diff options
Diffstat (limited to 'tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json')
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json | 461 |
1 files changed, 414 insertions, 47 deletions
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 863c9e103969..b016f7d1ff3d 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -1,26 +1,167 @@ [ { + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound." + }, + { + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD)", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example." + }, + { + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricConstraint": "NO_NMI_WATCHDOG", + "MetricExpr": "1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) - ( UOPS_ISSUED.ANY + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD)", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound." + }, + { + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) - ( UOPS_ISSUED.ANY + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. " + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * ( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) * ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) )", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "Mispredictions" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * ( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) )", + "MetricGroup": "Bad;BadSpec;BrMispredicts_SMT", + "MetricName": "Mispredictions_SMT" + }, + { + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricExpr": "100 * ((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) - ( UOPS_ISSUED.ANY + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) * ( ( (CYCLE_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD + (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD) - (( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) / ( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ ) ) * (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD))) / #((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) - ( UOPS_ISSUED.ANY + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) ) * ( (min( CPU_CLK_UNHALTED.THREAD , cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@ ) / CPU_CLK_UNHALTED.THREAD) / #(CYCLE_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD + (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD) - (( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) / ( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ ) ) * (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD))) ) + ( (( CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS ) / CPU_CLK_UNHALTED.THREAD) / #((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) - ( UOPS_ISSUED.ANY + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) ) * ( (OFFCORE_REQUESTS_BUFFER.SQ_FULL / CPU_CLK_UNHALTED.THREAD) / #(( CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS ) / CPU_CLK_UNHALTED.THREAD) ) ) + ( (max( ( CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS ) / CPU_CLK_UNHALTED.THREAD , 0 )) / #((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) - ( UOPS_ISSUED.ANY + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) ) * ( ((L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )) * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / CPU_CLK_UNHALTED.THREAD) / #(max( ( CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS ) / CPU_CLK_UNHALTED.THREAD , 0 )) ) ", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "Memory_Bandwidth" + }, + { + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricExpr": "100 * ((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) - ( UOPS_ISSUED.ANY + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * ( ( (CYCLE_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD + (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD) - (( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) / ( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ ) ) * (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD))) / #((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) - ( UOPS_ISSUED.ANY + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * ( (min( CPU_CLK_UNHALTED.THREAD , cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@ ) / CPU_CLK_UNHALTED.THREAD) / #(CYCLE_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD + (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD) - (( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) / ( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ ) ) * (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD))) ) + ( (( CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS ) / CPU_CLK_UNHALTED.THREAD) / #((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) - ( UOPS_ISSUED.ANY + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * ( (( OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) / #(( CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS ) / CPU_CLK_UNHALTED.THREAD) ) ) + ( (max( ( CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS ) / CPU_CLK_UNHALTED.THREAD , 0 )) / #((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) - ( UOPS_ISSUED.ANY + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * ( ((L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )) * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / CPU_CLK_UNHALTED.THREAD) / #(max( ( CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS ) / CPU_CLK_UNHALTED.THREAD , 0 )) ) ", + "MetricGroup": "Mem;MemoryBW;Offcore_SMT", + "MetricName": "Memory_Bandwidth_SMT" + }, + { + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricExpr": "100 * ((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) - ( UOPS_ISSUED.ANY + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) * ( ( (CYCLE_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD + (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD) - (( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) / ( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ ) ) * (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD))) / #((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) - ( UOPS_ISSUED.ANY + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) ) * ( (min( CPU_CLK_UNHALTED.THREAD , OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD ) / CPU_CLK_UNHALTED.THREAD - (min( CPU_CLK_UNHALTED.THREAD , cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@ ) / CPU_CLK_UNHALTED.THREAD)) / #(CYCLE_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD + (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD) - (( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) / ( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ ) ) * (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD))) ) + ( (( CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS ) / CPU_CLK_UNHALTED.THREAD) / #((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) - ( UOPS_ISSUED.ANY + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) ) * ( (( (20.5 * ((CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC) * msr@tsc@ / 1000000000 / duration_time)) - (3.5 * ((CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC) * msr@tsc@ / 1000000000 / duration_time)) ) * MEM_LOAD_RETIRED.L3_HIT * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / 2) / CPU_CLK_UNHALTED.THREAD) / #(( CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS ) / CPU_CLK_UNHALTED.THREAD) ) + ( (( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) / ( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ ) ) * (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD)) / #((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) - ( UOPS_ISSUED.ANY + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) ) )", + "MetricGroup": "Mem;MemoryLat;Offcore", + "MetricName": "Memory_Latency" + }, + { + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricExpr": "100 * ((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) - ( UOPS_ISSUED.ANY + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * ( ( (CYCLE_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD + (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD) - (( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) / ( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ ) ) * (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD))) / #((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) - ( UOPS_ISSUED.ANY + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * ( (min( CPU_CLK_UNHALTED.THREAD , OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD ) / CPU_CLK_UNHALTED.THREAD - (min( CPU_CLK_UNHALTED.THREAD , cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@ ) / CPU_CLK_UNHALTED.THREAD)) / #(CYCLE_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD + (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD) - (( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) / ( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ ) ) * (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD))) ) + ( (( CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS ) / CPU_CLK_UNHALTED.THREAD) / #((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) - ( UOPS_ISSUED.ANY + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * ( (( (20.5 * ((CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC) * msr@tsc@ / 1000000000 / duration_time)) - (3.5 * ((CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC) * msr@tsc@ / 1000000000 / duration_time)) ) * MEM_LOAD_RETIRED.L3_HIT * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / 2) / CPU_CLK_UNHALTED.THREAD) / #(( CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS ) / CPU_CLK_UNHALTED.THREAD) ) + ( (( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) / ( (MEM_LOAD_RETIRED.L2_HIT * ( 1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) )) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ ) ) * (( CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS ) / CPU_CLK_UNHALTED.THREAD)) / #((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) - ( UOPS_ISSUED.ANY + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) )", + "MetricGroup": "Mem;MemoryLat;Offcore_SMT", + "MetricName": "Memory_Latency_SMT" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * ((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) - ( UOPS_ISSUED.ANY + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) * ( ( (max( ( CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS ) / CPU_CLK_UNHALTED.THREAD , 0 )) / ((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) - ( UOPS_ISSUED.ANY + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) ) * ( (min( 9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE , max( CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS , 0 ) ) / CPU_CLK_UNHALTED.THREAD) / (max( ( CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS ) / CPU_CLK_UNHALTED.THREAD , 0 )) ) + ( (EXE_ACTIVITY.BOUND_ON_STORES / CPU_CLK_UNHALTED.THREAD) / #((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) - ( UOPS_ISSUED.ANY + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) ) * ( (( 9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE ) / CPU_CLK_UNHALTED.THREAD) / #(EXE_ACTIVITY.BOUND_ON_STORES / CPU_CLK_UNHALTED.THREAD) ) ) ", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "Memory_Data_TLBs" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * ((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) - ( UOPS_ISSUED.ANY + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * ( ( (max( ( CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS ) / CPU_CLK_UNHALTED.THREAD , 0 )) / ((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) - ( UOPS_ISSUED.ANY + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * ( (min( 9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE , max( CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS , 0 ) ) / CPU_CLK_UNHALTED.THREAD) / (max( ( CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS ) / CPU_CLK_UNHALTED.THREAD , 0 )) ) + ( (EXE_ACTIVITY.BOUND_ON_STORES / CPU_CLK_UNHALTED.THREAD) / #((( CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES ) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES)) * (1 - (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) - ( UOPS_ISSUED.ANY + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * ( (( 9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) / #(EXE_ACTIVITY.BOUND_ON_STORES / CPU_CLK_UNHALTED.THREAD) ) ) ", + "MetricGroup": "Mem;MemoryTLB;_SMT", + "MetricName": "Memory_Data_TLBs_SMT" + }, + { + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * (( BR_INST_RETIRED.CONDITIONAL + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - ( BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN ) - 2 * BR_INST_RETIRED.NEAR_CALL) ) / (4 * CPU_CLK_UNHALTED.THREAD))", + "MetricGroup": "Ret", + "MetricName": "Branching_Overhead" + }, + { + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * (( BR_INST_RETIRED.CONDITIONAL + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - ( BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN ) - 2 * BR_INST_RETIRED.NEAR_CALL) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "MetricGroup": "Ret_SMT", + "MetricName": "Branching_Overhead_SMT" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) * ( (ICACHE_64B.IFTAG_STALL / CPU_CLK_UNHALTED.THREAD) + (( ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ ) / CPU_CLK_UNHALTED.THREAD) + (9 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) ) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD))", + "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "Big_Code" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * ( (ICACHE_64B.IFTAG_STALL / CPU_CLK_UNHALTED.THREAD) + (( ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ ) / CPU_CLK_UNHALTED.THREAD) + (9 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) ) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB_SMT", + "MetricName": "Big_Code_SMT" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricExpr": "100 * ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) - (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) * ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) ) - (100 * (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) * ( (ICACHE_64B.IFTAG_STALL / CPU_CLK_UNHALTED.THREAD) + (( ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ ) / CPU_CLK_UNHALTED.THREAD) + (9 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) ) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)))", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "Instruction_Fetch_BW" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricExpr": "100 * ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) - (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) ) - (100 * (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * ( (ICACHE_64B.IFTAG_STALL / CPU_CLK_UNHALTED.THREAD) + (( ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ ) / CPU_CLK_UNHALTED.THREAD) + (9 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) ) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))", + "MetricGroup": "Fed;FetchBW;Frontend_SMT", + "MetricName": "Instruction_Fetch_BW_SMT" + }, + { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Summary", + "MetricGroup": "Ret;Summary", "MetricName": "IPC" }, { "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Retire", + "MetricGroup": "Pipeline;Ret;Retire", "MetricName": "UPI" }, { "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;FetchBW;PGO", - "MetricName": "IpTB" + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "UpTB" }, { "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / (INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD)", - "MetricGroup": "Pipeline", + "MetricGroup": "Pipeline;Mem", "MetricName": "CPI" }, { @@ -30,39 +171,84 @@ "MetricName": "CLKS" }, { - "BriefDescription": "Instructions Per Cycle (per physical core)", + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "TmaL1", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", + "MetricGroup": "TmaL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "Execute_per_Issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + }, + { + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "SMT;TmaL1", + "MetricGroup": "Ret;SMT;TmaL1", "MetricName": "CoreIPC" }, { - "BriefDescription": "Instructions Per Cycle (per physical core)", + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", "MetricExpr": "INST_RETIRED.ANY / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", - "MetricGroup": "SMT;TmaL1", + "MetricGroup": "Ret;SMT;TmaL1_SMT", "MetricName": "CoreIPC_SMT" }, { "BriefDescription": "Floating Point Operations Per Cycle", "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Flops", + "MetricGroup": "Ret;Flops", "MetricName": "FLOPc" }, { "BriefDescription": "Floating Point Operations Per Cycle", "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", - "MetricGroup": "Flops_SMT", + "MetricGroup": "Ret;Flops_SMT", "MetricName": "FLOPc_SMT" }, { + "BriefDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width)", + "MetricExpr": "( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) ) / ( 2 * CPU_CLK_UNHALTED.THREAD )", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "FP_Arith_Utilization", + "PublicDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). Values > 1 are possible due to Fused-Multiply Add (FMA) counting." + }, + { + "BriefDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) ) / ( 2 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ) )", + "MetricGroup": "Cor;Flops;HPC_SMT", + "MetricName": "FP_Arith_Utilization_SMT", + "PublicDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). Values > 1 are possible due to Fused-Multiply Add (FMA) counting. