perf vendor events intel: Update Icelake+ metric constraints

Avoid grouping events especially in cases where the kernel's PMU
driver fails to not open the events, causing the events to report back
as "<not counted>".

This update comes from:

  https://github.com/intel/perfmon/pull/94

Fixes issues reported with patch:

  https://lore.kernel.org/lkml/20230719001836.198363-3-irogers@google.com/

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20230801053634.1142634-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
index daf9458..c6780d5 100644 (file)
--- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
@@ -558,6 +558,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -800,6 +801,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
@@ -1058,7 +1060,6 @@
     },
     {
         "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",
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
@@ -1230,6 +1231,7 @@
     },
     {
         "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",
@@ -1267,6 +1269,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory 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_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_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -1355,7 +1358,6 @@
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / tma_info_core_core_clks",
         "MetricGroup": "Flops;Ret",
         "MetricName": "tma_info_core_flopc",
@@ -1363,7 +1365,6 @@
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.PORT_0@ + cpu_core@FP_ARITH_DISPATCHED.PORT_1@ + cpu_core@FP_ARITH_DISPATCHED.PORT_5@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
@@ -1769,7 +1770,6 @@
     },
     {
         "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire",
@@ -2002,6 +2002,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -2375,6 +2376,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
@@ -2405,6 +2407,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",

diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
index 0f1628d..06e67e3 100644 (file)
--- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
@@ -466,6 +466,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -682,6 +683,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",

diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
index 8fcc05c..a6eed0d 100644 (file)
--- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
@@ -85,6 +85,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
@@ -319,7 +320,6 @@
     },
     {
         "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",
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
@@ -464,6 +464,7 @@
     },
     {
         "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",
@@ -497,6 +498,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory 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_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_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_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -574,14 +576,12 @@
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks",
         "MetricGroup": "Flops;Ret",
         "MetricName": "tma_info_core_flopc"
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
@@ -927,7 +927,6 @@
     },
     {
         "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
@@ -1100,6 +1099,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -1419,6 +1419,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
@@ -1446,6 +1447,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",

diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
index 9bb7e3f..7082ad5 100644 (file)
--- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
@@ -289,6 +289,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
@@ -523,7 +524,6 @@
     },
     {
         "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",
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
@@ -668,6 +668,7 @@
     },
     {
         "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",
@@ -701,6 +702,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory 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_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (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_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -778,14 +780,12 @@
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks",
         "MetricGroup": "Flops;Ret",
         "MetricName": "tma_info_core_flopc"
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
@@ -1144,7 +1144,6 @@
     },
     {
         "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
@@ -1369,6 +1368,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -1715,6 +1715,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
@@ -1742,6 +1743,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",

diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json
index 1bb9ced..a0191c8 100644 (file)
--- a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json
@@ -85,6 +85,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
@@ -319,7 +320,6 @@
     },
     {
         "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",
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
@@ -464,6 +464,7 @@
     },
     {
         "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",
@@ -497,6 +498,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory 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_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_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_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -574,14 +576,12 @@
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks",
         "MetricGroup": "Flops;Ret",
         "MetricName": "tma_info_core_flopc"
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
@@ -933,7 +933,6 @@
     },
     {
         "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
@@ -1126,6 +1125,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -1445,6 +1445,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
@@ -1472,6 +1473,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",

diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
index c207c85..222212a 100644 (file)
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
@@ -553,7 +553,6 @@
     },
     {
         "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",
@@ -717,6 +716,7 @@
     },
     {
         "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",
@@ -750,6 +750,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory 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_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (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_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -827,14 +828,12 @@
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + FP_ARITH_INST_RETIRED2.SCALAR_HALF + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF + 4 * AMX_OPS_RETIRED.BF16",
         "MetricGroup": "Flops;Ret",
         "MetricName": "tma_info_core_flopc"
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
@@ -1216,7 +1215,6 @@
     },
     {
         "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
@@ -1467,6 +1465,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -1841,6 +1840,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
@@ -1868,6 +1868,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",

diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
index c7c2d6a..fab084e 100644 (file)
--- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
@@ -79,6 +79,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
@@ -313,7 +314,6 @@
     },
     {
         "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",
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
@@ -458,6 +458,7 @@
     },
     {
         "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",
@@ -491,6 +492,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory 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_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_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_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -568,14 +570,12 @@
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks",
         "MetricGroup": "Flops;Ret",
         "MetricName": "tma_info_core_flopc"
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
@@ -927,7 +927,6 @@
     },
     {
         "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
@@ -1114,6 +1113,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -1433,6 +1433,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
@@ -1460,6 +1461,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",