blk + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_capacity / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_early_blk + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_early_blk + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_early_blk + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "MetricName": "tma_bottleneck_data_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_bottleneck_compute_bound_est", - "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ", - "Unit": "cpu_core" - }, - { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20", @@ -830,7 +809,7 @@ }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -839,7 +818,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_early_blk + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -866,7 +845,7 @@ }, { "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_data_cache_memory_bandwidth + tma_bottleneck_data_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", @@ -883,7 +862,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", @@ -1023,7 +1002,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@R, 25 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", @@ -1076,7 +1054,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(cpu_core@IDQ.DSB_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ + cpu_core@IDQ.DSB_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", + "MetricExpr": "(cpu_core@IDQ.DSB_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / 2 + cpu_core@IDQ.DSB_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.STARVATION_CYCLES@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", @@ -1130,7 +1108,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1147,7 +1125,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -1197,7 +1175,7 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)", + "MetricExpr": "cpu_core@FP_ARITH_OPS_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", @@ -1207,7 +1185,7 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)", + "MetricExpr": "cpu_core@FP_ARITH_OPS_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", @@ -1217,7 +1195,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", + "MetricExpr": "(cpu_core@FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_OPS_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -1227,7 +1205,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR\\,umask\\=0x30@ / (tma_retiring * tma_info_thread_slots)", + "MetricExpr": "cpu_core@FP_ARITH_OPS_RETIRED.VECTOR\\,umask\\=0x30@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -1238,7 +1216,7 @@ { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -1259,7 +1237,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", @@ -1437,7 +1415,7 @@ }, { "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / tma_info_thread_clks", + "MetricExpr": "(cpu_core@FP_ARITH_OPS_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_OPS_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE@) / tma_info_thread_clks", "MetricGroup": "Flops;Ret", "MetricName": "tma_info_core_flopc", "Unit": "cpu_core" @@ -1578,7 +1556,7 @@ }, { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + cpu_core@FP_ARITH_INST_RETIRED.VECTOR@)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_OPS_RETIRED.SCALAR@ + cpu_core@FP_ARITH_OPS_RETIRED.VECTOR@)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", @@ -1587,7 +1565,7 @@ }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_OPS_RETIRED.128B_PACKED_SINGLE@)", "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", @@ -1596,7 +1574,7 @@ }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_OPS_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE@)", "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", @@ -1605,7 +1583,7 @@ }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@FP_ARITH_OPS_RETIRED.SCALAR_DOUBLE@", "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", @@ -1614,7 +1592,7 @@ }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@FP_ARITH_OPS_RETIRED.SCALAR_SINGLE@", "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", @@ -1639,7 +1617,7 @@ }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_OPS_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_OPS_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE@)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_ipflop", "MetricThreshold": "tma_info_inst_mix_ipflop < 10", @@ -1694,7 +1672,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * cpu_core@L1D.REPLACEMENT@ / 1e9 / tma_info_system_time", + "MetricExpr": "64 * cpu_core@L1D.L1_REPLACEMENT@ / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw", "Unit": "cpu_core" @@ -1707,6 +1685,13 @@ "Unit": "cpu_core" }, { + "BriefDescription": "L0 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * (cpu_core@MEM_LOAD_RETIRED.L1_MISS@ + cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@) / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l1dl0_mpki", + "Unit": "cpu_core" + }, + { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / cpu_core@INST_RETIRED.ANY@", "MetricGroup": "CacheHits;Mem", @@ -1922,6 +1907,13 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Average number of uops fetched from MS per cycle", + "MetricExpr": "cpu_core@IDQ.MS_UOPS@ / cpu_core@IDQ.MS_UOPS\\,cmask\\=1@", + "MetricGroup": "Fed;FetchLat;MicroSeq", + "MetricName": "tma_info_pipeline_fetch_ms", + "Unit": "cpu_core" + }, + { "BriefDescription": "Instructions per a microcode Assist invocation", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", @@ -1955,7 +1947,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc\\,cpu=cpu_core@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency", "Unit": "cpu_core" @@ -1969,14 +1961,22 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.REF_TSC@ / TSC", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.REF_TSC@ / msr@tsc\\,cpu=cpu_core@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized", "Unit": "cpu_core" }, { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "32 * UNC_M_TOTAL_DATA / 1e9 / tma_info_system_time", + "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full", + "Unit": "cpu_core" + }, + { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / 1e9 / tma_info_system_time", + "MetricExpr": "(cpu_core@FP_ARITH_OPS_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_OPS_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE@) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width", @@ -2021,6 +2021,13 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "UNC_CLOCK.SOCKET", + "MetricGroup": "SoC", + "MetricName": "tma_info_system_socket_clks", + "Unit": "cpu_core" + }, + { "BriefDescription": "Run duration time in seconds", "MetricExpr": "duration_time", "MetricGroup": "Summary", @@ -2036,6 +2043,13 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]", + "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time", + "MetricGroup": "SoC", + "MetricName": "tma_info_system_uncore_frequency", + "Unit": "cpu_core" + }, + { "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "Pipeline", @@ -2156,12 +2170,12 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", - "MetricExpr": "4 * cpu_core@DEPENDENT_LOADS.ANY@ / tma_info_thread_clks", + "BriefDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "MetricExpr": "4 * cpu_core@DEPENDENT_LOADS.ANY\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS", + "PublicDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2177,7 +2191,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@R, 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", @@ -2198,12 +2211,11 @@ }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@R, 9 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_data_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2285,6 +2297,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@MEM_INST_RETIRED.LOCK_LOADS@R / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", @@ -2295,7 +2308,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit", - "MetricExpr": "cpu_core@LSD.UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks", + "MetricExpr": "cpu_core@LSD.UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks / 2", "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", @@ -2320,7 +2333,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2330,13 +2343,13 @@ "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -2347,7 +2360,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", @@ -2386,7 +2398,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / 2 + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", + "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / 2 + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.STARVATION_CYCLES@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", @@ -2406,7 +2418,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", - "MetricExpr": "cpu_core@IDQ.MS_CYCLES_ANY@ / tma_info_thread_clks", + "MetricExpr": "cpu_core@IDQ.MS_CYCLES_ANY@ / tma_info_thread_clks / 1.8", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -2445,7 +2457,8 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", - "MetricExpr": "max(0, tma_light_operations - (tma_x87_use + (cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + cpu_core@FP_ARITH_INST_RETIRED.VECTOR@) / (tma_retiring * tma_info_thread_slots) + (cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@ + cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_thread_slots) + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "max(0, tma_light_operations - (tma_x87_use + (cpu_core@FP_ARITH_OPS_RETIRED.SCALAR@ + cpu_core@FP_ARITH_OPS_RETIRED.VECTOR@) / (tma_retiring * tma_info_thread_slots) + (cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@ + cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_thread_slots) + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6", @@ -2483,6 +2496,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "((cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", @@ -2493,6 +2507,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_THRESHOLD_AND_NMI", "MetricExpr": "cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", @@ -2503,6 +2518,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_THRESHOLD_AND_NMI", "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", @@ -2513,7 +2529,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", @@ -2524,7 +2539,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", @@ -2545,7 +2559,7 @@ { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2576,7 +2590,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", @@ -2611,7 +2624,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2626,6 +2639,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "This metric estimates clocks wasted due to loads blocked due to unknown store address (did not do memory disambiguation) or due to unknown store data", + "MetricExpr": "7 * cpu_core@LD_BLOCKS.STORE_EARLY\\,cmask\\=1@ / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_early_blk", + "MetricThreshold": "tma_store_early_blk > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/memory.json b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json index 8021a1c7dd3b..caa387e10259 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json @@ -163,7 +163,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "53", "UMask": "0x1", "Unit": "cpu_core" @@ -176,7 +176,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "1009", "UMask": "0x1", "Unit": "cpu_core" @@ -189,7 +189,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "20011", "UMask": "0x1", "Unit": "cpu_core" @@ -202,7 +202,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048", "MSRIndex": "0x3F6", "MSRValue": "0x800", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "23", "UMask": "0x1", "Unit": "cpu_core" @@ -215,7 +215,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "503", "UMask": "0x1", "Unit": "cpu_core" @@ -228,7 +228,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -241,7 +241,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -254,7 +254,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "101", "UMask": "0x1", "Unit": "cpu_core" @@ -267,7 +267,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "2003", "UMask": "0x1", "Unit": "cpu_core" @@ -280,7 +280,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "50021", "UMask": "0x1", "Unit": "cpu_core" @@ -291,7 +291,7 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -352,7 +352,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by DRAM.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -376,7 +376,7 @@ }, { "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", @@ -412,7 +412,7 @@ }, { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/other.json b/tools/perf/pmu-events/arch/x86/lunarlake/other.json index 59949f9541d8..1df716442549 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/other.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/other.json @@ -151,7 +151,7 @@ }, { "BriefDescription": "Counts streaming stores that have any type of response.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json index 6ac410510628..cdaa01e9a57d 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json @@ -110,7 +110,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -128,7 +128,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x111", "Unit": "cpu_core" @@ -147,7 +147,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x10", "Unit": "cpu_core" @@ -166,7 +166,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x101", "Unit": "cpu_core" @@ -176,7 +176,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN_BWD", - "PublicDescription": "Counts taken backward conditional branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts taken backward conditional branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x1", "Unit": "cpu_core" @@ -186,7 +186,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN_FWD", - "PublicDescription": "Counts taken forward conditional branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts taken forward conditional branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x102", "Unit": "cpu_core" @@ -205,7 +205,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x40", "Unit": "cpu_core" @@ -224,7 +224,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", + "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -261,7 +261,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x2", "Unit": "cpu_core" @@ -280,13 +280,13 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x8", "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of taken branch instructions retired", + "BriefDescription": "Counts the number of near taken branch instructions retired", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", @@ -299,7 +299,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -327,7 +327,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -336,7 +336,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST", - "PublicDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x44", "Unit": "cpu_core" @@ -355,7 +355,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x111", "Unit": "cpu_core" @@ -365,7 +365,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_COST", - "PublicDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x151", "Unit": "cpu_core" @@ -384,7 +384,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0", + "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x10", "Unit": "cpu_core" @@ -394,7 +394,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST", - "PublicDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x50", "Unit": "cpu_core" @@ -413,7 +413,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x101", "Unit": "cpu_core" @@ -423,7 +423,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD", - "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x1", "Unit": "cpu_core" @@ -433,7 +433,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD_COST", - "PublicDescription": "number of branch instructions retired that were mispredicted and taken backward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "number of branch instructions retired that were mispredicted and taken backward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x8001", "Unit": "cpu_core" @@ -443,7 +443,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST", - "PublicDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x141", "Unit": "cpu_core" @@ -453,7 +453,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD", - "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -462,7 +462,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD_COST", - "PublicDescription": "number of branch instructions retired that were mispredicted and taken forward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "number of branch instructions retired that were mispredicted and taken forward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x8002", "Unit": "cpu_core" @@ -481,7 +481,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", + "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -500,7 +500,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0", + "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x2", "Unit": "cpu_core" @@ -510,7 +510,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST", - "PublicDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x42", "Unit": "cpu_core" @@ -520,7 +520,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_COST", - "PublicDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0xc0", "Unit": "cpu_core" @@ -548,7 +548,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -558,7 +558,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST", - "PublicDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "400009", "UMask": "0x60", "Unit": "cpu_core" @@ -568,7 +568,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x8", "Unit": "cpu_core" @@ -587,7 +587,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET_COST", - "PublicDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "PublicDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x48", "Unit": "cpu_core" @@ -906,7 +906,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 0", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 0,1", "SampleAfterValue": "2000003", "Unit": "cpu_core" }, @@ -915,7 +915,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.BR_FUSED", - "PublicDescription": "retired macro-fused uops when there is a branch in the macro-fused pair (the two instructions that got macro-fused count once in this pmon) Available PDIST counters: 0", + "PublicDescription": "retired macro-fused uops when there is a branch in the macro-fused pair (the two instructions that got macro-fused count once in this pmon) Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -925,7 +925,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", - "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0", + "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0,1", "SampleAfterValue": "2000003", "UMask": "0x30", "Unit": "cpu_core" @@ -935,7 +935,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0,1", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -954,7 +954,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0,1", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1228,6 +1228,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of times a load got early blocked due to preceding store operation with unknown address or unknown data. Excluding in-line (immediate) wakeups", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_EARLY", + "SampleAfterValue": "100003", + "UMask": "0xa1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of occurrences a retired load gets blocked because its address partially overlaps with an older store (size mismatch) - unknown_sta/bad_forward", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x03", @@ -1451,7 +1460,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xe4", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PublicDescription": "LBR record is inserted Available PDIST counters: 0", + "PublicDescription": "LBR record is inserted Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/lunarlake/uncore-interconnect.json new file mode 100644 index 000000000000..69ef928d57f6 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/lunarlake/uncore-interconnect.json @@ -0,0 +1,10 @@ +[ + { + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "Counter": "FIXED", + "EventCode": "0xff", + "EventName": "UNC_CLOCK.SOCKET", + "PerPkg": "1", + "Unit": "SANTA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/uncore-memory.json b/tools/perf/pmu-events/arch/x86/lunarlake/uncore-memory.json index 7d63580302de..63c4aa2791e4 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/uncore-memory.json @@ -32,5 +32,13 @@ "Experimental": "1", "PerPkg": "1", "Unit": "iMC" + }, + { + "BriefDescription": "Total number of read and write byte transfers to/from DRAM, in 32B chunk, per DDR channel. Counter increments by 1 after sending or receiving 32B chunk data.", + "Counter": "0,1,2,3,4", + "EventCode": "0x3C", + "EventName": "UNC_M_TOTAL_DATA", + "PerPkg": "1", + "Unit": "iMC" } ] diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 354ce241500b..32093bded949 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -1,7 +1,7 @@ Family-model,Version,Filename,EventType -GenuineIntel-6-(97|9A|B7|BA|BF),v1.31,alderlake,core -GenuineIntel-6-BE,v1.31,alderlaken,core -GenuineIntel-6-C[56],v1.09,arrowlake,core +GenuineIntel-6-(97|9A|B7|BA|BF),v1.34,alderlake,core +GenuineIntel-6-BE,v1.34,alderlaken,core +GenuineIntel-6-C[56],v1.13,arrowlake,core GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core GenuineIntel-6-(3D|47),v30,broadwell,core GenuineIntel-6-56,v12,broadwellde,core @@ -9,11 +9,11 @@ GenuineIntel-6-4F,v23,broadwellx,core GenuineIntel-6-55-[56789ABCDEF],v1.25,cascadelakex,core GenuineIntel-6-DD,v1.00,clearwaterforest,core GenuineIntel-6-9[6C],v1.05,elkhartlake,core -GenuineIntel-6-CF,v1.14,emeraldrapids,core +GenuineIntel-6-CF,v1.20,emeraldrapids,core GenuineIntel-6-5[CF],v13,goldmont,core GenuineIntel-6-7A,v1.01,goldmontplus,core -GenuineIntel-6-B6,v1.09,grandridge,core -GenuineIntel-6-A[DE],v1.10,graniterapids,core +GenuineIntel-6-B6,v1.10,grandridge,core +GenuineIntel-6-A[DE],v1.15,graniterapids,core GenuineIntel-6-(3C|45|46),v36,haswell,core GenuineIntel-6-3F,v29,haswellx,core GenuineIntel-6-7[DE],v1.24,icelake,core @@ -22,15 +22,15 @@ GenuineIntel-6-3A,v24,ivybridge,core GenuineIntel-6-3E,v24,ivytown,core GenuineIntel-6-2D,v24,jaketown,core GenuineIntel-6-(57|85),v16,knightslanding,core -GenuineIntel-6-BD,v1.14,lunarlake,core -GenuineIntel-6-(AA|AC|B5),v1.14,meteorlake,core +GenuineIntel-6-BD,v1.18,lunarlake,core +GenuineIntel-6-(AA|AC|B5),v1.17,meteorlake,core GenuineIntel-6-1[AEF],v4,nehalemep,core GenuineIntel-6-2E,v4,nehalemex,core GenuineIntel-6-CC,v1.00,pantherlake,core GenuineIntel-6-A7,v1.04,rocketlake,core GenuineIntel-6-2A,v19,sandybridge,core -GenuineIntel-6-8F,v1.28,sapphirerapids,core -GenuineIntel-6-AF,v1.11,sierraforest,core +GenuineIntel-6-8F,v1.35,sapphirerapids,core +GenuineIntel-6-AF,v1.12,sierraforest,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v59,skylake,core GenuineIntel-6-55-[01234],v1.37,skylakex,core diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json index 82b115183924..d4731e300d6d 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json @@ -14,7 +14,6 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.HWPF_MISS", - "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20", "Unit": "cpu_core" @@ -24,7 +23,7 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.REPLACEMENT", - "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -34,7 +33,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -46,7 +45,7 @@ "EdgeDetect": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS", - "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", + "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -56,7 +55,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALLS", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -66,7 +65,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -77,7 +76,7 @@ "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -87,7 +86,7 @@ "Counter": "0,1,2,3", "EventCode": "0x25", "EventName": "L2_LINES_IN.ALL", - "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", "SampleAfterValue": "100003", "UMask": "0x1f", "Unit": "cpu_core" @@ -147,7 +146,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.NON_SILENT", - "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_core" @@ -167,7 +166,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", "SampleAfterValue": "200003", "UMask": "0x1", "Unit": "cpu_core" @@ -177,7 +176,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.USELESS_HWPF", - "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", "SampleAfterValue": "200003", "UMask": "0x4", "Unit": "cpu_core" @@ -187,7 +186,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.ALL", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]", "SampleAfterValue": "200003", "UMask": "0xff", "Unit": "cpu_core" @@ -206,7 +205,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.HIT", - "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT] Available PDIST counters: 0", + "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT]", "SampleAfterValue": "200003", "UMask": "0xdf", "Unit": "cpu_core" @@ -225,7 +224,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", "SampleAfterValue": "200003", "UMask": "0x3f", "Unit": "cpu_core" @@ -244,7 +243,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", - "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0", + "PublicDescription": "Counts the total number of L2 code requests.", "SampleAfterValue": "200003", "UMask": "0xe4", "Unit": "cpu_core" @@ -254,7 +253,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", "SampleAfterValue": "200003", "UMask": "0xe1", "Unit": "cpu_core" @@ -264,7 +263,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_MISS", - "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts demand requests that miss L2 cache.", "SampleAfterValue": "200003", "UMask": "0x27", "Unit": "cpu_core" @@ -274,7 +273,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", - "PublicDescription": "Counts demand requests to L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts demand requests to L2 cache.", "SampleAfterValue": "200003", "UMask": "0xe7", "Unit": "cpu_core" @@ -284,7 +283,6 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_HWPF", - "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf0", "Unit": "cpu_core" @@ -294,7 +292,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_RFO", - "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", "SampleAfterValue": "200003", "UMask": "0xe2", "Unit": "cpu_core" @@ -304,7 +302,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", - "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", "SampleAfterValue": "200003", "UMask": "0xc4", "Unit": "cpu_core" @@ -314,7 +312,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", - "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", "SampleAfterValue": "200003", "UMask": "0x24", "Unit": "cpu_core" @@ -324,7 +322,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", "SampleAfterValue": "200003", "UMask": "0xc1", "Unit": "cpu_core" @@ -334,7 +332,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", - "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", + "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", "SampleAfterValue": "200003", "UMask": "0x21", "Unit": "cpu_core" @@ -344,7 +342,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HIT", - "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT] Available PDIST counters: 0", + "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT]", "SampleAfterValue": "200003", "UMask": "0xdf", "Unit": "cpu_core" @@ -354,7 +352,6 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HWPF_MISS", - "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x30", "Unit": "cpu_core" @@ -364,7 +361,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", "SampleAfterValue": "200003", "UMask": "0x3f", "Unit": "cpu_core" @@ -374,7 +371,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.REFERENCES", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]", "SampleAfterValue": "200003", "UMask": "0xff", "Unit": "cpu_core" @@ -384,7 +381,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", "SampleAfterValue": "200003", "UMask": "0xc2", "Unit": "cpu_core" @@ -394,7 +391,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", "SampleAfterValue": "200003", "UMask": "0x22", "Unit": "cpu_core" @@ -404,7 +401,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_HIT", - "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", + "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", "SampleAfterValue": "200003", "UMask": "0xc8", "Unit": "cpu_core" @@ -414,7 +411,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_MISS", - "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", + "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", "SampleAfterValue": "200003", "UMask": "0x28", "Unit": "cpu_core" @@ -424,7 +421,7 @@ "Counter": "0,1,2,3", "EventCode": "0x23", "EventName": "L2_TRANS.L2_WB", - "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts L2 writebacks that access L2 cache.", "SampleAfterValue": "200003", "UMask": "0x40", "Unit": "cpu_core" @@ -434,7 +431,7 @@ "Counter": "0,1,2,3", "EventCode": "0x42", "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", - "PublicDescription": "This event counts the number of cycles when the L1D is locked. It is a superset of the 0x1 mask (BUS_LOCK_CLOCKS.BUS_LOCK_DURATION). Available PDIST counters: 0", + "PublicDescription": "This event counts the number of cycles when the L1D is locked. It is a superset of the 0x1 mask (BUS_LOCK_CLOCKS.BUS_LOCK_DURATION).", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -454,7 +451,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", - "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", "SampleAfterValue": "100003", "UMask": "0x41", "Unit": "cpu_core" @@ -474,7 +471,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", "SampleAfterValue": "100003", "UMask": "0x4f", "Unit": "cpu_core" @@ -695,7 +692,7 @@ "Counter": "0,1,2,3", "EventCode": "0x43", "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY", - "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0", + "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)", "SampleAfterValue": "1000003", "UMask": "0xfd", "Unit": "cpu_core" @@ -947,7 +944,6 @@ "Counter": "0,1,2,3", "EventCode": "0x44", "EventName": "MEM_STORE_RETIRED.L2_HIT", - "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1", "Unit": "cpu_core" @@ -974,7 +970,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024", @@ -986,7 +982,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", @@ -998,7 +994,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", @@ -1010,7 +1006,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048", @@ -1022,7 +1018,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", @@ -1034,7 +1030,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", @@ -1046,7 +1042,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", @@ -1058,7 +1054,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", @@ -1070,7 +1066,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", @@ -1082,7 +1078,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", @@ -1177,12 +1173,36 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe5", "EventName": "MEM_UOP_RETIRED.ANY", - "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0", + "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" }, { + "BriefDescription": "Counts writebacks of modified cachelines that hit in the L3 or were snooped from another core's caches.