From cbd393afa3ff6ef951e40c3bfbe7538aaf72c9aa Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 2 May 2023 15:38:15 -0700 Subject: [PATCH] perf vendor events intel: Add sapphirerapids metric constraints Previously these constraints were disabled as they contained topdown events. Since: https://lore.kernel.org/all/20230312021543.3060328-9-irogers@google.com/ the topdown events are correctly grouped even if no group exists. This change was created by PR: https://github.com/intel/perfmon/pull/71 Signed-off-by: Ian Rogers Tested-by: Kan Liang Cc: Adrian Hunter Cc: Ahmad Yasin Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Caleb Biggers Cc: Edward Baker Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kang Minchul Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Samantha Alt Cc: Stephane Eranian Cc: Sumanth Korikkar Cc: Suzuki Poulouse Cc: Thomas Richter Cc: Tiezhu Yang Cc: Weilin Wang Cc: Xing Zhengjun Cc: Yang Jihong Link: https://lore.kernel.org/r/20230502223851.2234828-9-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json | 11 +++++++++++ 1 file changed, 11 insertions(+) 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 620fc5b..4308e24 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -290,6 +290,7 @@ }, { "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector + tma_fp_amx", "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", @@ -412,6 +413,7 @@ }, { "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(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_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_branch_misprediction_cost", @@ -457,6 +459,7 @@ }, { "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", "MetricGroup": "Cor;SMT", "MetricName": "tma_info_core_bound_likely", @@ -509,6 +512,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_dsb_misses", @@ -590,6 +594,7 @@ }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", "MetricGroup": "Fed;FetchBW;Frontend", "MetricName": "tma_info_instruction_fetch_bw", @@ -998,6 +1003,7 @@ }, { "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_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_info_memory_data_tlbs", @@ -1006,6 +1012,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "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_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))", "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_info_memory_latency", @@ -1014,6 +1021,7 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * (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;tma_issueBM", "MetricName": "tma_info_mispredictions", @@ -1054,6 +1062,7 @@ }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_retiring * tma_info_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_retire" @@ -1328,6 +1337,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1399,6 +1409,7 @@ }, { "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 + tma_nop_instructions))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", -- 2.7.4