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Pipeline;PortsUtil", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "ILP" }, { + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": " ( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) * ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) ) * (4 * CPU_CLK_UNHALTED.THREAD) / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "Branch_Misprediction_Cost" + }, + { + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": " ( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) ) * (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts_SMT", + "MetricName": "Branch_Misprediction_Cost_SMT" + }, + { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "BrMispredicts", + "MetricGroup": "Bad;BadSpec;BrMispredicts", "MetricName": "IpMispredict" }, { @@ -86,122 +272,249 @@ { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;InsType", + "MetricGroup": "Branches;Fed;InsType", "MetricName": "IpBranch" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches", + "MetricGroup": "Branches;Fed;PGO", "MetricName": "IpCall" }, { + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", + "MetricName": "IpTB" + }, + { "BriefDescription": "Branch instructions per taken branch. ", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;PGO", + "MetricGroup": "Branches;Fed;PGO", "MetricName": "BpTkBranch" }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )", - "MetricGroup": "Flops;FpArith;InsType", + "MetricGroup": "Flops;InsType", "MetricName": "IpFLOP" }, { + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / ( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) )", + "MetricGroup": "Flops;InsType", + "MetricName": "IpArith", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." + }, + { + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "IpArith_Scalar_SP", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + }, + { + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "IpArith_Scalar_DP", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE )", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "IpArith_AVX128", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "IpArith_AVX256", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "IpArith_AVX512", + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + }, + { "BriefDescription": "Total number of retired Instructions, Sample with: INST_RETIRED.PREC_DIST", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1", "MetricName": "Instructions" }, { + "BriefDescription": "Average number of Uops issued by front-end when it issued something", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "Fetch_UpC" + }, + { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;FetchBW", + "MetricGroup": "DSB;Fed;FetchBW", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", + "BriefDescription": "Total penalty related to DSB (uop cache) misses - subset/see of/the Instruction_Fetch_BW Bottleneck.", + "MetricExpr": "(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) * (DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) + ((IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) - (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD))) * (( IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS ) / CPU_CLK_UNHALTED.THREAD / 2) / #((IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) - (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)))", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "DSB_Misses_Cost" + }, + { + "BriefDescription": "Total penalty related to DSB (uop cache) misses - subset/see of/the Instruction_Fetch_BW Bottleneck.", + "MetricExpr": "(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * (DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + ((IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) - (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ) / 2) / #((IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) - (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))", + "MetricGroup": "DSBmiss;Fed_SMT", + "MetricName": "DSB_Misses_Cost_SMT" + }, + { + "BriefDescription": "Number of Instructions per non-speculative DSB miss", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "IpDSB_Miss_Ret" + }, + { + "BriefDescription": "Fraction of branches that are non-taken conditionals", + "MetricExpr": "BR_INST_RETIRED.NOT_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "Cond_NT" + }, + { + "BriefDescription": "Fraction of branches that are taken conditionals", + "MetricExpr": "( BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN ) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "Cond_TK" + }, + { + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "( BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN ) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "CallRet" + }, + { + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - ( BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN ) - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "Jump" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles)", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )", - "MetricGroup": "MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency" + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "Load_Miss_Real_Latency", + "PublicDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles). Latency may be overestimated for multi-load instructions - e.g. repeat