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.COREWB_M.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0008", + "PublicDescription": "Counts writebacks of modified cachelines that hit in the L3 or were snooped from another core's caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts writebacks of non-modified cachelines that hit in the L3 or were snooped from another core's caches.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.COREWB_NONM.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C1000", + "PublicDescription": "Counts writebacks of non-modified cachelines that hit in the L3 or were snooped from another core's caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", @@ -1399,11 +1419,23 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts all data read, code read, RFO and ITOM requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C4477", + "PublicDescription": "Counts all data read, code read, RFO and ITOM requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Any memory transaction that reached the SQ.", "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", - "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc.. Available PDIST counters: 0", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -1413,7 +1445,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DATA_RD", - "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -1423,7 +1455,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", - "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests. Available PDIST counters: 0", + "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -1433,7 +1465,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", - "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1443,7 +1475,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", - "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -1454,7 +1486,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1465,7 +1497,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1476,7 +1508,6 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", - "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1487,7 +1518,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1497,7 +1528,6 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", - "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1507,7 +1537,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1517,7 +1547,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1527,7 +1557,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", - "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion. Available PDIST counters: 0", + "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1537,7 +1567,7 @@ "Counter": "0,1,2,3", "EventCode": "0x2c", "EventName": "SQ_MISC.BUS_LOCK", - "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -1547,7 +1577,6 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.ANY", - "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xf", "Unit": "cpu_core" @@ -1557,7 +1586,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.NTA", - "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1567,7 +1596,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", - "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHW instructions executed.", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -1577,7 +1606,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T0", - "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -1587,7 +1616,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T1_T2", - "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json b/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json index ae9778aa755b..28dc5e06ee31 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json @@ -15,7 +15,6 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.FPDIV_ACTIVE", - "PublicDescription": "This event counts the cycles the floating point divider is busy. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -25,7 +24,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.FP", - "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0", + "PublicDescription": "Counts all microcode Floating Point assists.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -35,7 +34,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.SSE_AVX_MIX", - "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -45,7 +43,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_0", - "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -55,7 +52,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_1", - "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -65,7 +61,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_5", - "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -75,7 +70,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V0", - "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -85,7 +79,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V1", - "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -95,7 +88,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V2", - "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -105,7 +97,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -115,7 +107,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -125,7 +117,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -135,7 +127,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -145,7 +137,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x18", "Unit": "cpu_core" @@ -155,7 +147,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", - "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" @@ -165,7 +157,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -175,7 +167,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -185,7 +177,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.VECTOR", - "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "1000003", "UMask": "0xfc", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json index 82727022efb6..6484834b1127 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json @@ -14,7 +14,7 @@ "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "BACLEARS.ANY", - "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -24,7 +24,7 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.LCP", - "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", "SampleAfterValue": "500009", "UMask": "0x1", "Unit": "cpu_core" @@ -34,7 +34,6 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.MS_BUSY", - "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x2", "Unit": "cpu_core" @@ -44,7 +43,7 @@ "Counter": "0,1,2,3", "EventCode": "0x61", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -405,7 +404,7 @@ "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALLS", - "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.", "SampleAfterValue": "500009", "UMask": "0x4", "Unit": "cpu_core" @@ -417,7 +416,6 @@ "EdgeDetect": "1", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALL_PERIODS", - "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x4", "Unit": "cpu_core" @@ -427,7 +425,7 @@ "Counter": "0,1,2,3", "EventCode": "0x83", "EventName": "ICACHE_TAG.STALLS", - "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", "SampleAfterValue": "200003", "UMask": "0x4", "Unit": "cpu_core" @@ -438,7 +436,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -449,7 +447,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -459,7 +457,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.DSB_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -470,7 +468,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -481,7 +479,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -491,7 +489,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -502,7 +500,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES_ANY", - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", "SampleAfterValue": "2000003", "UMask": "0x20", "Unit": "cpu_core" @@ -514,7 +512,7 @@ "EdgeDetect": "1", "EventCode": "0x79", "EventName": "IDQ.MS_SWITCHES", - "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -524,7 +522,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", - "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "1000003", "UMask": "0x20", "Unit": "cpu_core" @@ -534,7 +532,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CORE", - "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0", + "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -545,7 +543,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -557,7 +555,7 @@ "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -567,7 +565,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -578,7 +576,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -590,7 +588,7 @@ "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json index 17b94f810d5a..f0cbeda4d5ca 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json @@ -5,7 +5,6 @@ "CounterMask": "2", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", - "PublicDescription": "Cycles while L3 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -16,7 +15,6 @@ "CounterMask": "6", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", - "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x6", "Unit": "cpu_core" @@ -90,7 +88,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -101,7 +99,6 @@ "CounterMask": "2", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS", - "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -112,7 +109,6 @@ "CounterMask": "3", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS", - "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" @@ -123,7 +119,7 @@ "CounterMask": "5", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS", - "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", + "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_core" @@ -134,7 +130,7 @@ "CounterMask": "9", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS", - "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", + "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", "SampleAfterValue": "1000003", "UMask": "0x9", "Unit": "cpu_core" @@ -411,7 +407,6 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -422,7 +417,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ. Available PDIST counters: 0", + "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -432,7 +427,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0", + "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json b/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json index 0088be169f9b..948c16a1f95b 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json @@ -1,56 +1,56 @@ [ { "BriefDescription": "C10 residency percent per package", - "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c10\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C10_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C1 residency percent per core", - "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricExpr": "cstate_core@c1\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C1_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C8 residency percent per package", - "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c8\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C8_Pkg_Residency", "ScaleUnit": "100%" @@ -541,7 +541,7 @@ }, { "BriefDescription": "Average CPU Utilization", - "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.REF_TSC@ / TSC", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.REF_TSC@ / msr@tsc\\,cpu=cpu_atom@", "MetricName": "tma_info_system_cpu_utilization", "Unit": "cpu_atom" }, @@ -748,7 +748,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -787,11 +787,20 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ", + "Unit": "cpu_core" + }, + { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "MetricName": "tma_bottleneck_data_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full", "Unit": "cpu_core" }, @@ -799,23 +808,14 @@ "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "MetricName": "tma_bottleneck_data_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_bottleneck_compute_bound_est", - "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ", - "Unit": "cpu_core" - }, - { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20", @@ -823,7 +823,7 @@ }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -859,7 +859,7 @@ }, { "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_data_cache_memory_bandwidth + tma_bottleneck_data_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", @@ -876,7 +876,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", @@ -1007,7 +1007,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R, 25 * tma_info_system_core_frequency) * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", @@ -1124,7 +1123,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1253,7 +1252,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", @@ -1923,7 +1922,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute", @@ -1984,7 +1983,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc\\,cpu=cpu_core@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency", "Unit": "cpu_core" @@ -1998,7 +1997,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.REF_TSC@ / TSC", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.REF_TSC@ / msr@tsc\\,cpu=cpu_core@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized", "Unit": "cpu_core" @@ -2008,7 +2007,7 @@ "MetricExpr": "64 * (UNC_HAC_ARB_TRK_REQUESTS.ALL + UNC_HAC_ARB_COH_TRK_REQUESTS.ALL) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full", "Unit": "cpu_core" }, { @@ -2095,6 +2094,13 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]", + "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time", + "MetricGroup": "SoC", + "MetricName": "tma_info_system_uncore_frequency", + "Unit": "cpu_core" + }, + { "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "Pipeline", @@ -2213,12 +2219,12 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "BriefDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (cpu_core@MEM_INST_RETIRED.ALL_LOADS@ - cpu_core@MEM_LOAD_RETIRED.FB_HIT@ - cpu_core@MEM_LOAD_RETIRED.L1_MISS@) * 20 / 100, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2234,7 +2240,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@R, 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", @@ -2255,12 +2260,11 @@ }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@R, 9 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_data_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2342,6 +2346,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@MEM_INST_RETIRED.LOCK_LOADS@R / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", @@ -2377,7 +2382,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2387,13 +2392,13 @@ "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -2404,7 +2409,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", @@ -2463,7 +2467,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", - "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2", + "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2.4", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -2502,6 +2506,7 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", @@ -2570,6 +2575,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", @@ -2580,6 +2586,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_THRESHOLD_AND_NMI", "MetricExpr": "max(cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ - cpu_core@RESOURCE_STALLS.SCOREBOARD@, 0) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", @@ -2590,6 +2597,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_THRESHOLD_AND_NMI", "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", @@ -2600,7 +2608,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", @@ -2611,7 +2618,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", @@ -2632,7 +2638,7 @@ { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@)", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2663,7 +2669,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", @@ -2698,7 +2703,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%", "Unit": "cpu_core" }, diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/other.json b/tools/perf/pmu-events/arch/x86/meteorlake/other.json index cb21bb933617..8320ffd83c51 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/other.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/other.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.HARDWARE", - "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count. Available PDIST counters: 0", + "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -14,7 +14,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.PAGE_FAULT", - "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -83,7 +82,7 @@ "CounterMask": "1", "EventCode": "0x2d", "EventName": "XQ.FULL_CYCLES", - "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json index 22b25708e799..bfdaabe9377d 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json @@ -15,7 +15,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.DIV_ACTIVE", - "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", "SampleAfterValue": "1000003", "UMask": "0x9", "Unit": "cpu_core" @@ -26,7 +26,6 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.IDIV_ACTIVE", - "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -36,7 +35,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.ANY", - "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.", "SampleAfterValue": "100003", "UMask": "0x1b", "Unit": "cpu_core" @@ -44,6 +43,7 @@ { "BriefDescription": "Counts the total number of branch instructions retired for all branch types.", "Counter": "0,1,2,3,4,5,6,7", + "Errata": "MTL012, MTL013", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", @@ -62,6 +62,7 @@ { "BriefDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches.", "Counter": "0,1,2,3,4,5,6,7", + "Errata": "MTL013", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", "SampleAfterValue": "200003", @@ -110,6 +111,7 @@ { "BriefDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return.", "Counter": "0,1,2,3,4,5,6,7", + "Errata": "MTL013", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", "SampleAfterValue": "200003", @@ -129,6 +131,7 @@ { "BriefDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired.", "Counter": "0,1,2,3,4,5,6,7", + "Errata": "MTL013", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", "SampleAfterValue": "200003", @@ -148,6 +151,7 @@ { "BriefDescription": "Counts the number of near indirect CALL branch instructions retired.", "Counter": "0,1,2,3,4,5,6,7", + "Errata": "MTL013", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT_CALL", "SampleAfterValue": "200003", @@ -167,6 +171,7 @@ "BriefDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT_CALL", "Counter": "0,1,2,3,4,5,6,7", "Deprecated": "1", + "Errata": "MTL013", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.IND_CALL", "SampleAfterValue": "200003", @@ -176,6 +181,7 @@ { "BriefDescription": "Counts the number of near CALL branch instructions retired.", "Counter": "0,1,2,3,4,5,6,7", + "Errata": "MTL012, MTL013", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", "SampleAfterValue": "200003", @@ -214,6 +220,7 @@ { "BriefDescription": "Counts the number of near taken branch instructions retired.", "Counter": "0,1,2,3,4,5,6,7", + "Errata": "MTL013", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", "SampleAfterValue": "200003", @@ -484,7 +491,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C01", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -494,7 +501,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C02", - "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", + "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", "SampleAfterValue": "2000003", "UMask": "0x20", "Unit": "cpu_core" @@ -504,7 +511,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C0_WAIT", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", "SampleAfterValue": "2000003", "UMask": "0x70", "Unit": "cpu_core" @@ -530,7 +537,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED", - "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", + "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -540,7 +547,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0", + "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.", "SampleAfterValue": "25003", "UMask": "0x2", "Unit": "cpu_core" @@ -550,7 +557,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE", - "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40", "Unit": "cpu_core" @@ -562,7 +568,6 @@ "EdgeDetect": "1", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", - "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40", "Unit": "cpu_core" @@ -572,7 +577,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED", - "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", + "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -589,7 +594,7 @@ "BriefDescription": "Reference cycles when the core is not in halt state.", "Counter": "Fixed counter 2", "EventName": "CPU_CLK_UNHALTED.REF_TSC", - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003", "UMask": "0x3", "Unit": "cpu_core" @@ -609,7 +614,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -626,7 +631,7 @@ "BriefDescription": "Core cycles when the thread is not in halt state", "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.THREAD", - "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Available PDIST counters: 0", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -644,7 +649,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", "SampleAfterValue": "2000003", "Unit": "cpu_core" }, @@ -654,7 +659,6 @@ "CounterMask": "8", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", - "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -665,7 +669,6 @@ "CounterMask": "1", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", - "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -676,7 +679,6 @@ "CounterMask": "16", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", - "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -687,7 +689,6 @@ "CounterMask": "12", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", - "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xc", "Unit": "cpu_core" @@ -698,7 +699,6 @@ "CounterMask": "5", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", - "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_core" @@ -709,7 +709,6 @@ "CounterMask": "4", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", - "PublicDescription": "Total execution stalls. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -719,7 +718,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -729,7 +728,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL", - "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0xc", "Unit": "cpu_core" @@ -739,7 +737,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -749,7 +747,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", - "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -759,7 +757,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", - "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -770,7 +768,6 @@ "CounterMask": "5", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", - "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x21", "Unit": "cpu_core" @@ -781,7 +778,7 @@ "CounterMask": "2", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", - "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", "SampleAfterValue": "1000003", "UMask": "0x40", "Unit": "cpu_core" @@ -791,7 +788,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", - "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0", + "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", "SampleAfterValue": "1000003", "UMask": "0x80", "Unit": "cpu_core" @@ -801,7 +798,7 @@ "Counter": "0,1,2,3", "EventCode": "0x75", "EventName": "INST_DECODED.DECODERS", - "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -846,7 +843,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", - "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -856,7 +852,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -875,7 +871,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -887,7 +883,7 @@ "EdgeDetect": "1", "EventCode": "0xad", "EventName": "INT_MISC.CLEARS_COUNT", - "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", "SampleAfterValue": "500009", "UMask": "0x1", "Unit": "cpu_core" @@ -897,7 +893,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", - "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", "SampleAfterValue": "500009", "UMask": "0x80", "Unit": "cpu_core" @@ -907,7 +903,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.RECOVERY_CYCLES", - "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", "SampleAfterValue": "500009", "UMask": "0x1", "Unit": "cpu_core" @@ -919,7 +915,6 @@ "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", "MSRIndex": "0x3F7", "MSRValue": "0x7", - "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40", "Unit": "cpu_core" @@ -929,7 +924,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.UOP_DROPPING", - "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -939,7 +934,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.128BIT", - "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x13", "Unit": "cpu_core" @@ -949,7 +943,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.256BIT", - "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xac", "Unit": "cpu_core" @@ -959,7 +952,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_128", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" @@ -969,7 +962,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_256", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", "SampleAfterValue": "1000003", "UMask": "0xc", "Unit": "cpu_core" @@ -979,7 +972,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.MUL_256", - "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80", "Unit": "cpu_core" @@ -989,7 +981,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.SHUFFLES", - "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40", "Unit": "cpu_core" @@ -999,7 +990,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_128", - "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1009,7 +999,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_256", - "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20", "Unit": "cpu_core" @@ -1028,7 +1017,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", - "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -1047,7 +1036,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.NO_SR", - "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", "SampleAfterValue": "100003", "UMask": "0x88", "Unit": "cpu_core" @@ -1066,7 +1055,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", "SampleAfterValue": "100003", "UMask": "0x82", "Unit": "cpu_core" @@ -1076,7 +1065,7 @@ "Counter": "0,1,2,3", "EventCode": "0x4c", "EventName": "LOAD_HIT_PREFETCH.SWPF", - "PublicDescription": "Counts all software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0", + "PublicDescription": "Counts all software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1087,7 +1076,7 @@ "CounterMask": "1", "EventCode": "0xa8", "EventName": "LSD.CYCLES_ACTIVE", - "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1098,7 +1087,7 @@ "CounterMask": "6", "EventCode": "0xa8", "EventName": "LSD.CYCLES_OK", - "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1108,7 +1097,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa8", "EventName": "LSD.UOPS", - "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1128,7 +1117,7 @@ "EdgeDetect": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.COUNT", - "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0", + "PublicDescription": "Counts the number of machine clears (nukes) of any type.