From: Ian Rogers Date: Mon, 18 Aug 2025 19:04:15 +0000 (-0700) Subject: perf vendor events: Update skylake metrics X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=94ce35cdb626733f0473615fd6337b9bdc44ea84;p=users%2Fhch%2Fmisc.git perf vendor events: Update skylake metrics Update metrics from TMA 5.0 to 5.1. Signed-off-by: Ian Rogers Tested-by: Thomas Falcon Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andreas Färber Cc: Caleb Biggers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Manivannan Sadhasivam Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Weilin Wang Cc: linux-actions@lists.infradead.org Link: https://lore.kernel.org/r/20250818190416.145274-20-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- 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", @@ -130,32 +132,36 @@ "MetricThreshold": "tma_bottleneck_branching_overhead > 5", "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" @@ -992,6 +1006,12 @@ "MetricGroup": "Fed;FetchBW", "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)", @@ -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", @@ -351,32 +353,36 @@ "MetricThreshold": "tma_bottleneck_branching_overhead > 5", "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" @@ -1242,6 +1256,12 @@ "MetricGroup": "Fed;FetchBW", "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)", @@ -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",