From 638a9e433ecd61e64761352dbec1fa4f5874c941 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Wed, 7 Aug 2024 15:18:06 +0200 Subject: Merging upstream version 6.10.3. Signed-off-by: Daniel Baumann --- .../pmu-events/arch/x86/icelakex/icx-metrics.json | 95 +++++++++------------- 1 file changed, 38 insertions(+), 57 deletions(-) (limited to 'tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json') 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 c015b8277d..769ba12bef 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -667,23 +667,20 @@ { "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", "MetricExpr": "(100 * (1 - max(0, topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots - (CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * (topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots)) / (((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + max(0, topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots - (CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * (topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots)) * RS_EVENTS.EMPTY_CYCLES) / CPU_CLK_UNHALTED.THREAD * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CPU_CLK_UNHALTED.THREAD * CPU_CLK_UNHALTED.THREAD + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD) if max(0, topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots - (CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * (topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots)) < (((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + max(0, topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots - (CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * (topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots)) * RS_EVENTS.EMPTY_CYCLES) / CPU_CLK_UNHALTED.THREAD * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CPU_CLK_UNHALTED.THREAD * CPU_CLK_UNHALTED.THREAD + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD) else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT;TopdownL1;tma_L1_group", - "MetricName": "tma_info_botlnk_core_bound_likely", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_botlnk_core_bound_likely" }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.", "MetricExpr": "100 * (100 * ((5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / slots * (DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD) / (ICACHE_DATA.STALLS / CPU_CLK_UNHALTED.THREAD + ICACHE_TAG.STALLS / CPU_CLK_UNHALTED.THREAD + (INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + 10 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) + min(3 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD, 1) + DECODE.LCP / CPU_CLK_UNHALTED.THREAD + DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD) + max(0, topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / slots - (5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / slots) * ((IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / (CPU_CLK_UNHALTED.DISTRIBUTED if #SMT_on else CPU_CLK_UNHALTED.THREAD) / 2) / ((IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / (CPU_CLK_UNHALTED.DISTRIBUTED if #SMT_on else CPU_CLK_UNHALTED.THREAD) / 2 + (IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / (CPU_CLK_UNHALTED.DISTRIBUTED if #SMT_on else CPU_CLK_UNHALTED.THREAD) / 2)))", - "MetricGroup": "DSBmiss;Fed;TopdownL1;tma_L1_group", - "MetricName": "tma_info_botlnk_dsb_misses", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_botlnk_dsb_misses" }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck.", "MetricExpr": "100 * (100 * ((5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / slots * (ICACHE_DATA.STALLS / CPU_CLK_UNHALTED.THREAD) / (ICACHE_DATA.STALLS / CPU_CLK_UNHALTED.THREAD + ICACHE_TAG.STALLS / CPU_CLK_UNHALTED.THREAD + (INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + 10 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) + min(3 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD, 1) + DECODE.LCP / CPU_CLK_UNHALTED.THREAD + DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD)))", - "MetricGroup": "Fed;FetchLat;IcMiss;TopdownL1;tma_L1_group", - "MetricName": "tma_info_botlnk_ic_misses", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_botlnk_ic_misses" }, { "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", @@ -1045,16 +1042,14 @@ { "BriefDescription": "\"Bus lock\" per kilo instruction", "MetricExpr": "tma_info_memory_mix_bus_lock_pki", - "MetricGroup": "Mem;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_bus_lock_pki", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem", + "MetricName": "tma_info_memory_bus_lock_pki" }, { "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "tma_info_memory_tlb_code_stlb_mpki", - "MetricGroup": "Fed;MemoryTLB;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_code_stlb_mpki", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_memory_code_stlb_mpki" }, { "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", @@ -1095,9 +1090,8 @@ { "BriefDescription": "Average Parallel L2 cache miss data reads", "MetricExpr": "tma_info_memory_latency_data_l2_mlp", - "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_data_l2_mlp", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_data_l2_mlp" }, { "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", @@ -1114,9 +1108,8 @@ { "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / (duration_time * 1e3 / 1e3)", - "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t" }, { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", @@ -1139,23 +1132,20 @@ { "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / (duration_time * 1e3 / 1e3)", - "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_l2_cache_fill_bw_2t", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l2_cache_fill_bw_2t" }, { "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / INST_RETIRED.ANY", - "MetricGroup": "L2Evicts;Mem;Server;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_l2_evictions_nonsilent_pki", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_memory_l2_evictions_nonsilent_pki" }, { "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / INST_RETIRED.ANY", - "MetricGroup": "L2Evicts;Mem;Server;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_l2_evictions_silent_pki", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_memory_l2_evictions_silent_pki" }, { "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", @@ -1190,9 +1180,8 @@ { "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / (duration_time * 1e3 / 1e3)", - "MetricGroup": "Mem;MemoryBW;Offcore;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_l3_cache_access_bw_2t", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_l3_cache_access_bw_2t" }, { "BriefDescription": "", @@ -1203,9 +1192,8 @@ { "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / (duration_time * 1e3 / 1e3)", - "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_l3_cache_fill_bw_2t", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l3_cache_fill_bw_2t" }, { "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", @@ -1240,23 +1228,20 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_load_l2_miss_latency", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_memory_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", - "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_load_l2_mlp", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_load_l2_mlp" }, { "BriefDescription": "Average Latency for L3 cache miss demand Loads", "MetricExpr": "cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,umask\\=0x10@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_load_l3_miss_latency", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_memory_load_l3_miss_latency" }, { "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", @@ -1267,9 +1252,8 @@ { "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "tma_info_memory_tlb_load_stlb_mpki", - "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_load_stlb_mpki", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_load_stlb_mpki" }, { "BriefDescription": "\"Bus lock\" per kilo instruction", @@ -1293,16 +1277,14 @@ { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (2 * (CPU_CLK_UNHALTED.DISTRIBUTED if #SMT_on else CPU_CLK_UNHALTED.THREAD))", - "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_page_walks_utilization", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_page_walks_utilization" }, { "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "tma_info_memory_tlb_store_stlb_mpki", - "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_store_stlb_mpki", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_store_stlb_mpki" }, { "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", @@ -1332,9 +1314,8 @@ { "BriefDescription": "Un-cacheable retired load per kilo instruction", "MetricExpr": "1e3 * MEM_LOAD_MISC_RETIRED.UC / INST_RETIRED.ANY", - "MetricGroup": "Mem;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_uc_load_pki", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem", + "MetricName": "tma_info_memory_uc_load_pki" }, { "BriefDescription": "", -- cgit v1.2.3