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1184,7 +1173,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SMC", - "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -1194,7 +1183,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe0", "EventName": "MISC2_RETIRED.LFENCE", - "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0", + "PublicDescription": "number of LFENCE retired instructions", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -1213,7 +1202,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcc", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -1223,7 +1212,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SB", - "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -1233,7 +1222,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SCOREBOARD", - "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -1243,7 +1231,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", "EventName": "RS.EMPTY", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", "SampleAfterValue": "1000003", "UMask": "0x7", "Unit": "cpu_core" @@ -1256,7 +1244,7 @@ "EventCode": "0xa5", "EventName": "RS.EMPTY_COUNT", "Invert": "1", - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", "SampleAfterValue": "100003", "UMask": "0x7", "Unit": "cpu_core" @@ -1266,7 +1254,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", "EventName": "RS.EMPTY_RESOURCE", - "PublicDescription": "Cycles when RS was empty and a resource allocation stall is asserted Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1285,7 +1272,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", - "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0", + "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", "SampleAfterValue": "10000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1295,7 +1282,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BAD_SPEC_SLOTS", - "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0", + "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.", "SampleAfterValue": "10000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1305,7 +1292,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", - "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", "SampleAfterValue": "10000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1315,7 +1302,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", - "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1324,7 +1310,7 @@ "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event", "Counter": "Fixed counter 3", "EventName": "TOPDOWN.SLOTS", - "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3). Available PDIST counters: 0", + "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).", "SampleAfterValue": "10000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1334,7 +1320,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.SLOTS_P", - "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", "SampleAfterValue": "10000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1591,7 +1577,7 @@ "Counter": "0,1,2,3", "EventCode": "0x76", "EventName": "UOPS_DECODED.DEC0_UOPS", - "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0. Available PDIST counters: 0", + "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0.", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1601,7 +1587,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_0", - "PublicDescription": "Number of uops dispatch to execution port 0. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution port 0.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1611,7 +1597,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_1", - "PublicDescription": "Number of uops dispatch to execution port 1. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution port 1.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1621,7 +1607,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_2_3_10", - "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1631,7 +1617,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_4_9", - "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 4 and 9", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1641,7 +1627,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_5_11", - "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 5 and 11", "SampleAfterValue": "2000003", "UMask": "0x20", "Unit": "cpu_core" @@ -1651,7 +1637,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_6", - "PublicDescription": "Number of uops dispatch to execution port 6. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution port 6.", "SampleAfterValue": "2000003", "UMask": "0x40", "Unit": "cpu_core" @@ -1661,7 +1647,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_7_8", - "PublicDescription": "Number of uops dispatch to execution ports 7 and 8. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 7 and 8.", "SampleAfterValue": "2000003", "UMask": "0x80", "Unit": "cpu_core" @@ -1671,7 +1657,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE", - "PublicDescription": "Counts the number of uops executed from any thread. Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops executed from any thread.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1682,7 +1668,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1693,7 +1679,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1704,7 +1690,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1715,7 +1701,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1726,7 +1712,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_1", - "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1737,7 +1723,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_2", - "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1748,7 +1734,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_3", - "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1759,7 +1745,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_4", - "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1771,7 +1757,7 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALLS", "Invert": "1", - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1781,7 +1767,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.THREAD", - "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1791,7 +1776,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.X87", - "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of x87 uops executed.", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1810,7 +1795,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xae", "EventName": "UOPS_ISSUED.ANY", - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1821,7 +1806,6 @@ "CounterMask": "1", "EventCode": "0xae", "EventName": "UOPS_ISSUED.CYCLES", - "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1840,7 +1824,7 @@ "CounterMask": "1", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.CYCLES", - "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where at least one uop has retired.", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1850,7 +1834,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.HEAVY", - "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0", + "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1880,7 +1864,6 @@ "EventName": "UOPS_RETIRED.MS", "MSRIndex": "0x3F7", "MSRValue": "0x8", - "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1890,7 +1873,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.SLOTS", - "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0", + "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1902,7 +1885,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALLS", "Invert": "1", - "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0", + "PublicDescription": "This event counts cycles without actually retired uops.", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json index f300129e9e2d..305b96b26a4e 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json @@ -13,7 +13,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", - "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -24,7 +24,7 @@ "CounterMask": "1", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -43,7 +43,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" @@ -53,7 +53,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -73,7 +73,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -93,7 +93,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -113,7 +113,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -132,7 +132,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.STLB_HIT", - "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -143,7 +143,7 @@ "CounterMask": "1", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -162,7 +162,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" @@ -172,7 +172,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -192,7 +192,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -212,7 +212,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -232,7 +232,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -260,7 +260,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.STLB_HIT", - "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -271,7 +271,7 @@ "CounterMask": "1", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -291,7 +291,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" @@ -311,7 +311,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -331,7 +331,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -351,7 +351,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/cache.json b/tools/perf/pmu-events/arch/x86/pantherlake/cache.json index c84f3d9fdb10..7098ea1d6d16 100644 --- a/tools/perf/pmu-events/arch/x86/pantherlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/pantherlake/cache.json @@ -1,5 +1,136 @@ [ { + "BriefDescription": "Counts the number of cache lines replaced in L0 data cache.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x51", + "EventName": "L1D.L0_REPLACEMENT", + "PublicDescription": "Counts L0 data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cachelines replaced into the L1 d-cache. Successful replacements only (not blocked) and exclude WB-miss case", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x51", + "EventName": "L1D.L1_REPLACEMENT", + "PublicDescription": "Counts cachelines replaced into the L1 d-cache.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cachelines replaced into the L0 and L1 d-cache. Successful replacements only (not blocked) and exclude WB-miss case", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x51", + "EventName": "L1D.REPLACEMENT", + "PublicDescription": "Counts cachelines replaced into the L0 and L1 d-cache.", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x49", + "EventName": "L1D_MISS.FB_FULL", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x49", + "EventName": "L1D_MISS.L2_STALLS", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of demand requests that missed L1D cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x49", + "EventName": "L1D_MISS.LOAD", + "PublicDescription": "Count occurrences (rising-edge) of DCACHE_PENDING sub-event0. Impl. sends per-port binary inc-bit the occupancy increases* (at FB alloc or promotion).", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of L1D misses that are outstanding", + "Counter": "2", + "EventCode": "0x48", + "EventName": "L1D_PENDING.LOAD", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "Counter": "2", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PENDING.LOAD_CYCLES", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache lines filling L2", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.ALL", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "SampleAfterValue": "100003", + "UMask": "0x1f", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.E", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.NON_SILENT", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.SILENT", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of L2 cache accesses from front door requests for Code Read, Data Read, RFO, ITOM, and L2 Prefetches. Does not include rejects or recycles, per core event.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x24", @@ -9,6 +140,35 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "All accesses to L2 cache [This event is alias to L2_RQSTS.REFERENCES, L2_RQSTS.ANY]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_REQUEST.ALL", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES, L2_RQSTS.ANY]", + "SampleAfterValue": "200003", + "UMask": "0xff", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of L2 cache accesses from front door requests that resulted in a Hit. Does not include rejects or recycles, per core event.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.HIT", + "SampleAfterValue": "1000003", + "UMask": "0x1bf", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_RQSTS.MISS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_REQUEST.MISS", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", + "SampleAfterValue": "200003", + "UMask": "0x3f", + "Unit": "cpu_core" + }, + { "BriefDescription": "L2 code requests", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x24", @@ -29,6 +189,106 @@ "Unit": "cpu_core" }, { + "BriefDescription": "All accesses to L2 cache [This event is alias to L2_RQSTS.REFERENCES, L2_REQUEST.ALL]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ANY", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES, L2_REQUEST.ALL]", + "SampleAfterValue": "200003", + "UMask": "0xff", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "SampleAfterValue": "200003", + "UMask": "0x44", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache misses when fetching instructions", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "SampleAfterValue": "200003", + "UMask": "0x24", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand Data Read requests that hit L2 cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x41", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand Data Read miss L2 cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", + "SampleAfterValue": "200003", + "UMask": "0x21", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_REQUEST.MISS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.MISS", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", + "SampleAfterValue": "200003", + "UMask": "0x3f", + "Unit": "cpu_core" + }, + { + "BriefDescription": "All accesses to L2 cache [This event is alias to L2_REQUEST.ALL,L2_RQSTS.ANY]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.REFERENCES", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL,L2_RQSTS.ANY]", + "SampleAfterValue": "200003", + "UMask": "0xff", + "Unit": "cpu_core" + }, + { + "BriefDescription": "RFO requests that hit L2 cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_HIT", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x42", + "Unit": "cpu_core" + }, + { + "BriefDescription": "RFO requests that miss L2 cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_MISS", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x22", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when L1D is locked", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x42", + "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", + "PublicDescription": "This event counts the number of cycles when the L1D is locked.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", @@ -69,12 +329,67 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an L1 demand load miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x7f", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.L2_HIT", + "PublicDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 cache.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.L2_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x7e", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.LLC_HIT", + "SampleAfterValue": "1000003", + "UMask": "0x6", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x38", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the caches. DRAM, MMIO or other LOCAL memory type provides the data.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS_LOCALMEM", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts all retired load instructions.", "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PublicDescription": "Counts Instructions with at least one architecturally visible load retired. Available PDIST counters: 0", + "PublicDescription": "Counts Instructions with at least one architecturally visible load retired. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x81", "Unit": "cpu_core" @@ -85,16 +400,442 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0", + "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x82", "Unit": "cpu_core" }, { + "BriefDescription": "Retired software prefetch instructions.", + "Counter": "0,1,2,3", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ALL_SWPF", + "PublicDescription": "Counts all retired software prefetch instructions. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x84", + "Unit": "cpu_core" + }, + { + "BriefDescription": "All retired memory instructions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ANY", + "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x87", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions with locked access.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.LOCK_LOADS", + "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x21", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions that split across a cacheline boundary.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x41", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired store instructions that split across a cacheline boundary.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x42", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that hit the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_HIT_ANY", + "PublicDescription": "Number of retired instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0xf", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions that hit the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS", + "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x9", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired store instructions that hit the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES", + "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0xa", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired SWPF instructions that hit the STLB.", + "Counter": "0,1,2,3", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_HIT_SWPF", + "PublicDescription": "Number of retired SWPF instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0xc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that miss the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_ANY", + "PublicDescription": "Number of retired instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x17", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions that miss the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", + "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x11", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired store instructions that miss the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", + "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x12", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired SWPF instructions that miss the STLB.", + "Counter": "0,1,2,3", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_SWPF", + "PublicDescription": "Number of retired SWPF instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x14", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$)", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", + "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$) Available PDIST counters: 0,1", + "SampleAfterValue": "20011", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded. Available PDIST counters: 0,1", + "SampleAfterValue": "20011", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0,1", + "SampleAfterValue": "20011", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0,1", + "SampleAfterValue": "20011", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions which data source is memory side cache.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.MEMSIDE_CACHE", + "PublicDescription": "Retired load instructions which data source is memory side cache. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd4", + "EventName": "MEM_LOAD_MISC_RETIRED.UC", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of completed demand load requests that missed the L1, but hit the FB(fill buffer), because a preceding miss to the same cacheline initiated the line to be brought into L1, but data is not yet ready in L1.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.FB_HIT", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions with L1 cache hits as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x101", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts retired load instructions with at least one uop that hit in the Level 0 of the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_HIT_L0", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the Level 0 of the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts retired load instructions with at least one uop that hit in the Level 1 of the L1 data cache.", + "Counter": "0,1,2,3", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_HIT_L1", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the Level 1 of the L1 data cache. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions missed L1 cache as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_MISS", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0,1", + "SampleAfterValue": "200003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions with L2 cache hits as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L2_HIT", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0,1", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions missed L2 cache as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L2_MISS", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0,1", + "SampleAfterValue": "100021", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions with L3 cache hits as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L3_HIT", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0,1", + "SampleAfterValue": "100021", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions missed L3 cache as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L3_MISS", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0,1", + "SampleAfterValue": "50021", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss the L3 cache and hit in DRAM", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM", + "PublicDescription": "Counts the number of load ops retired that miss the L3 cache and hit in DRAM Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss the L3 cache and hit in memside cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.MEMSIDE_CACHE", + "PublicDescription": "Counts the number of load ops retired that miss the L3 cache and hit in memside cache. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that hit the L1 data cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", + "PublicDescription": "Counts the number of load ops retired that hit the L1 data cache. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss in the L1 data cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", + "PublicDescription": "Counts the number of load ops retired that miss in the L1 data cache. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", + "PublicDescription": "Counts the number of load ops retired that hit in the L2 cache. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", + "PublicDescription": "Counts the number of load ops retired that miss in the L2 cache. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that hit in the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", + "PublicDescription": "Counts the number of load ops retired that hit in the L3 cache. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x1c", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked for any of the following reasons: load buffer, store buffer or RSV full.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked due to a load buffer full condition.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.LD_BUF", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked due to an RSV full condition.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.RSV", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked due to a store buffer full condition.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.ST_BUF", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "MEM_STORE_RETIRED.L2_HIT", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x44", + "EventName": "MEM_STORE_RETIRED.L2_HIT", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of cache-lines required by retired stores whose Data Source is: Memory Side Cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x44", + "EventName": "MEM_STORE_RETIRED.MEMSIDE_CACHE", + "SampleAfterValue": "100021", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of load ops retired.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", + "PublicDescription": "Counts the number of load ops retired. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x81", "Unit": "cpu_atom" @@ -104,130 +845,246 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", + "PublicDescription": "Counts the number of store ops retired. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x82", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048", "MSRIndex": "0x3F6", "MSRValue": "0x800", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of load uops retired that performed one or more locks", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", + "PublicDescription": "Counts the number of load uops retired that performed one or more locks Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x21", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of memory uops retired that were splits.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.SPLIT", + "PublicDescription": "Counts the number of memory uops retired that were splits. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x43", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired split load uops.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", + "PublicDescription": "Counts the number of retired split load uops. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x41", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired split store uops.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", + "PublicDescription": "Counts the number of retired split store uops. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x42", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of memory uops retired that missed in the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS", + "PublicDescription": "Counts the number of memory uops retired that missed in the second level TLB. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x13", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load uops retired that miss in the second Level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "PublicDescription": "Counts the number of load uops retired that miss in the second Level TLB. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x11", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of store uops retired that miss in the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", + "PublicDescription": "Counts the number of store uops retired that miss in the second level TLB. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x12", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", + "PublicDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x6", "Unit": "cpu_atom" }, { + "BriefDescription": "Retired memory uops for any access", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe5", + "EventName": "MEM_UOP_RETIRED.ANY", + "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", + "SampleAfterValue": "1000003", + "UMask": "0xf", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts writebacks of modified cachelines that were supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.COREWB_M.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x7E001E00008", + "PublicDescription": "Counts writebacks of modified cachelines that were supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts writebacks of non-modified cachelines that were supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.COREWB_NONM.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x7E001E01000", + "PublicDescription": "Counts writebacks of non-modified cachelines that were supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand data reads that have any type of response.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", @@ -241,7 +1098,7 @@ }, { "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -252,6 +1109,30 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x40001E00001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches which forwarded the unmodified data to the requesting core.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x20001E00001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", @@ -265,7 +1146,7 @@ }, { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -274,5 +1155,221 @@ "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x40001E00002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts all data read, code read, RFO and ITOM requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x7E001E04477", + "PublicDescription": "Counts all data read, code read, RFO and ITOM requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Any memory transaction that reached the SQ.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", + "SampleAfterValue": "100003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand and prefetch data reads", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DATA_RD", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cacheable and Non-Cacheable code read requests", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand Data Read requests sent to uncore", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 1 outstanding demand data read request is pending.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Store Read transactions pending for off-core. Highly correlated.", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", + "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2c", + "EventName": "SQ_MISC.BUS_LOCK", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.ANY", + "SampleAfterValue": "100003", + "UMask": "0xf", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of PREFETCHNTA instructions executed.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.NTA", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of PREFETCHW instructions executed.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", + "PublicDescription": "Counts the number of PREFETCHW instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of PREFETCHT0 instructions executed.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.T0", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.T1_T2", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" } ] diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/counter.json b/tools/perf/pmu-events/arch/x86/pantherlake/counter.json index 69f158a97707..432b6946ccbc 100644 --- a/tools/perf/pmu-events/arch/x86/pantherlake/counter.json +++ b/tools/perf/pmu-events/arch/x86/pantherlake/counter.json @@ -1,12 +1,17 @@ [ { "Unit": "cpu_atom", - "CountersNumFixed": "3", - "CountersNumGeneric": "39" + "CountersNumFixed": "7", + "CountersNumGeneric": "8" }, { "Unit": "cpu_core", "CountersNumFixed": "4", "CountersNumGeneric": "10" + }, + { + "Unit": "iMC", + "CountersNumFixed": "0", + "CountersNumGeneric": "5" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/floating-point.json b/tools/perf/pmu-events/arch/x86/pantherlake/floating-point.json new file mode 100644 index 000000000000..57c26866bc79 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/pantherlake/floating-point.json @@ -0,0 +1,286 @@ +[ + { + "BriefDescription": "Cycles when floating-point divide unit is busy executing divide or square root operations.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.FPDIV_ACTIVE", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for floating-point operations only.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts all microcode FP assists.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc1", + "EventName": "ASSISTS.FP", + "PublicDescription": "Counts all microcode Floating Point assists.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "ASSISTS.SSE_AVX_MIX", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc1", + "EventName": "ASSISTS.SSE_AVX_MIX", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of FP-arith-uops dispatched on 1st VEC port (port 0). FP-arith-uops are of type ADD* / SUB* / MUL / FMA* / DPP.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.V0", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of FP-arith-uops dispatched on 2nd VEC port (port 1)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.V1", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of FP-arith-uops dispatched on 3rd VEC port (port 5)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.V2", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of FP-arith-uops dispatched on 4th VEC port", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.V3", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.128B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.256B_PACKED_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x18", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.SCALAR", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.SCALAR_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.SCALAR_SINGLE", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.VECTOR", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x3c", + "Unit": "cpu_core" + }, + { + "BriefDescription": "FP_ARITH_OPS_RETIRED.VECTOR_128B", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.VECTOR_128B", + "SampleAfterValue": "100003", + "UMask": "0xc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "FP_ARITH_OPS_RETIRED.VECTOR_256B", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.VECTOR_256B", + "SampleAfterValue": "100003", + "UMask": "0x30", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of all types of floating point operations per uop with all default weighting", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc8", + "EventName": "FP_FLOPS_RETIRED.ALL", + "PublicDescription": "Counts the number of all types of floating point operations per uop with all default weighting Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of floating point operations that produce 32 bit single precision results", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc8", + "EventName": "FP_FLOPS_RETIRED.FP32", + "PublicDescription": "Counts the number of floating point operations that produce 32 bit single precision results Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of floating point operations that produce 64 bit double precision results", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc8", + "EventName": "FP_FLOPS_RETIRED.FP64", + "PublicDescription": "Counts the number of floating point operations that produce 64 bit double precision results Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 128 bit double precision floating point. This may be SSE or AVX.128 operations.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.128B_DP", + "PublicDescription": "Counts the number of retired instructions whose sources are a packed 128 bit double precision floating point. This may be SSE or AVX.128 operations. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 128 bit single precision floating point. This may be SSE or AVX.128 operations.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.128B_SP", + "PublicDescription": "Counts the number of retired instructions whose sources are a packed 128 bit single precision floating point. This may be SSE or AVX.128 operations. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 256 bit double precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.256B_DP", + "PublicDescription": "Counts the number of retired instructions whose sources are a packed 256 bit double precision floating point. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 256 bit single precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.256B_SP", + "PublicDescription": "Counts the number of retired instructions whose sources are a packed 256 bit single precision floating point. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a scalar 32bit single precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.32B_SP", + "PublicDescription": "Counts the number of retired instructions whose sources are a scalar 32bit single precision floating point. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a scalar 64 bit double precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.64B_DP", + "PublicDescription": "Counts the number of retired instructions whose sources are a scalar 64 bit double precision floating point. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the total number of floating point retired instructions.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.ALL", + "PublicDescription": "Counts the total number of floating point retired instructions. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x3f", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of floating point operations retired that required microcode assist.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.FP_ASSIST", + "PublicDescription": "Counts the number of floating point operations retired that required microcode assist, which is not a reflection of the number of FP operations, instructions or uops.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + } +] diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/frontend.json b/tools/perf/pmu-events/arch/x86/pantherlake/frontend.json index aedf631e3c0f..d36faa683d3f 100644 --- a/tools/perf/pmu-events/arch/x86/pantherlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/pantherlake/frontend.json @@ -1,5 +1,370 @@ [ { + "BriefDescription": "Counts the total number of BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe6", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Counts the total number of BACLEARS, which occur when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Clears due to Unknown Branches.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x60", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of BACLEARS due to a conditional jump.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe6", + "EventName": "BACLEARS.COND", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of BACLEARS due to an indirect branch.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe6", + "EventName": "BACLEARS.INDIRECT", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of BACLEARS due to a return branch.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe6", + "EventName": "BACLEARS.RETURN", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of BACLEARS due to a direct, unconditional jump.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe6", + "EventName": "BACLEARS.UNCOND", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x87", + "EventName": "DECODE.LCP", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", + "SampleAfterValue": "500009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles the Microcode Sequencer is busy.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x87", + "EventName": "DECODE.MS_BUSY", + "SampleAfterValue": "500009", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "DSB-to-MITE switch true penalty cycles.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x61", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired ANT branches", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ANY_ANT", + "MSRIndex": "0x3F7", + "MSRValue": "0x9", + "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired Instructions who experienced DSB miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x1", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired Instructions who experienced a critical DSB miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x11", + "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "PublicDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Retired Instructions who experienced iTLB true miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x14", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.L1I_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x12", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.L2_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x13", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "MSRIndex": "0x3F7", + "MSRValue": "0x608006", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "MSRIndex": "0x3F7", + "MSRValue": "0x601006", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", + "MSRIndex": "0x3F7", + "MSRValue": "0x600206", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", + "MSRIndex": "0x3F7", + "MSRValue": "0x610006", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", + "MSRIndex": "0x3F7", + "MSRValue": "0x100206", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", + "MSRIndex": "0x3F7", + "MSRValue": "0x602006", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", + "MSRIndex": "0x3F7", + "MSRValue": "0x600406", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", + "MSRIndex": "0x3F7", + "MSRValue": "0x620006", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "MSRIndex": "0x3F7", + "MSRValue": "0x604006", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", + "MSRIndex": "0x3F7", + "MSRValue": "0x600806", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted Retired ANT branches", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.MISP_ANT", + "MSRIndex": "0x3F7", + "MSRValue": "0x9", + "PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts flows delivered by the Microcode Sequencer", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.MS_FLOWS", + "MSRIndex": "0x3F7", + "MSRValue": "0x8", + "PublicDescription": "Counts flows delivered by the Microcode Sequencer Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.STLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x15", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that caused clears due to being Unknown Branches.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", + "MSRIndex": "0x3F7", + "MSRValue": "0x17", + "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to Instruction L1 cache miss, that hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "FRONTEND_RETIRED_SOURCE.ICACHE_L2_HIT", + "PublicDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to Instruction L1 cache miss, that hit in the L2 cache. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss that hit in the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "FRONTEND_RETIRED_SOURCE.ITLB_STLB_HIT", + "PublicDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss that hit in the second level TLB. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss that also missed the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "FRONTEND_RETIRED_SOURCE.ITLB_STLB_MISS", + "PublicDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss that also missed the second level TLB. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x80", @@ -9,6 +374,15 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are present.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE.HIT", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are not present. -", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x80", @@ -18,6 +392,134 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x80", + "EventName": "ICACHE_DATA.STALLS", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.", + "SampleAfterValue": "500009", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "ICACHE_DATA.STALL_PERIODS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x80", + "EventName": "ICACHE_DATA.STALL_PERIODS", + "SampleAfterValue": "500009", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x83", + "EventName": "ICACHE_TAG.STALLS", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES_ANY", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles DSB is delivering optimal number of Uops", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "8", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES_OK", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x79", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles MITE is delivering any Uop", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES_ANY", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles MITE is delivering optimal number of Uops", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "8", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES_OK", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x79", + "EventName": "IDQ.MITE_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_CYCLES_ANY", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of switches from DSB or MITE to the MS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_SWITCHES", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "SampleAfterValue": "100003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x79", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { "BriefDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x9c", @@ -26,5 +528,38 @@ "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", + "Invert": "1", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when no uops are delivered by the IDQ for 2 or more cycles when backend of the machine is not stalled - normally indicating a Fetch Latency issue", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.FETCH_LATENCY", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls for 2 or more cycles - normally indicating a Fetch Latency issue.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "8", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.STARVATION_CYCLES", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" } ] diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/memory.json b/tools/perf/pmu-events/arch/x86/pantherlake/memory.json index 47daee8cc00f..397a15dbb964 100644 --- a/tools/perf/pmu-events/arch/x86/pantherlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/pantherlake/memory.json @@ -1,5 +1,33 @@ [ { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a core bound stall including a store address match, a DTLB miss or a page walk that detains the load from retiring.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.L1_BOUND_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0xf4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears due to memory ordering caused by a snoop from an external agent. Does not count internally generated machine clears such as those due to memory disambiguation.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of machine clears due to memory ordering conflicts.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.", "Counter": "2,3,4,5,6,7,8,9", "Data_LA": "1", @@ -7,7 +35,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1", "SampleAfterValue": "53", "UMask": "0x1", "Unit": "cpu_core" @@ -20,7 +48,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1", "SampleAfterValue": "1009", "UMask": "0x1", "Unit": "cpu_core" @@ -33,7 +61,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1", "SampleAfterValue": "20011", "UMask": "0x1", "Unit": "cpu_core" @@ -46,7 +74,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048", "MSRIndex": "0x3F6", "MSRValue": "0x800", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1", "SampleAfterValue": "23", "UMask": "0x1", "Unit": "cpu_core" @@ -59,7 +87,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1", "SampleAfterValue": "503", "UMask": "0x1", "Unit": "cpu_core" @@ -72,7 +100,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -85,7 +113,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -98,7 +126,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1", "SampleAfterValue": "101", "UMask": "0x1", "Unit": "cpu_core" @@ -111,7 +139,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1", "SampleAfterValue": "2003", "UMask": "0x1", "Unit": "cpu_core" @@ -124,7 +152,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1", "SampleAfterValue": "50021", "UMask": "0x1", "Unit": "cpu_core" @@ -135,12 +163,32 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" }, { + "BriefDescription": "Counts misaligned loads that are 4K page splits.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x13", + "EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT", + "PublicDescription": "Counts misaligned loads that are 4K page splits. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts misaligned stores that are 4K page splits.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x13", + "EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT", + "PublicDescription": "Counts misaligned stores that are 4K page splits. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand data reads that were supplied by DRAM.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", @@ -154,7 +202,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by DRAM.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -178,7 +226,7 @@ }, { "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", @@ -202,7 +250,7 @@ }, { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", - "Counter": "0,1,2,3", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", @@ -211,5 +259,35 @@ "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand data read requests that miss the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where data return is pending for a Demand Data Read request who miss L3 cache.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" } ] diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/other.json b/tools/perf/pmu-events/arch/x86/pantherlake/other.json new file mode 100644 index 000000000000..d49651d4f112 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/pantherlake/other.json @@ -0,0 +1,44 @@ +[ + { + "BriefDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc1", + "EventName": "ASSISTS.HARDWARE", + "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "ASSISTS.PAGE_FAULT", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc1", + "EventName": "ASSISTS.PAGE_FAULT", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts streaming stores that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles the uncore cannot take further requests", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x2d", + "EventName": "XQ.FULL", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + } +] diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/pipeline.json b/tools/perf/pmu-events/arch/x86/pantherlake/pipeline.json index 2caf2f85327f..2d805ac98c5b 100644 --- a/tools/perf/pmu-events/arch/x86/pantherlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/pantherlake/pipeline.json @@ -1,10 +1,51 @@ [ { + "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.DIV_ACTIVE", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "SampleAfterValue": "1000003", + "UMask": "0x9", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when integer divide unit is busy executing divide or square root operations.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.IDIV_ACTIVE", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer operations only.", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc1", + "EventName": "ASSISTS.ANY", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.", + "SampleAfterValue": "100003", + "UMask": "0x1f", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa2", + "EventName": "BE_STALLS.SCOREBOARD", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the total number of branch instructions retired for all branch types.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", + "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "Unit": "cpu_atom" }, @@ -13,8 +54,242 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0", + "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND", + "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of not taken conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_NTAKEN", + "PublicDescription": "Counts the number of not taken conditional branch instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Not taken branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_NTAKEN", + "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Taken conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_TAKEN", + "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Taken backward conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_TAKEN_BWD", + "PublicDescription": "Counts taken backward conditional branch instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Taken forward conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_TAKEN_FWD", + "PublicDescription": "Counts taken forward conditional branch instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Far branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_INST_RETIRED.NEAR_INDIRECT]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT", + "PublicDescription": "This event is deprecated. [This event is alias to BR_INST_RETIRED.NEAR_INDIRECT] Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x50", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of near CALL branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PublicDescription": "Counts the number of near CALL branch instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x30", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Direct and indirect near call instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x30", + "Unit": "cpu_core" + }, + { + "BriefDescription": "near relative call instructions retired. [This event is alias to BR_INST_RETIRED.NEAR_REL_CALL]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_DIRECT_CALL", + "PublicDescription": "Counts near relative call instructions retired. [This event is alias to BR_INST_RETIRED.NEAR_REL_CALL] Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "near relative jump instructions retired. [This event is alias to BR_INST_RETIRED.NEAR_REL_JMP]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_DIRECT_JMP", + "PublicDescription": "Counts near relative jump instructions retired. [This event is alias to BR_INST_RETIRED.NEAR_REL_JMP] Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Indirect near branch instructions retired (excluding returns) [This event is alias to BR_INST_RETIRED.INDIRECT]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_INDIRECT", + "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. [This event is alias to BR_INST_RETIRED.INDIRECT] Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x50", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Indirect near call instructions retired. [This event is alias to BR_INST_RETIRED.NEAR_IND_CALL]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_INDIRECT_CALL", + "PublicDescription": "Counts indirect near call instructions retired. [This event is alias to BR_INST_RETIRED.NEAR_IND_CALL] Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Indirect near jump instructions retired. [This event is alias to BR_INST_RETIRED.NEAR_IND_JMP]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_INDIRECT_JMP", + "PublicDescription": "Counts indirect near jump instructions retired. [This event is alias to BR_INST_RETIRED.NEAR_IND_JMP] Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_INST_RETIRED.NEAR_INDIRECT_CALL]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_IND_CALL", + "PublicDescription": "This event is deprecated. [This event is alias to BR_INST_RETIRED.NEAR_INDIRECT_CALL] Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_INST_RETIRED.NEAR_INDIRECT_JMP]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_IND_JMP", + "PublicDescription": "This event is deprecated. [This event is alias to BR_INST_RETIRED.NEAR_INDIRECT_JMP] Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Indirect and Direct Relative near jump instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_JMP", + "PublicDescription": "Counts near jump instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0xc0", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_INST_RETIRED.NEAR_DIRECT_CALL]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_REL_CALL", + "PublicDescription": "This event is deprecated. [This event is alias to BR_INST_RETIRED.NEAR_DIRECT_CALL] Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_INST_RETIRED.NEAR_DIRECT_JMP]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_REL_JMP", + "PublicDescription": "This event is deprecated. [This event is alias to BR_INST_RETIRED.NEAR_DIRECT_JMP] Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Return instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of near taken branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PublicDescription": "Counts the number of near taken branch instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0xfb", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Taken branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", + "UMask": "0xfb", "Unit": "cpu_core" }, { @@ -22,7 +297,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", + "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "Unit": "cpu_atom" }, @@ -31,15 +306,438 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.ALL_BRANCHES_TPEBS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST", + "PublicDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.ALL_BRANCHES_TPEBS] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "Unit": "cpu_core" + }, + { + "BriefDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.ALL_BRANCHES_COST]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_TPEBS", + "PublicDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.ALL_BRANCHES_COST] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND", + "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.COND_TPEBS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_COST", + "PublicDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.COND_TPEBS] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x8007", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted not taken conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_NTAKEN", + "PublicDescription": "Counts the number of mispredicted not taken conditional branch instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Mispredicted non-taken conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_NTAKEN", + "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.COND_NTAKEN_TPEBS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST", + "PublicDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.COND_NTAKEN_TPEBS] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x8004", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.COND_NTAKEN_COST]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_NTAKEN_TPEBS", + "PublicDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.COND_NTAKEN_COST] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x8004", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted taken conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN", + "PublicDescription": "Counts the number of mispredicted taken conditional branch instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken backward.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD", + "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "400009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.COND_TAKEN_BWD_TPEBS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD_COST", + "PublicDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.COND_TAKEN_BWD_TPEBS] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x8001", + "Unit": "cpu_core" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken backward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.COND_TAKEN_BWD_COST]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD_TPEBS", + "PublicDescription": "number of branch instructions retired that were mispredicted and taken backward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.COND_TAKEN_BWD_COST] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x8001", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.COND_TAKEN_TPEBS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST", + "PublicDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.COND_TAKEN_TPEBS] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x8003", + "Unit": "cpu_core" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken forward.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD", + "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.COND_TAKEN_FWD_TPEBS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD_COST", + "PublicDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.COND_TAKEN_FWD_TPEBS] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x8002", + "Unit": "cpu_core" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken forward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.COND_TAKEN_FWD_COST]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD_TPEBS", + "PublicDescription": "number of branch instructions retired that were mispredicted and taken forward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.COND_TAKEN_FWD_COST] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x8002", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.COND_TAKEN_COST]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_TPEBS", + "PublicDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.COND_TAKEN_COST] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x8003", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.COND_COST]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TPEBS", + "PublicDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.COND_COST] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x8007", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_INDIRECT]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT", + "PublicDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_INDIRECT] Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x50", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_INDIRECT_CALL]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", + "PublicDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_INDIRECT_CALL] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_INDIRECT_CALL_TPEBS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST", + "PublicDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_INDIRECT_CALL_TPEBS] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x8010", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_INDIRECT_TPEBS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_COST", + "PublicDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_INDIRECT_TPEBS] Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x8050", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_INDIRECT_JMP]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_JMP", + "PublicDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_INDIRECT_JMP] Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_INDIRECT_JMP_TPEBS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_JMP_COST", + "PublicDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_INDIRECT_JMP_TPEBS] Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x8040", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Miss-predicted near indirect branch instructions retired (excluding returns) [This event is alias to BR_MISP_RETIRED.INDIRECT]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_INDIRECT", + "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. [This event is alias to BR_MISP_RETIRED.INDIRECT] Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x50", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted indirect CALL retired. [This event is alias to BR_MISP_RETIRED.INDIRECT_CALL]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_INDIRECT_CALL", + "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. [This event is alias to BR_MISP_RETIRED.INDIRECT_CALL] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.INDIRECT_CALL_COST]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_INDIRECT_CALL_TPEBS", + "PublicDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.INDIRECT_CALL_COST] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x8010", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Miss-predicted near indirect jump instructions retired. [This event is alias to BR_MISP_RETIRED.INDIRECT_JMP]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_INDIRECT_JMP", + "PublicDescription": "Miss-predicted near indirect jump instructions retired. [This event is alias to BR_MISP_RETIRED.INDIRECT_JMP] Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Miss-predicted near indirect jump instructions retired. Precise cost. [This event is alias to BR_MISP_RETIRED.INDIRECT_JMP_COST]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_INDIRECT_JMP_TPEBS", + "PublicDescription": "Miss-predicted near indirect jump instructions retired. Precise cost. [This event is alias to BR_MISP_RETIRED.INDIRECT_JMP_COST] Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x8040", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.INDIRECT_COST]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_INDIRECT_TPEBS", + "PublicDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.INDIRECT_COST] Available PDIST counters: 0,1", + "SampleAfterValue": "100003", + "UMask": "0x8050", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS [This event is alias to BR_MISP_RETIRED.RET]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_RETURN", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. [This event is alias to BR_MISP_RETIRED.RET] Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.RET_COST]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_RETURN_TPEBS", + "PublicDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.RET_COST] Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x8008", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0xfb", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_TAKEN_TPEBS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST", + "PublicDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_TAKEN_TPEBS] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x80fb", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.NEAR_TAKEN_COST]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_TPEBS", + "PublicDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. [This event is alias to BR_MISP_RETIRED.NEAR_TAKEN_COST] Available PDIST counters: 0,1", + "SampleAfterValue": "400009", + "UMask": "0x80fb", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_RETURN]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.RET", + "PublicDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_RETURN] Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_RETURN_TPEBS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.RET_COST", + "PublicDescription": "This event is deprecated. [This event is alias to BR_MISP_RETIRED.NEAR_RETURN_TPEBS] Available PDIST counters: 0,1", + "SampleAfterValue": "100007", + "UMask": "0x8008", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C01", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C02", + "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.1 or C0.2 or running a PAUSE in C0 ACPI state.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C0_WAIT", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", + "SampleAfterValue": "2000003", + "UMask": "0x70", "Unit": "cpu_core" }, { "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles.", "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.CORE", - "SampleAfterValue": "1000003", + "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_atom" }, @@ -57,7 +755,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.CORE_P", - "SampleAfterValue": "1000003", + "SampleAfterValue": "2000003", "Unit": "cpu_atom" }, { @@ -70,10 +768,30 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Core clocks when a PAUSE is pending.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.PAUSE", + "SampleAfterValue": "2000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Pause instructions", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", + "SampleAfterValue": "2000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles.", "Counter": "Fixed counter 2", "EventName": "CPU_CLK_UNHALTED.REF_TSC", - "SampleAfterValue": "1000003", + "SampleAfterValue": "2000003", "UMask": "0x3", "Unit": "cpu_atom" }, @@ -92,7 +810,7 @@ "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is not affected by core frequency changes and increments at a fixed frequency that is also used for the Time Stamp Counter (TSC). This event uses a programmable general purpose performance counter.", - "SampleAfterValue": "1000003", + "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_atom" }, @@ -110,7 +828,7 @@ "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles.", "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.THREAD", - "SampleAfterValue": "1000003", + "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_atom" }, @@ -128,7 +846,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "SampleAfterValue": "1000003", + "SampleAfterValue": "2000003", "Unit": "cpu_atom" }, { @@ -141,11 +859,130 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "16", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total execution stalls.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "4", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Count number of times a load is depending on another load that had just write back its data or in previous or 2 cycles back. This event supports in-direct dependency through a single uop.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x02", + "EventName": "DEPENDENT_LOADS.ANY", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL", + "SampleAfterValue": "2000003", + "UMask": "0xc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "5", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", + "SampleAfterValue": "2000003", + "UMask": "0x21", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where the Store Buffer was full and no loads caused an execution stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "2", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles no uop executed while RS was not empty, the SB was not full and there was no outstanding load.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instruction decoders utilized in a cycle", + "Counter": "2", + "EventCode": "0x75", + "EventName": "INST_DECODED.DECODERS", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Fixed Counter: Counts the number of instructions retired.", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", "PublicDescription": "Fixed Counter: Counts the number of instructions retired. Available PDIST counters: 32", - "SampleAfterValue": "1000003", + "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_atom" }, @@ -163,7 +1000,8 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "SampleAfterValue": "1000003", + "PublicDescription": "Counts the number of instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "2000003", "Unit": "cpu_atom" }, { @@ -171,8 +1009,273 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 0", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 0,1", + "SampleAfterValue": "2000003", + "Unit": "cpu_core" + }, + { + "BriefDescription": "retired macro-fused uops when there is a branch in the macro-fused pair (the two instructions that got macro-fused count once in this pmon)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.BR_FUSED", + "PublicDescription": "retired macro-fused uops when there is a branch in the macro-fused pair (the two instructions that got macro-fused count once in this pmon) Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "INST_RETIRED.MACRO_FUSED", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.MACRO_FUSED", + "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0,1", + "SampleAfterValue": "2000003", + "UMask": "0x30", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired NOP instructions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.NOP", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0,1", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Precise instruction retired with PEBS precise-distribution", + "Counter": "Fixed counter 0", + "EventName": "INST_RETIRED.PREC_DIST", + "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Iterations of Repeat string retired instructions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.REP_ITERATION", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0,1", "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Bubble cycles of BPClear.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xad", + "EventName": "INT_MISC.BPCLEAR_CYCLES", + "MSRIndex": "0x3F7", + "MSRValue": "0xB", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Clears speculative count", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xad", + "EventName": "INT_MISC.CLEARS_COUNT", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "SampleAfterValue": "500009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xad", + "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "SampleAfterValue": "500009", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xad", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "SampleAfterValue": "500009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Bubble cycles of BAClear (Unknown Branch).", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xad", + "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", + "MSRIndex": "0x3F7", + "MSRValue": "0x7", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "TMA slots where uops got dropped", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xad", + "EventName": "INT_MISC.UOP_DROPPING", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of uops executed on integer port 0,1, 2, 3.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.PRIMARY", + "SampleAfterValue": "1000003", + "UMask": "0x78", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of vector integer instructions retired of 128-bit vector-width.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.128BIT", + "SampleAfterValue": "1000003", + "UMask": "0x13", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of vector integer instructions retired of 256-bit vector-width.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.256BIT", + "SampleAfterValue": "1000003", + "UMask": "0xac", + "Unit": "cpu_core" + }, + { + "BriefDescription": "integer ADD, SUB, SAD 128-bit vector instructions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.ADD_128", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "integer ADD, SUB, SAD 256-bit vector instructions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.ADD_256", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", + "SampleAfterValue": "1000003", + "UMask": "0xc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "INT_VEC_RETIRED.MUL_256", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.MUL_256", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "INT_VEC_RETIRED.SHUFFLES", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.SHUFFLES", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "INT_VEC_RETIRED.VNNI_128", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.VNNI_128", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "INT_VEC_RETIRED.VNNI_256", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.VNNI_256", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.ADDRESS_ALIAS", + "PublicDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "False dependencies in MOB due to partial compare on address.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.ADDRESS_ALIAS", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of retired loads that are blocked for any of the following reasons: DTLB miss, address alias, store forward or data unknown (includes memory disambiguation blocks and ESP consuming load blocks).", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.ALL", + "PublicDescription": "Counts the number of retired loads that are blocked for any of the following reasons: DTLB miss, address alias, store forward or data unknown (includes memory disambiguation blocks and ESP consuming load blocks). Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Bank conflicts in DCU due to limited lookup ports.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.BANK_CONFLICT", + "PublicDescription": "Counts the number of times a load got blocked due to bank conflicts in DCU", + "SampleAfterValue": "100003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.DATA_UNKNOWN", + "PublicDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.NO_SR", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "SampleAfterValue": "100003", + "UMask": "0x88", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of times a load got early blocked due to preceding store operation with unknown address or unknown data. Excluding in-line (immediate) wakeups", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_EARLY", + "SampleAfterValue": "100003", + "UMask": "0xa1", "Unit": "cpu_core" }, { @@ -180,6 +1283,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "Counts the number of retired loads that are blocked because its address partially overlapped with an older store. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_atom" @@ -195,10 +1299,129 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xa8", + "EventName": "LSD.CYCLES_ACTIVE", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles optimal number of Uops delivered by the LSD, but did not come from the decoder.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "8", + "EventCode": "0xa8", + "EventName": "LSD.CYCLES_OK", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Uops delivered by the LSD.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa8", + "EventName": "LSD.UOPS", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of machine clears (nukes) of any type.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.COUNT", + "PublicDescription": "Counts the number of machine clears (nukes) of any type.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of machine clears due to memory ordering in which an internal load passes an older store within the same CPU.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.DISAMBIGUATION", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears due to a page fault. Counts both I-Side and D-Side (Loads/Stores) page faults. A page fault occurs when either the page is not present, or an access violation occurs.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.PAGE_FAULT", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Self-modifying code (SMC) detected.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.SMC", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L1 cache (that is: no execution & load in flight & no load missed L1 cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.L1", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L2 cache (that is: no execution & load in flight & load missed L1 & no load missed L2 cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.L2", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L3 cache (that is: no execution & load in flight & load missed L1 & load missed L2 cache & no load missed L3 Cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.L3", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for Memory (that is: no execution & load in flight & a load missed L3 cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.MEM", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "LFENCE instructions retired", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe0", + "EventName": "MISC2_RETIRED.LFENCE", + "PublicDescription": "number of LFENCE retired instructions", + "SampleAfterValue": "400009", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe4", "EventName": "MISC_RETIRED.LBR_INSERTS", + "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_atom" @@ -208,12 +1431,83 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xe4", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PublicDescription": "LBR record is inserted Available PDIST counters: 0", + "PublicDescription": "LBR record is inserted Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of LFENCE instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe0", + "EventName": "MISC_RETIRED1.LFENCE", + "PublicDescription": "Counts the number of LFENCE instructions retired. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of accesses to KeyLocker cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe1", + "EventName": "MISC_RETIRED2.KEYLOCKER_ACCESS", + "PublicDescription": "Counts the number of accesses to KeyLocker cache. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of misses to KeyLocker cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe1", + "EventName": "MISC_RETIRED2.KEYLOCKER_MISS", + "PublicDescription": "Counts the number of misses to KeyLocker cache. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x11", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa5", + "EventName": "RS.EMPTY", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_COUNT", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", + "SampleAfterValue": "100003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_RESOURCE", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state).", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.C01_MS_SCB", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xa4", @@ -224,6 +1518,35 @@ "Unit": "cpu_core" }, { + "BriefDescription": "TMA slots wasted due to incorrect speculations.", + "Counter": "0", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BAD_SPEC_SLOTS", + "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.", + "SampleAfterValue": "10000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "TMA slots wasted due to incorrect speculation by branch mispredictions", + "Counter": "0", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", + "SampleAfterValue": "10000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "TOPDOWN.MEMORY_BOUND_SLOTS", + "Counter": "3", + "EventCode": "0xa4", + "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", + "SampleAfterValue": "10000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event", "Counter": "Fixed counter 3", "EventName": "TOPDOWN.SLOTS", @@ -244,7 +1567,7 @@ }, { "BriefDescription": "Fixed Counter: Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.", - "Counter": "36", + "Counter": "Fixed counter 4", "EventName": "TOPDOWN_BAD_SPECULATION.ALL", "SampleAfterValue": "1000003", "UMask": "0x5", @@ -279,7 +1602,7 @@ }, { "BriefDescription": "Fixed Counter: Counts the number of retirement slots not consumed due to front end stalls.", - "Counter": "37", + "Counter": "Fixed counter 5", "EventName": "TOPDOWN_FE_BOUND.ALL", "SampleAfterValue": "1000003", "UMask": "0x6", @@ -296,7 +1619,7 @@ }, { "BriefDescription": "Fixed Counter: Counts the number of consumed retirement slots.", - "Counter": "38", + "Counter": "Fixed counter 6", "EventName": "TOPDOWN_RETIRING.ALL", "SampleAfterValue": "1000003", "UMask": "0x7", @@ -313,6 +1636,237 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Number of non dec-by-all uops decoded by decoder", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x76", + "EventName": "UOPS_DECODED.DEC0_UOPS", + "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops executed on INT EU ALU ports.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.ALU", + "PublicDescription": "Number of ALU integer uops dispatch to execution.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops executed on any INT EU ports", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.INT_EU_ALL", + "PublicDescription": "Number of integer uops dispatched to execution.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Uops dispatched/executed by any of the 3 JEUs (all ups that hold the JEU including macro; micro jumps; fetch-from-eip)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.JMP", + "PublicDescription": "Number of jump uops dispatch to execution", + "SampleAfterValue": "2000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops executed on Load ports", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.LOAD", + "PublicDescription": "Number of Load uops dispatched to execution.", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of (shift) 1-cycle Uops dispatched/executed by any of the Shift Eus", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.SHIFT", + "PublicDescription": "Number of SHIFT integer uops dispatch to execution", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Uops dispatched/executed by Slow EU (e.g. 3+ cycles LEA, >1 cycles shift, iDIVs, CR; *H operation)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.SLOW", + "PublicDescription": "Number of Slow integer uops dispatch to execution.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Uops dispatched on STA ports", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.STA", + "PublicDescription": "Number of STA (Store Address) uops dispatch to execution", + "SampleAfterValue": "2000003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops executed on STD ports", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.STD", + "PublicDescription": "Number of STD (Store Data) uops dispatch to execution", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "Counter": "3", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", + "Counter": "3", + "CounterMask": "2", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "Counter": "3", + "CounterMask": "3", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "Counter": "3", + "CounterMask": "4", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "Counter": "3", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.STALLS", + "Invert": "1", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", + "Counter": "3", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.THREAD", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of x87 uops dispatched.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.X87", + "PublicDescription": "Counts the number of x87 uops executed.", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops that RAT issues to RS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xae", + "EventName": "UOPS_ISSUED.ANY", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "UOPS_ISSUED.CYCLES", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xae", + "EventName": "UOPS_ISSUED.CYCLES", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles with retired uop(s).", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.CYCLES", + "PublicDescription": "Counts cycles where at least one uop has retired.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired uops except the last uop of each instruction.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.HEAVY", + "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "UOPS_RETIRED.MS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.MS", + "MSRIndex": "0x3F7", + "MSRValue": "0x8", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of non-speculative switches to the Microcode Sequencer (MS)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.MS_SWITCHES", + "MSRIndex": "0x3F7", + "MSRValue": "0x8", + "PublicDescription": "Switches to the Microcode Sequencer", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { "BriefDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc2", @@ -321,5 +1875,17 @@ "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles without actually retired uops.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.STALLS", + "Invert": "1", + "PublicDescription": "This event counts cycles without actually retired uops.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" } ] diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/uncore-memory.json b/tools/perf/pmu-events/arch/x86/pantherlake/uncore-memory.json new file mode 100644 index 000000000000..a881b99be5f3 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/pantherlake/uncore-memory.json @@ -0,0 +1,26 @@ +[ + { + "BriefDescription": "Read CAS command sent to DRAM", + "Counter": "0,1,2,3,4", + "EventCode": "0x22", + "EventName": "UNC_M_CAS_COUNT_RD", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Write CAS command sent to DRAM", + "Counter": "0,1,2,3,4", + "EventCode": "0x23", + "EventName": "UNC_M_CAS_COUNT_WR", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Total number of read and write byte transfers to/from DRAM, in 32B chunk, per DDR channel. Counter increments by 1 after sending or receiving 32B chunk data.", + "Counter": "0,1,2,3,4", + "EventCode": "0x3C", + "EventName": "UNC_M_TOTAL_DATA", + "PerPkg": "1", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/pantherlake/virtual-memory.json index 690c5dff9d9e..8d56c16b2a39 100644 --- a/tools/perf/pmu-events/arch/x86/pantherlake/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/pantherlake/virtual-memory.json @@ -1,5 +1,44 @@ [ { + "BriefDescription": "Counts the number of page walks initiated by a demand load that missed the first and second level TLBs.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.MISS_CAUSED_WALK", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Loads that miss the DTLB and hit the STLB.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x320", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a demand load.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to any page size.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x08", @@ -20,6 +59,86 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Page walks completed due to a demand data load to a 1G page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Page walks completed due to a demand data load to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks initiated by a store that missed the first and second level TLBs.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.MISS_CAUSED_WALK", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of first level TLB misses but second level hits due to stores that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Stores that miss the DTLB and hit the STLB.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x320", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to any page size.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x49", @@ -40,6 +159,85 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Page walks completed due to a demand data store to a 1G page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Page walks completed due to a demand data store to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks initiated by a instruction fetch that missed the first and second level TLBs.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.MISS_CAUSED_WALK", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of first level TLB misses but second level hits due to an instruction fetch that did not start a page walk. Account for all pages sizes. Will result in an ITLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.STLB_HIT", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.STLB_HIT", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x120", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x85", @@ -58,5 +256,55 @@ "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks outstanding for iside in PMH every cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for iside in PMH every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals. Walks could be counted by edge detecting on this event, but would count restarted suspended walks.", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of retired loads that are blocked due to a first level TLB miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.DTLB_MISS", + "PublicDescription": "Counts the number of retired loads that are blocked due to a first level TLB miss. Available PDIST counters: 0,1", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" } ] diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json index 71737a1a1997..79dc34157481 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json @@ -1,63 +1,63 @@ [ { "BriefDescription": "C10 residency percent per package", - "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c10\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C10_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C8 residency percent per package", - "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c8\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C8_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C9 residency percent per package", - "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c9\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C9_Pkg_Residency", "ScaleUnit": "100%" @@ -85,7 +85,6 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", @@ -134,6 +133,7 @@ }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", @@ -148,39 +148,44 @@ "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" }, { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " + }, + { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "MetricName": "tma_bottleneck_data_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "MetricName": "tma_bottleneck_data_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_bottleneck_compute_bound_est", - "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -188,6 +193,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", @@ -196,6 +202,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", @@ -204,6 +211,7 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", @@ -212,7 +220,8 @@ }, { "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_data_cache_memory_bandwidth + tma_bottleneck_data_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", @@ -220,6 +229,7 @@ }, { "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -427,7 +437,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -619,6 +629,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", @@ -1074,7 +1085,7 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -1098,6 +1109,12 @@ "MetricName": "tma_info_pipeline_fetch_mite" }, { + "BriefDescription": "Average number of uops fetched from MS per cycle", + "MetricExpr": "IDQ.MS_UOPS / cpu@IDQ.MS_UOPS\\,cmask\\=1@", + "MetricGroup": "Fed;FetchLat;MicroSeq", + "MetricName": "tma_info_pipeline_fetch_ms" + }, + { "BriefDescription": "Instructions per a microcode Assist invocation", "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", @@ -1113,7 +1130,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1125,7 +1142,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, @@ -1134,7 +1151,7 @@ "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", @@ -1165,6 +1182,7 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@cmask\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", @@ -1316,12 +1334,12 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "BriefDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1345,7 +1363,6 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -1359,7 +1376,7 @@ "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_data_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1465,7 +1482,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1474,7 +1491,7 @@ "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1542,7 +1559,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", - "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 2", + "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 3.3", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -1676,7 +1693,7 @@ { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1713,7 +1730,6 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", @@ -1727,7 +1743,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -1741,7 +1757,6 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index 823d8b7c4224..d40761903429 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -1,49 +1,49 @@ [ { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricExpr": "cstate_core@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" @@ -71,7 +71,6 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", @@ -296,7 +295,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -308,7 +307,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json index 21db53f9e9d6..c66324d41a89 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json @@ -1,10 +1,72 @@ [ { + "BriefDescription": "Hit snoop reply with data, line invalidated.", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "CORE_SNOOP_RESPONSE.I_FWD_FE", + "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated: removed from this core's cache, after the data is forwarded back to the requestor and indicating the data was found unmodified in the (FE) Forward or Exclusive State in this cores caches cache. A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x20" + }, + { + "BriefDescription": "HitM snoop reply with data, line invalidated.", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "CORE_SNOOP_RESPONSE.I_FWD_M", + "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated: removed from this core's caches, after the data is forwarded back to the requestor, and indicating the data was found modified(M) in this cores caches cache (aka HitM response). A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Hit snoop reply without sending the data, line invalidated.", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "CORE_SNOOP_RESPONSE.I_HIT_FSE", + "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated in this core's caches without forwarded back to the requestor. The line was in Forward, Shared or Exclusive (FSE) state in this cores caches. A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Line not found snoop reply", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "CORE_SNOOP_RESPONSE.MISS", + "PublicDescription": "Counts responses to snoops indicating that the data was not found (IHitI) in this core's caches. A single snoop response from the core counts on all hyperthreads of the Core.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Hit snoop reply with data, line kept in Shared state.", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "CORE_SNOOP_RESPONSE.S_FWD_FE", + "PublicDescription": "Counts responses to snoops indicating the line may be kept on this core in the (S)hared state, after the data is forwarded back to the requestor, initially the data was found in the cache in the (FS) Forward or Shared state. A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x40" + }, + { + "BriefDescription": "HitM snoop reply with data, line kept in Shared state", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "CORE_SNOOP_RESPONSE.S_FWD_M", + "PublicDescription": "Counts responses to snoops indicating the line may be kept on this core in the (S)hared state, after the data is forwarded back to the requestor, initially the data was found in the cache in the (M)odified state. A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Hit snoop reply without sending the data, line kept in Shared state.", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "CORE_SNOOP_RESPONSE.S_HIT_FSE", + "PublicDescription": "Counts responses to snoops indicating the line was kept on this core in the (S)hared state, and that the data was found unmodified but not forwarded back to the requestor, initially the data was found in the cache in the (FSE) Forward, Shared state or Exclusive state. A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { "BriefDescription": "L1D.HWPF_MISS", "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.HWPF_MISS", - "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -13,7 +75,7 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.REPLACEMENT", - "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -22,7 +84,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -33,7 +95,7 @@ "EdgeDetect": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS", - "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", + "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -43,7 +105,6 @@ "Deprecated": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALL", - "PublicDescription": "This event is deprecated. Refer to new event L1D_PEND_MISS.L2_STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -52,7 +113,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALLS", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -61,7 +122,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -71,7 +132,7 @@ "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -80,7 +141,7 @@ "Counter": "0,1,2,3", "EventCode": "0x25", "EventName": "L2_LINES_IN.ALL", - "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", "SampleAfterValue": "100003", "UMask": "0x1f" }, @@ -89,7 +150,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.NON_SILENT", - "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", "SampleAfterValue": "200003", "UMask": "0x2" }, @@ -98,7 +159,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -107,7 +168,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.USELESS_HWPF", - "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", "SampleAfterValue": "200003", "UMask": "0x4" }, @@ -116,7 +177,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.ALL", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]", "SampleAfterValue": "200003", "UMask": "0xff" }, @@ -125,7 +186,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", "SampleAfterValue": "200003", "UMask": "0x3f" }, @@ -134,7 +195,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", - "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0", + "PublicDescription": "Counts the total number of L2 code requests.", "SampleAfterValue": "200003", "UMask": "0xe4" }, @@ -143,7 +204,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", "SampleAfterValue": "200003", "UMask": "0xe1" }, @@ -152,7 +213,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_MISS", - "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts demand requests that miss L2 cache.", "SampleAfterValue": "200003", "UMask": "0x27" }, @@ -161,7 +222,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", - "PublicDescription": "Counts demand requests to L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts demand requests to L2 cache.", "SampleAfterValue": "200003", "UMask": "0xe7" }, @@ -170,7 +231,6 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_HWPF", - "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf0" }, @@ -179,7 +239,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_RFO", - "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", "SampleAfterValue": "200003", "UMask": "0xe2" }, @@ -188,7 +248,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", - "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", "SampleAfterValue": "200003", "UMask": "0xc4" }, @@ -197,7 +257,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", - "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", "SampleAfterValue": "200003", "UMask": "0x24" }, @@ -206,7 +266,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", "SampleAfterValue": "200003", "UMask": "0xc1" }, @@ -215,7 +275,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", - "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", + "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", "SampleAfterValue": "200003", "UMask": "0x21" }, @@ -224,7 +284,6 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HWPF_MISS", - "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x30" }, @@ -233,7 +292,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", "SampleAfterValue": "200003", "UMask": "0x3f" }, @@ -242,7 +301,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.REFERENCES", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]", "SampleAfterValue": "200003", "UMask": "0xff" }, @@ -251,7 +310,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", "SampleAfterValue": "200003", "UMask": "0xc2" }, @@ -260,7 +319,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", "SampleAfterValue": "200003", "UMask": "0x22" }, @@ -269,7 +328,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_HIT", - "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", + "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", "SampleAfterValue": "200003", "UMask": "0xc8" }, @@ -278,7 +337,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_MISS", - "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", + "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", "SampleAfterValue": "200003", "UMask": "0x28" }, @@ -287,7 +346,7 @@ "Counter": "0,1,2,3", "EventCode": "0x23", "EventName": "L2_TRANS.L2_WB", - "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0", + "PublicDescription": "Counts L2 writebacks that access L2 cache.", "SampleAfterValue": "200003", "UMask": "0x40" }, @@ -296,7 +355,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", - "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", "SampleAfterValue": "100003", "UMask": "0x41" }, @@ -305,7 +364,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", "SampleAfterValue": "100003", "UMask": "0x4f" }, @@ -394,7 +453,7 @@ "Counter": "0,1,2,3", "EventCode": "0x43", "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY", - "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0", + "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)", "SampleAfterValue": "1000003", "UMask": "0xfd" }, @@ -582,7 +641,6 @@ "Counter": "0,1,2,3", "EventCode": "0x44", "EventName": "MEM_STORE_RETIRED.L2_HIT", - "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -591,7 +649,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe5", "EventName": "MEM_UOP_RETIRED.ANY", - "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0", + "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -1073,7 +1131,6 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", - "PublicDescription": "OFFCORE_REQUESTS.ALL_REQUESTS Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -1082,7 +1139,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DATA_RD", - "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -1091,7 +1148,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", - "PublicDescription": "Counts both cacheable and non-cacheable code read requests. Available PDIST counters: 0", + "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -1100,7 +1157,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", - "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1109,7 +1166,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", - "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -1119,7 +1176,6 @@ "Deprecated": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", - "PublicDescription": "This event is deprecated. Refer to new event OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -1129,7 +1185,6 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -1139,7 +1194,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1149,7 +1204,6 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", - "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1159,7 +1213,6 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -1168,7 +1221,6 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", - "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -1177,7 +1229,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1186,7 +1238,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -1195,7 +1247,7 @@ "Counter": "0,1,2,3", "EventCode": "0x2c", "EventName": "SQ_MISC.BUS_LOCK", - "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -1204,7 +1256,6 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.ANY", - "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xf" }, @@ -1213,7 +1264,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.NTA", - "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1222,7 +1273,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", - "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHW instructions executed.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -1231,7 +1282,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T0", - "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -1240,7 +1291,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T1_T2", - "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", "SampleAfterValue": "100003", "UMask": "0x4" } diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json index 8c9207750c82..bc475e163227 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json @@ -5,7 +5,6 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.FPDIV_ACTIVE", - "PublicDescription": "ARITH.FPDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -14,7 +13,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.FP", - "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0", + "PublicDescription": "Counts all microcode Floating Point assists.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -23,7 +22,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.SSE_AVX_MIX", - "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -32,7 +30,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_0", - "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -41,7 +38,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_1", - "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -50,7 +46,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_5", - "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -59,7 +54,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V0", - "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -68,7 +62,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V1", - "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -77,7 +70,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V2", - "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -86,7 +78,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -95,7 +87,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -104,7 +96,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -113,7 +105,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -122,7 +114,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x18" }, @@ -131,7 +123,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x40" }, @@ -140,7 +132,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -149,7 +141,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x60" }, @@ -158,7 +150,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", - "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -167,7 +159,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -176,7 +168,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -185,7 +177,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.VECTOR", - "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "1000003", "UMask": "0xfc" }, @@ -194,7 +186,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF", - "PublicDescription": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -203,7 +194,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF", - "PublicDescription": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -212,7 +202,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF", - "PublicDescription": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -221,7 +210,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF", - "PublicDescription": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -230,7 +218,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.SCALAR", - "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR Available PDIST counters: 0", + "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR", "SampleAfterValue": "100003", "UMask": "0x3" }, @@ -239,7 +227,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.SCALAR_HALF", - "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -248,7 +235,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.VECTOR", - "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR Available PDIST counters: 0", + "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR", "SampleAfterValue": "100003", "UMask": "0x1c" } diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json index 9fe9d62b867a..793c486ffabe 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "BACLEARS.ANY", - "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -13,7 +13,7 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.LCP", - "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -22,7 +22,6 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.MS_BUSY", - "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x2" }, @@ -31,7 +30,7 @@ "Counter": "0,1,2,3", "EventCode": "0x61", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -249,7 +248,7 @@ "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALLS", - "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.", "SampleAfterValue": "500009", "UMask": "0x4" }, @@ -260,7 +259,6 @@ "EdgeDetect": "1", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALL_PERIODS", - "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x4" }, @@ -269,7 +267,7 @@ "Counter": "0,1,2,3", "EventCode": "0x83", "EventName": "ICACHE_TAG.STALLS", - "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", "SampleAfterValue": "200003", "UMask": "0x4" }, @@ -279,7 +277,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -289,7 +287,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -298,7 +296,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.DSB_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -308,7 +306,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -318,7 +316,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -327,7 +325,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -337,7 +335,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES_ANY", - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -348,7 +346,7 @@ "EdgeDetect": "1", "EventCode": "0x79", "EventName": "IDQ.MS_SWITCHES", - "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -357,7 +355,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", - "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Available PDIST counters: 0", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS).", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -366,7 +364,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -376,7 +374,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -387,7 +385,7 @@ "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -396,7 +394,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -406,7 +404,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -417,7 +415,7 @@ "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", "SampleAfterValue": "1000003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json index 7c3f9b76d367..5e6c1f05c981 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json @@ -5,7 +5,6 @@ "CounterMask": "6", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", - "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x6" }, @@ -14,7 +13,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -24,7 +23,6 @@ "CounterMask": "2", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS", - "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -34,7 +32,6 @@ "CounterMask": "3", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS", - "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -44,7 +41,7 @@ "CounterMask": "5", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS", - "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", + "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -54,7 +51,7 @@ "CounterMask": "9", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS", - "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", + "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -478,7 +475,6 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -487,7 +483,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0", + "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -505,7 +501,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_EVENTS", - "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt). Available PDIST counters: 0", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -514,7 +510,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_MEM", - "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts). Available PDIST counters: 0", + "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -523,7 +519,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", - "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.", "SampleAfterValue": "100003", "UMask": "0x40" }, @@ -532,7 +528,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", - "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -541,7 +537,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.COMMIT", - "PublicDescription": "Counts the number of times RTM commit succeeded. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times RTM commit succeeded.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -550,7 +546,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.START", - "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -559,7 +555,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CAPACITY_READ", - "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads Available PDIST counters: 0", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -568,7 +564,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CAPACITY_WRITE", - "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes. Available PDIST counters: 0", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -577,7 +573,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CONFLICT", - "PublicDescription": "Counts the number of times a TSX line had a cache conflict. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times a TSX line had a cache conflict.", "SampleAfterValue": "100003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json index a58d65556609..21f49f609ed4 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json @@ -4,11 +4,35 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.PAGE_FAULT", - "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, { + "BriefDescription": "HW_INTERRUPTS.MASKED", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcb", + "EventName": "HW_INTERRUPTS.MASKED", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "HW_INTERRUPTS.PENDING_AND_MASKED", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcb", + "EventName": "HW_INTERRUPTS.PENDING_AND_MASKED", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of hardware interrupts received by the processor.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcb", + "EventName": "HW_INTERRUPTS.RECEIVED", + "PublicDescription": "Counts the number of hardware interruptions received by the processor.", + "SampleAfterValue": "203", + "UMask": "0x1" + }, + { "BriefDescription": "Counts streaming stores that have any type of response.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", @@ -25,7 +49,7 @@ "CounterMask": "1", "EventCode": "0x2d", "EventName": "XQ.FULL_CYCLES", - "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", "SampleAfterValue": "1000003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json index 48bec483b49a..1fa7957956df 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json @@ -6,7 +6,6 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.DIVIDER_ACTIVE", - "PublicDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -16,7 +15,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.DIV_ACTIVE", - "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -27,7 +26,6 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.FP_DIVIDER_ACTIVE", - "PublicDescription": "This event is deprecated. Refer to new event ARITH.FPDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -37,7 +35,6 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.IDIV_ACTIVE", - "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -48,7 +45,6 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.INT_DIVIDER_ACTIVE", - "PublicDescription": "This event is deprecated. Refer to new event ARITH.IDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -57,7 +53,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.ANY", - "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.", "SampleAfterValue": "100003", "UMask": "0x1b" }, @@ -217,7 +213,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C01", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -226,7 +222,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C02", - "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", + "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -235,7 +231,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C0_WAIT", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", "SampleAfterValue": "2000003", "UMask": "0x70" }, @@ -244,7 +240,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED", - "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", + "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -253,7 +249,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0", + "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.", "SampleAfterValue": "25003", "UMask": "0x2" }, @@ -262,7 +258,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE", - "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -273,7 +268,6 @@ "EdgeDetect": "1", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", - "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -282,7 +276,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED", - "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", + "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -299,7 +293,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -316,7 +310,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", "SampleAfterValue": "2000003" }, { @@ -325,7 +319,6 @@ "CounterMask": "8", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", - "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -335,7 +328,6 @@ "CounterMask": "1", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", - "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -345,7 +337,6 @@ "CounterMask": "16", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", - "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -355,7 +346,6 @@ "CounterMask": "12", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", - "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xc" }, @@ -365,7 +355,6 @@ "CounterMask": "5", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", - "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -375,7 +364,6 @@ "CounterMask": "4", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", - "PublicDescription": "Total execution stalls. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -384,7 +372,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb7", "EventName": "EXE.AMX_BUSY", - "PublicDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -393,7 +380,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -402,7 +389,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL", - "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0xc" }, @@ -411,7 +397,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -420,7 +406,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", - "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -429,7 +415,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", - "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -439,7 +425,6 @@ "CounterMask": "5", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", - "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x21" }, @@ -449,7 +434,7 @@ "CounterMask": "2", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", - "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -458,7 +443,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", - "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0", + "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", "SampleAfterValue": "1000003", "UMask": "0x80" }, @@ -467,7 +452,7 @@ "Counter": "0,1,2,3", "EventCode": "0x75", "EventName": "INST_DECODED.DECODERS", - "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -492,7 +477,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", - "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -501,7 +485,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions Available PDIST counters: 0", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -518,7 +502,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -529,7 +513,7 @@ "EdgeDetect": "1", "EventCode": "0xad", "EventName": "INT_MISC.CLEARS_COUNT", - "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -538,7 +522,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", - "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", "SampleAfterValue": "500009", "UMask": "0x80" }, @@ -547,7 +531,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.MBA_STALLS", - "PublicDescription": "INT_MISC.MBA_STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -556,7 +539,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.RECOVERY_CYCLES", - "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -567,7 +550,6 @@ "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", "MSRIndex": "0x3F7", "MSRValue": "0x7", - "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -576,7 +558,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.UOP_DROPPING", - "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -585,7 +567,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.128BIT", - "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x13" }, @@ -594,7 +575,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.256BIT", - "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xac" }, @@ -603,7 +583,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_128", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -612,7 +592,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_256", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", "SampleAfterValue": "1000003", "UMask": "0xc" }, @@ -621,7 +601,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.MUL_256", - "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80" }, @@ -630,7 +609,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.SHUFFLES", - "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -639,7 +617,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_128", - "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -648,7 +625,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_256", - "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -657,7 +633,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", - "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -666,7 +642,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.NO_SR", - "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", "SampleAfterValue": "100003", "UMask": "0x88" }, @@ -675,7 +651,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", "SampleAfterValue": "100003", "UMask": "0x82" }, @@ -684,7 +660,7 @@ "Counter": "0,1,2,3", "EventCode": "0x4c", "EventName": "LOAD_HIT_PREFETCH.SWPF", - "PublicDescription": "Counts all software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0", + "PublicDescription": "Counts all software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -694,7 +670,7 @@ "CounterMask": "1", "EventCode": "0xa8", "EventName": "LSD.CYCLES_ACTIVE", - "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -704,7 +680,7 @@ "CounterMask": "6", "EventCode": "0xa8", "EventName": "LSD.CYCLES_OK", - "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -713,7 +689,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa8", "EventName": "LSD.UOPS", - "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -724,7 +700,7 @@ "EdgeDetect": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.COUNT", - "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0", + "PublicDescription": "Counts the number of machine clears (nukes) of any type.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -733,7 +709,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SMC", - "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -742,7 +718,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe0", "EventName": "MISC2_RETIRED.LFENCE", - "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0", + "PublicDescription": "number of LFENCE retired instructions", "SampleAfterValue": "400009", "UMask": "0x20" }, @@ -751,7 +727,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcc", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -760,7 +736,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SB", - "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -769,7 +745,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SCOREBOARD", - "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -778,7 +753,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", "EventName": "RS.EMPTY", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", "SampleAfterValue": "1000003", "UMask": "0x7" }, @@ -790,7 +765,7 @@ "EventCode": "0xa5", "EventName": "RS.EMPTY_COUNT", "Invert": "1", - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", "SampleAfterValue": "100003", "UMask": "0x7" }, @@ -799,7 +774,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", "EventName": "RS.EMPTY_RESOURCE", - "PublicDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -812,7 +786,6 @@ "EventCode": "0xa5", "EventName": "RS_EMPTY.COUNT", "Invert": "1", - "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x7" }, @@ -822,7 +795,6 @@ "Deprecated": "1", "EventCode": "0xa5", "EventName": "RS_EMPTY.CYCLES", - "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x7" }, @@ -831,7 +803,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", - "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources. Available PDIST counters: 0", + "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.", "SampleAfterValue": "10000003", "UMask": "0x2" }, @@ -840,7 +812,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BAD_SPEC_SLOTS", - "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0", + "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.", "SampleAfterValue": "10000003", "UMask": "0x4" }, @@ -849,7 +821,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", - "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", "SampleAfterValue": "10000003", "UMask": "0x8" }, @@ -858,7 +830,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", - "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x10" }, @@ -875,7 +846,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.SLOTS_P", - "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", "SampleAfterValue": "10000003", "UMask": "0x1" }, @@ -884,7 +855,6 @@ "Counter": "0,1,2,3", "EventCode": "0x76", "EventName": "UOPS_DECODED.DEC0_UOPS", - "PublicDescription": "UOPS_DECODED.DEC0_UOPS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -893,7 +863,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_0", - "PublicDescription": "Number of uops dispatch to execution port 0. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution port 0.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -902,7 +872,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_1", - "PublicDescription": "Number of uops dispatch to execution port 1. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution port 1.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -911,7 +881,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_2_3_10", - "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -920,7 +890,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_4_9", - "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 4 and 9", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -929,7 +899,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_5_11", - "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 5 and 11", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -938,7 +908,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_6", - "PublicDescription": "Number of uops dispatch to execution port 6. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution port 6.", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -947,7 +917,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_7_8", - "PublicDescription": "Number of uops dispatch to execution ports 7 and 8. Available PDIST counters: 0", + "PublicDescription": "Number of uops dispatch to execution ports 7 and 8.", "SampleAfterValue": "2000003", "UMask": "0x80" }, @@ -956,7 +926,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE", - "PublicDescription": "Counts the number of uops executed from any thread. Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops executed from any thread.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -966,7 +936,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -976,7 +946,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -986,7 +956,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -996,7 +966,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -1006,7 +976,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_1", - "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1016,7 +986,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_2", - "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1026,7 +996,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_3", - "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1036,7 +1006,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_4", - "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1047,7 +1017,7 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALLS", "Invert": "1", - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1059,7 +1029,6 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALL_CYCLES", "Invert": "1", - "PublicDescription": "This event is deprecated. Refer to new event UOPS_EXECUTED.STALLS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1068,7 +1037,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.THREAD", - "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1077,7 +1045,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.X87", - "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0", + "PublicDescription": "Counts the number of x87 uops executed.", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -1086,7 +1054,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xae", "EventName": "UOPS_ISSUED.ANY", - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1096,7 +1064,6 @@ "CounterMask": "1", "EventCode": "0xae", "EventName": "UOPS_ISSUED.CYCLES", - "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1106,7 +1073,7 @@ "CounterMask": "1", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.CYCLES", - "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0", + "PublicDescription": "Counts cycles where at least one uop has retired.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1115,7 +1082,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.HEAVY", - "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0", + "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1126,7 +1093,6 @@ "EventName": "UOPS_RETIRED.MS", "MSRIndex": "0x3F7", "MSRValue": "0x8", - "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -1135,7 +1101,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.SLOTS", - "PublicDescription": "Counts the retirement slots used each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the retirement slots used each cycle.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -1146,7 +1112,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALLS", "Invert": "1", - "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0", + "PublicDescription": "This event counts cycles without actually retired uops.", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1158,7 +1124,6 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALL_CYCLES", "Invert": "1", - "PublicDescription": "This event is deprecated. Refer to new event UOPS_RETIRED.STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" } diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index fe3f288be10e..b6a28227a58a 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -1,28 +1,28 @@ [ { "BriefDescription": "C1 residency percent per core", - "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricExpr": "cstate_core@c1\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C1_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" @@ -40,6 +40,18 @@ "ScaleUnit": "1per_instr" }, { + "BriefDescription": "The average number of cores that are in cstate C0 as observed by the power control unit (PCU)", + "MetricExpr": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C0 / UNC_P_CLOCKTICKS * #num_packages", + "MetricGroup": "cpu_cstate", + "MetricName": "cpu_cstate_c0" + }, + { + "BriefDescription": "The average number of cores are in cstate C6 as observed by the power control unit (PCU)", + "MetricExpr": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C6 / UNC_P_CLOCKTICKS * #num_packages", + "MetricGroup": "cpu_cstate", + "MetricName": "cpu_cstate_c6" + }, + { "BriefDescription": "CPU operating frequency (in GHz)", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9", "MetricName": "cpu_operating_frequency", @@ -91,6 +103,12 @@ "ScaleUnit": "1MB/s" }, { + "BriefDescription": "Bandwidth of inbound IO reads that are initiated by end device controllers that are requesting memory from the CPU and miss the L3 cache", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_read_l3_miss", + "ScaleUnit": "1MB/s" + }, + { "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read_local", @@ -109,6 +127,12 @@ "ScaleUnit": "1MB/s" }, { + "BriefDescription": "Bandwidth of inbound IO writes that are initiated by end device controllers that are writing memory to the CPU", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_MISS_ITOM + UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR) * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_write_l3_miss", + "ScaleUnit": "1MB/s" + }, + { "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write_local", @@ -123,19 +147,19 @@ { "BriefDescription": "Percentage of inbound full cacheline writes initiated by end device controllers that miss the L3 cache", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM / UNC_CHA_TOR_INSERTS.IO_ITOM", - "MetricName": "io_percent_of_inbound_full_writes_that_miss_l3", + "MetricName": "io_full_write_l3_miss", "ScaleUnit": "100%" }, { "BriefDescription": "Percentage of inbound partial cacheline writes initiated by end device controllers that miss the L3 cache", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_RFO) / (UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_RFO)", - "MetricName": "io_percent_of_inbound_partial_writes_that_miss_l3", + "MetricName": "io_partial_write_l3_miss", "ScaleUnit": "100%" }, { "BriefDescription": "Percentage of inbound reads initiated by end device controllers that miss the L3 cache", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR / UNC_CHA_TOR_INSERTS.IO_PCIRDCUR", - "MetricName": "io_percent_of_inbound_reads_that_miss_l3", + "MetricName": "io_read_l3_miss", "ScaleUnit": "100%" }, { @@ -395,7 +419,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -430,39 +454,39 @@ "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" }, { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " + }, + { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "MetricName": "tma_bottleneck_data_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "MetricName": "tma_bottleneck_data_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_bottleneck_compute_bound_est", - "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -470,7 +494,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -478,7 +502,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_cxl_mem_bound + tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", @@ -494,7 +518,7 @@ }, { "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_data_cache_memory_bandwidth + tma_bottleneck_data_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", @@ -510,7 +534,7 @@ { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "BadSpec;BrMispredicts;BvMP;Default;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", @@ -611,7 +635,6 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(76.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 74.6 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", @@ -631,6 +654,15 @@ "ScaleUnit": "100%" }, { + "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external CXL Memory by loads (e.g", + "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0))) if #has_pmem > 0 else 1)) * (MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", + "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_cxl_mem_bound", + "MetricThreshold": "tma_cxl_mem_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external CXL Memory by loads (e.g. 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory, PMM - Persistent Memory Module [from CLX to SPR] or any other CXL Type3 Memory [EMR onwards]).", + "ScaleUnit": "100%" + }, + { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "74.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", @@ -660,7 +692,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks", + "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks - tma_cxl_mem_bound if #has_pmem > 0 else MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks)", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -718,7 +750,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -846,7 +878,7 @@ { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", @@ -1357,19 +1389,19 @@ { "BriefDescription": "Off-core accesses per kilo instruction for modified write requests", "MetricExpr": "1e3 * OCR.MODIFIED_WRITE.ANY_RESPONSE / tma_info_inst_mix_instructions", - "MetricGroup": "Offcore", + "MetricGroup": "Offcore;Server", "MetricName": "tma_info_memory_mix_offcore_mwrite_any_pki" }, { "BriefDescription": "Off-core accesses per kilo instruction for reads-to-core requests (speculative; including in-core HW prefetches)", "MetricExpr": "1e3 * OCR.READS_TO_CORE.ANY_RESPONSE / tma_info_inst_mix_instructions", - "MetricGroup": "CacheHits;Offcore", + "MetricGroup": "CacheHits;Offcore;Server", "MetricName": "tma_info_memory_mix_offcore_read_any_pki" }, { "BriefDescription": "L3 cache misses per kilo instruction for reads-to-core requests (speculative; including in-core HW prefetches)", "MetricExpr": "1e3 * OCR.READS_TO_CORE.L3_MISS / tma_info_inst_mix_instructions", - "MetricGroup": "Offcore", + "MetricGroup": "Offcore;Server", "MetricName": "tma_info_memory_mix_offcore_read_l3m_pki" }, { @@ -1395,21 +1427,21 @@ { "BriefDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket", "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / tma_info_system_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", + "MetricGroup": "HPC;Mem;MemoryBW;Offcore;Server", "MetricName": "tma_info_memory_soc_r2c_dram_bw", "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW." }, { "BriefDescription": "Average L3-cache miss BW for Reads-to-Core (R2C)", "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / tma_info_system_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", + "MetricGroup": "HPC;Mem;MemoryBW;Offcore;Server", "MetricName": "tma_info_memory_soc_r2c_l3m_bw", "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW." }, { "BriefDescription": "Average Off-core access BW for Reads-to-Core (R2C)", "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / tma_info_system_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", + "MetricGroup": "HPC;Mem;MemoryBW;Offcore;Server", "MetricName": "tma_info_memory_soc_r2c_offcore_bw", "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches." }, @@ -1439,7 +1471,7 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -1486,7 +1518,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1498,16 +1530,28 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, { + "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", + "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / tma_info_system_time if #has_pmem > 0 else 0)", + "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", + "MetricName": "tma_info_system_cxl_mem_read_bw" + }, + { + "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / tma_info_system_time if #has_pmem > 0 else 0)", + "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", + "MetricName": "tma_info_system_cxl_mem_write_bw" + }, + { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", @@ -1572,8 +1616,14 @@ "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { + "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", + "MetricExpr": "(1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / uncore_cha_0@event\\=0x1@ if #has_pmem > 0 else 0)", + "MetricGroup": "MemOffcore;MemoryLat;Server;SoC", + "MetricName": "tma_info_system_mem_pmm_read_latency", + "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" + }, + { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", @@ -1734,12 +1784,12 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "BriefDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1753,7 +1803,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "4.4 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", @@ -1772,12 +1821,11 @@ }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "32.6 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_data_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1860,6 +1908,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", @@ -1892,7 +1941,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1901,13 +1950,13 @@ "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "Backend;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -1917,7 +1966,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", @@ -1970,7 +2018,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", - "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2", + "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2.4", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -2005,6 +2053,7 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", @@ -2066,6 +2115,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", @@ -2075,6 +2125,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_THRESHOLD_AND_NMI", "MetricExpr": "(EXE_ACTIVITY.EXE_BOUND_0_PORTS + max(RS.EMPTY_RESOURCE - RESOURCE_STALLS.SCOREBOARD, 0)) / tma_info_thread_clks * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", @@ -2084,6 +2135,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_THRESHOLD_AND_NMI", "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", @@ -2093,7 +2145,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", @@ -2103,7 +2154,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", @@ -2132,7 +2182,7 @@ { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2160,7 +2210,6 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", @@ -2192,7 +2241,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json index a38db3e253f2..1bdda3c3ccbf 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json @@ -312,6 +312,17 @@ "Unit": "CHA" }, { + "BriefDescription": "Distress signal asserted : DPT Remote", + "Counter": "0,1,2,3", + "EventCode": "0xaf", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_NONLOCAL", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", + "UMask": "0x8", + "Unit": "CHA" + }, + { "BriefDescription": "Egress Blocking due to Ordering requirements : Down", "Counter": "0,1,2,3", "EventCode": "0xba", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-memory.json index 68be01dad7c9..30044177ccf8 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-memory.json @@ -2770,6 +2770,88 @@ "Unit": "iMC" }, { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.HIGH", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Number of DRAM Refreshes Issued : Counts the number of refreshes issued.", + "UMask": "0x24", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.HIGH_ALL", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x24", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.HIGH_PCH0", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.HIGH_PCH1", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.PANIC", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Number of DRAM Refreshes Issued : Counts the number of refreshes issued.", + "UMask": "0x12", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.PANIC_ALL", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x12", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.PANIC_PCH0", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_M_DRAM_REFRESH.PANIC_PCH1", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { "BriefDescription": "ECC Correctable Errors", "Counter": "0,1,2,3", "EventCode": "0x09", @@ -3048,6 +3130,28 @@ "Unit": "iMC" }, { + "BriefDescription": "Throttle Cycles for Rank 0", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Throttle Cycles for Rank 0 : Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1. : Thermal throttling is performed per DIMM. We support 3 DIMMs per channel. This ID allows us to filter by ID.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Throttle Cycles for Rank 0", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Throttle Cycles for Rank 0 : Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1.", + "UMask": "0x2", + "Unit": "iMC" + }, + { "BriefDescription": "Precharge due to read, write, underfill, or PGT.", "Counter": "0,1,2,3", "EventCode": "0x03", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-power.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-power.json index 9482ddaea4d1..71c35b165a3e 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-power.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-power.json @@ -178,7 +178,6 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C0", - "Experimental": "1", "PerPkg": "1", "PublicDescription": "Number of cores in C0 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" @@ -198,7 +197,6 @@ "Counter": "0,1,2,3", "EventCode": "0x37", "EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C6", - "Experimental": "1", "PerPkg": "1", "PublicDescription": "Number of cores in C6 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/virtual-memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/virtual-memory.json index 3d3f88600e26..609a9549cbf3 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/virtual-memory.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", - "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -14,7 +14,7 @@ "CounterMask": "1", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -23,7 +23,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -32,7 +32,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -41,7 +41,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -50,7 +50,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -59,7 +59,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -68,7 +68,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.STLB_HIT", - "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -78,7 +78,7 @@ "CounterMask": "1", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -87,7 +87,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -96,7 +96,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -105,7 +105,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -114,7 +114,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -123,7 +123,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -132,7 +132,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.STLB_HIT", - "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -142,7 +142,7 @@ "CounterMask": "1", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -151,7 +151,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -160,7 +160,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -169,7 +169,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -178,7 +178,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", "SampleAfterValue": "100003", "UMask": "0x10" } diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/cache.json b/tools/perf/pmu-events/arch/x86/sierraforest/cache.json index 877052db1490..b2650e8ae252 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/cache.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/cache.json @@ -163,6 +163,14 @@ "UMask": "0x6" }, { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC, no snoop was required. LLC provides the data. If the core has access to an L3 cache, an LLC hit refers to an L3 cache hit, otherwise it counts zeros.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.LLC_HIT_NOSNOOP", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches. If the core has access to an L3 cache, an LLC miss refers to an L3 cache miss, otherwise it is an L2 cache miss.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", @@ -179,6 +187,14 @@ "UMask": "0x80" }, { + "BriefDescription": "Counts the total number of load ops retired that miss the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.ALL", + "SampleAfterValue": "1000003", + "UMask": "0xff" + }, + { "BriefDescription": "Counts the number of load ops retired that miss the L3 cache and hit in DRAM", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd3", @@ -187,6 +203,31 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts the number of load ops retired that miss the L3 cache and hit in a Remote DRAM", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_OR_NOFWD", + "PublicDescription": "Counts the number of load ops retired that miss the L3 cache and hit in a Remote DRAM, OR had a Remote snoop miss/no fwd and hit in the Local Dram", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss the L3 cache and hit in a Remote Cache and modified data was forwarded", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_HITM", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss the L3 cache and hit in a Remote Cache and non-modified data was forwarded", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_NONM", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { "BriefDescription": "Counts the number of load ops retired that hit the L1 data cache.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd1", @@ -286,7 +327,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024", @@ -297,7 +338,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", @@ -308,7 +349,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", @@ -319,7 +360,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048", @@ -330,7 +371,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", @@ -341,7 +382,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", @@ -352,7 +393,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", @@ -363,7 +404,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", @@ -374,7 +415,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", @@ -385,7 +426,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", - "Counter": "0,1", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json b/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json index b9f3c611d87b..ca2c55917e55 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json @@ -1,56 +1,56 @@ [ { "BriefDescription": "C10 residency percent per package", - "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c10\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C10_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C1 residency percent per core", - "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricExpr": "cstate_core@c1\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C1_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C8 residency percent per package", - "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c8\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C8_Pkg_Residency", "ScaleUnit": "100%" @@ -735,7 +735,7 @@ }, { "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricName": "tma_info_system_cpu_utilization" }, { @@ -747,7 +747,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE_P@k / CPU_CLK_UNHALTED.CORE", + "MetricExpr": "CPU_CLK_UNHALTED.CORE_P:k / CPU_CLK_UNHALTED.CORE", "MetricGroup": "Summary", "MetricName": "tma_info_system_kernel_utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-interconnect.json index 952b6de3fefc..251e5d20fefe 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-interconnect.json @@ -839,12 +839,20 @@ "Counter": "0,1,2,3", "EventCode": "0x1F", "EventName": "UNC_I_MISC1.LOST_FWD", - "Experimental": "1", "PerPkg": "1", "UMask": "0x10", "Unit": "IRP" }, { + "BriefDescription": "Misc Events - Set 1 : Received Invalid : Secondary received a transfer that did not have sufficient MESI state", + "Counter": "0,1,2,3", + "EventCode": "0x1F", + "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { "BriefDescription": "Snoop Hit E/S responses", "Counter": "0,1,2,3", "EventCode": "0x12", diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-io.json b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-io.json index f4f956966e16..2ea2637df3fb 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-io.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-io.json @@ -1321,7 +1321,6 @@ "FCMask": "0x01", "PerPkg": "1", "PortMask": "0x0FF", - "PublicDescription": "-", "UMask": "0x4", "Unit": "IIO" }, diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json index c7e9dbe02eb0..a9fd7a34b24b 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json @@ -60,6 +60,33 @@ "BriefDescription": "CAS count for SubChannel 0 regular reads", "Counter": "0,1,2,3", "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT_SCH0.RD_NON_UNDERFILL", + "PerPkg": "1", + "UMask": "0xc3", + "Unit": "IMC" + }, + { + "BriefDescription": "CAS count for SubChannel 0 auto-precharge reads", + "Counter": "0,1,2,3", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT_SCH0.RD_PRE_REG", + "PerPkg": "1", + "UMask": "0xc2", + "Unit": "IMC" + }, + { + "BriefDescription": "CAS count for SubChannel 0 auto-precharge underfill reads", + "Counter": "0,1,2,3", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT_SCH0.RD_PRE_UNDERFILL", + "PerPkg": "1", + "UMask": "0xc8", + "Unit": "IMC" + }, + { + "BriefDescription": "CAS count for SubChannel 0 regular reads", + "Counter": "0,1,2,3", + "EventCode": "0x05", "EventName": "UNC_M_CAS_COUNT_SCH0.RD_REG", "PerPkg": "1", "UMask": "0xc1", @@ -75,6 +102,15 @@ "Unit": "IMC" }, { + "BriefDescription": "CAS count for SubChannel 0 underfill reads", + "Counter": "0,1,2,3", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT_SCH0.RD_UNDERFILL_ALL", + "PerPkg": "1", + "UMask": "0xcc", + "Unit": "IMC" + }, + { "BriefDescription": "CAS count for SubChannel 0, all writes", "Counter": "0,1,2,3", "EventCode": "0x05", @@ -125,6 +161,33 @@ "BriefDescription": "CAS count for SubChannel 1 regular reads", "Counter": "0,1,2,3", "EventCode": "0x06", + "EventName": "UNC_M_CAS_COUNT_SCH1.RD_NON_UNDERFILL", + "PerPkg": "1", + "UMask": "0xc3", + "Unit": "IMC" + }, + { + "BriefDescription": "CAS count for SubChannel 1 auto-precharge reads", + "Counter": "0,1,2,3", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_COUNT_SCH1.RD_PRE_REG", + "PerPkg": "1", + "UMask": "0xc2", + "Unit": "IMC" + }, + { + "BriefDescription": "CAS count for SubChannel 1 auto-precharge underfill reads", + "Counter": "0,1,2,3", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_COUNT_SCH1.RD_PRE_UNDERFILL", + "PerPkg": "1", + "UMask": "0xc8", + "Unit": "IMC" + }, + { + "BriefDescription": "CAS count for SubChannel 1 regular reads", + "Counter": "0,1,2,3", + "EventCode": "0x06", "EventName": "UNC_M_CAS_COUNT_SCH1.RD_REG", "PerPkg": "1", "UMask": "0xc1", @@ -140,6 +203,15 @@ "Unit": "IMC" }, { + "BriefDescription": "CAS count for SubChannel 1 underfill reads", + "Counter": "0,1,2,3", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_COUNT_SCH1.RD_UNDERFILL_ALL", + "PerPkg": "1", + "UMask": "0xcc", + "Unit": "IMC" + }, + { "BriefDescription": "CAS count for SubChannel 1, all writes", "Counter": "0,1,2,3", "EventCode": "0x06", @@ -195,7 +267,6 @@ "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -206,7 +277,6 @@ "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, @@ -217,7 +287,6 @@ "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x4", "Unit": "IMC" }, @@ -228,7 +297,6 @@ "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x8", "Unit": "IMC" }, @@ -239,7 +307,6 @@ "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -250,7 +317,6 @@ "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, @@ -261,7 +327,6 @@ "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x4", "Unit": "IMC" }, @@ -272,7 +337,6 @@ "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x8", "Unit": "IMC" }, @@ -283,7 +347,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -294,7 +357,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, @@ -305,7 +367,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK2", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x4", "Unit": "IMC" }, @@ -316,7 +377,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK3", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x8", "Unit": "IMC" }, @@ -327,7 +387,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x10", "Unit": "IMC" }, @@ -338,7 +397,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x20", "Unit": "IMC" }, @@ -349,7 +407,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK2", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x40", "Unit": "IMC" }, @@ -360,7 +417,6 @@ "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK3", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x80", "Unit": "IMC" }, @@ -371,7 +427,6 @@ "EventName": "UNC_M_POWER_CHANNEL_PPD_CYCLES", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "Unit": "IMC" }, { @@ -381,7 +436,6 @@ "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -392,7 +446,6 @@ "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, @@ -423,7 +476,6 @@ "EventName": "UNC_M_POWER_THROTTLE_CYCLES.MR4BLKEN", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x8", "Unit": "IMC" }, @@ -434,7 +486,6 @@ "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RAPLBLK", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x4", "Unit": "IMC" }, @@ -617,7 +668,6 @@ "EventName": "UNC_M_SELF_REFRESH.ENTER_SUCCESS", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "UNC_M_SELF_REFRESH.ENTER_SUCCESS", "UMask": "0x2", "Unit": "IMC" }, @@ -628,7 +678,6 @@ "EventName": "UNC_M_SELF_REFRESH.ENTER_SUCCESS_CYCLES", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -639,7 +688,6 @@ "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -650,7 +698,6 @@ "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, @@ -661,7 +708,6 @@ "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -672,7 +718,6 @@ "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, @@ -683,7 +728,6 @@ "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -694,7 +738,6 @@ "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, @@ -705,7 +748,6 @@ "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT0", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x1", "Unit": "IMC" }, @@ -716,7 +758,6 @@ "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT1", "Experimental": "1", "PerPkg": "1", - "PublicDescription": "-", "UMask": "0x2", "Unit": "IMC" }, diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index 2d3a037e88b5..707bd8790ed2 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -1,49 +1,49 @@ [ { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricExpr": "cstate_core@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" @@ -80,6 +80,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -117,6 +118,7 @@ }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", @@ -131,31 +133,35 @@ "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" }, { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " + }, + { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "MetricName": "tma_bottleneck_data_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "MetricName": "tma_bottleneck_data_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_bottleneck_compute_bound_est", - "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", @@ -163,6 +169,7 @@ }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", @@ -171,6 +178,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", @@ -179,6 +187,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", @@ -187,6 +196,7 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", @@ -195,7 +205,8 @@ }, { "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_data_cache_memory_bandwidth + tma_bottleneck_data_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", @@ -203,6 +214,7 @@ }, { "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -230,6 +242,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", @@ -391,7 +404,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -454,7 +467,6 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", @@ -520,6 +532,7 @@ }, { "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 4 / BR_MISP_RETIRED.ALL_BRANCHES / 100", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", @@ -555,6 +568,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", @@ -572,6 +586,7 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", @@ -713,7 +728,6 @@ }, { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", @@ -975,7 +989,7 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -993,6 +1007,12 @@ "MetricName": "tma_info_pipeline_fetch_mite" }, { + "BriefDescription": "Average number of uops fetched from MS per cycle", + "MetricExpr": "IDQ.MS_UOPS / cpu@IDQ.MS_UOPS\\,cmask\\=1@", + "MetricGroup": "Fed;FetchLat;MicroSeq", + "MetricName": "tma_info_pipeline_fetch_ms" + }, + { "BriefDescription": "Instructions per a microcode Assist invocation", "MetricExpr": "INST_RETIRED.ANY / (FP_ASSIST.ANY + OTHER_ASSISTS.ANY)", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", @@ -1008,7 +1028,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1020,7 +1040,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, @@ -1029,7 +1049,7 @@ "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", @@ -1175,12 +1195,13 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "BriefDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1217,7 +1238,7 @@ "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_data_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1241,6 +1262,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", @@ -1267,6 +1289,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", @@ -1275,6 +1298,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", @@ -1283,6 +1307,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", @@ -1291,6 +1316,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (9 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", @@ -1315,7 +1341,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1324,7 +1350,7 @@ "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1348,7 +1374,6 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", @@ -1358,6 +1383,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", @@ -1412,6 +1438,7 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", @@ -1421,6 +1448,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", @@ -1429,6 +1457,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", @@ -1509,6 +1538,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", @@ -1595,7 +1625,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -1652,6 +1682,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", @@ -1660,6 +1691,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", @@ -1668,6 +1700,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index 7cc7b076c3e2..56c2caaafef4 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -1,49 +1,49 @@ [ { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricExpr": "cstate_core@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" @@ -301,6 +301,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -338,6 +339,7 @@ }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", @@ -352,31 +354,35 @@ "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" }, { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " + }, + { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "MetricName": "tma_bottleneck_data_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "MetricName": "tma_bottleneck_data_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_bottleneck_compute_bound_est", - "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", @@ -384,6 +390,7 @@ }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", @@ -392,6 +399,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", @@ -400,6 +408,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", @@ -408,6 +417,7 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", @@ -416,7 +426,8 @@ }, { "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_data_cache_memory_bandwidth + tma_bottleneck_data_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", @@ -424,6 +435,7 @@ }, { "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -451,6 +463,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", @@ -612,7 +625,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -675,7 +688,6 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", @@ -750,6 +762,7 @@ }, { "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 4 / BR_MISP_RETIRED.ALL_BRANCHES / 100", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", @@ -785,6 +798,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", @@ -802,6 +816,7 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", @@ -943,7 +958,6 @@ }, { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", @@ -1225,7 +1239,7 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -1243,6 +1257,12 @@ "MetricName": "tma_info_pipeline_fetch_mite" }, { + "BriefDescription": "Average number of uops fetched from MS per cycle", + "MetricExpr": "IDQ.MS_UOPS / cpu@IDQ.MS_UOPS\\,cmask\\=1@", + "MetricGroup": "Fed;FetchLat;MicroSeq", + "MetricName": "tma_info_pipeline_fetch_ms" + }, + { "BriefDescription": "Instructions per a microcode Assist invocation", "MetricExpr": "INST_RETIRED.ANY / (FP_ASSIST.ANY + OTHER_ASSISTS.ANY)", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", @@ -1258,7 +1278,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1270,7 +1290,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, @@ -1279,7 +1299,7 @@ "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", @@ -1475,12 +1495,13 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "BriefDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1517,7 +1538,7 @@ "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_data_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1541,6 +1562,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", @@ -1567,6 +1589,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", @@ -1575,6 +1598,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", @@ -1583,6 +1607,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", @@ -1600,6 +1625,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", @@ -1624,7 +1650,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1633,7 +1659,7 @@ "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1657,7 +1683,6 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", @@ -1667,6 +1692,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", @@ -1721,6 +1747,7 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", @@ -1730,6 +1757,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", @@ -1738,6 +1766,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", @@ -1818,6 +1847,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", @@ -1923,7 +1953,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -1980,6 +2010,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", @@ -1988,6 +2019,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", @@ -1996,6 +2028,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json index 2db7a70f7a07..908da985c594 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json @@ -1,63 +1,63 @@ [ { "BriefDescription": "C10 residency percent per package", - "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c10\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C10_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c2\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c3\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricExpr": "cstate_core@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c6\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricExpr": "cstate_core@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c7\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C8 residency percent per package", - "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c8\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C8_Pkg_Residency", "ScaleUnit": "100%" }, { "BriefDescription": "C9 residency percent per package", - "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", + "MetricExpr": "cstate_pkg@c9\\-residency@ / msr@tsc@", "MetricGroup": "Power", "MetricName": "C9_Pkg_Residency", "ScaleUnit": "100%" @@ -85,7 +85,6 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", @@ -134,6 +133,7 @@ }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", @@ -148,39 +148,44 @@ "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" }, { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " + }, + { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "MetricName": "tma_bottleneck_data_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "MetricName": "tma_bottleneck_data_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_bottleneck_compute_bound_est", - "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_ms) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -188,6 +193,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", @@ -196,6 +202,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", @@ -204,6 +211,7 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", @@ -212,7 +220,8 @@ }, { "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_data_cache_memory_bandwidth + tma_bottleneck_data_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", @@ -220,6 +229,7 @@ }, { "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -427,7 +437,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -619,6 +629,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", @@ -1074,7 +1085,7 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "", + "BriefDescription": "Mem;Backend;CacheHits", "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -1098,6 +1109,12 @@ "MetricName": "tma_info_pipeline_fetch_mite" }, { + "BriefDescription": "Average number of uops fetched from MS per cycle", + "MetricExpr": "IDQ.MS_UOPS / cpu@IDQ.MS_UOPS\\,cmask\\=1@", + "MetricGroup": "Fed;FetchLat;MicroSeq", + "MetricName": "tma_info_pipeline_fetch_ms" + }, + { "BriefDescription": "Instructions per a microcode Assist invocation", "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", @@ -1113,7 +1130,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricExpr": "tma_info_system_turbo_utilization * msr@tsc@ / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1125,7 +1142,7 @@ }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" }, @@ -1134,7 +1151,7 @@ "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", @@ -1165,6 +1182,7 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@cmask\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", @@ -1316,12 +1334,12 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "BriefDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "This metric ([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1345,7 +1363,6 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", @@ -1359,7 +1376,7 @@ "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_data_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1465,7 +1482,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1474,7 +1491,7 @@ "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1542,7 +1559,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", - "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 2", + "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 3.3", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -1676,7 +1693,7 @@ { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1713,7 +1730,6 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", @@ -1727,7 +1743,7 @@ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -1741,7 +1757,6 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", |