strings." }, { "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "MemoryBound;MemoryBW", + "MetricGroup": "Mem;MemoryBound;MemoryBW", "MetricName": "MLP" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * CORE_CLKS )", - "MetricGroup": "MemoryTLB", - "MetricName": "Page_Walks_Utilization" - }, - { "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", - "MetricGroup": "MemoryBW", + "MetricGroup": "Mem;MemoryBW", "MetricName": "L1D_Cache_Fill_BW" }, { "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", - "MetricGroup": "MemoryBW", + "MetricGroup": "Mem;MemoryBW", "MetricName": "L2_Cache_Fill_BW" }, { "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", - "MetricGroup": "MemoryBW", + "MetricGroup": "Mem;MemoryBW", "MetricName": "L3_Cache_Fill_BW" }, { "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time", - "MetricGroup": "MemoryBW;Offcore", + "MetricGroup": "Mem;MemoryBW;Offcore", "MetricName": "L3_Cache_Access_BW" }, { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses", + "MetricGroup": "Mem;CacheMisses", "MetricName": "L1MPKI" }, { + "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1000 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", + "MetricGroup": "Mem;CacheMisses", + "MetricName": "L1MPKI_Load" + }, + { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses", + "MetricGroup": "Mem;Backend;CacheMisses", "MetricName": "L2MPKI" }, { "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Offcore", + "MetricGroup": "Mem;CacheMisses;Offcore", "MetricName": "L2MPKI_All" }, { + "BriefDescription": "L2 cache misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "Mem;CacheMisses", + "MetricName": "L2MPKI_Load" + }, + { "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses", + "MetricGroup": "Mem;CacheMisses", "MetricName": "L2HPKI_All" }, { + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricGroup": "Mem;CacheMisses", + "MetricName": "L2HPKI_Load" + }, + { "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses", + "MetricGroup": "Mem;CacheMisses", "MetricName": "L3MPKI" }, { + "BriefDescription": "Fill Buffer (FB) true hits per kilo instructions for retired demand loads", + "MetricExpr": "1000 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "Mem;CacheMisses", + "MetricName": "FB_HPKI" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricConstraint": "NO_NMI_WATCHDOG", + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * CPU_CLK_UNHALTED.THREAD )", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "Page_Walks_Utilization" + }, + { + "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 + EPT.WALK_PENDING ) / ( 2 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ) )", + "MetricGroup": "Mem;MemoryTLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { "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": "1000 * L2_LINES_OUT.SILENT / INST_RETIRED.ANY", - "MetricGroup": "L2Evicts;Server", + "MetricGroup": "L2Evicts;Mem;Server", "MetricName": "L2_Evictions_Silent_PKI" }, { "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", "MetricExpr": "1000 * L2_LINES_OUT.NON_SILENT / INST_RETIRED.ANY", - "MetricGroup": "L2Evicts;Server", + "MetricGroup": "L2Evicts;Mem;Server", "MetricName": "L2_Evictions_NonSilent_PKI" }, { @@ -219,7 +532,7 @@ { "BriefDescription": "Giga Floating Point Operations Per Second", "MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / 1000000000 ) / duration_time", - "MetricGroup": "Flops;HPC", + "MetricGroup": "Cor;Flops;HPC", "MetricName": "GFLOPs" }, { @@ -229,6 +542,48 @@ "MetricName": "Turbo_Utilization" }, { + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", + "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Power", + "MetricName": "Power_License0_Utilization", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." + }, + { + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / 2 / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", + "MetricGroup": "Power_SMT", + "MetricName": "Power_License0_Utilization_SMT", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", + "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Power", + "MetricName": "Power_License1_Utilization", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." + }, + { + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / 2 / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", + "MetricGroup": "Power_SMT", + "MetricName": "Power_License1_Utilization_SMT", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", + "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Power", + "MetricName": "Power_License2_Utilization", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." + }, + { + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / 2 / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", + "MetricGroup": "Power_SMT", + "MetricName": "Power_License2_Utilization_SMT", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", "MetricGroup": "SMT", @@ -241,33 +596,45 @@ "MetricName": "Kernel_Utilization" }, { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "Kernel_CPI" + }, + { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", - "MetricGroup": "HPC;MemoryBW;SoC", + "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "DRAM_BW_Use" }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", "MetricExpr": "1000000000 * ( cha@event\\=0x36\\,umask\\=0x21\\,config\\=0x40433@ / cha@event\\=0x35\\,umask\\=0x21\\,config\\=0x40433@ ) / ( cha_0@event\\=0x0@ / duration_time )", - "MetricGroup": "MemoryLat;SoC", + "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "MEM_Read_Latency" }, { "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", "MetricExpr": "cha@event\\=0x36\\,umask\\=0x21\\,config\\=0x40433@ / cha@event\\=0x36\\,umask\\=0x21\\,config\\=0x40433\\,thresh\\=1@", - "MetricGroup": "MemoryBW;SoC", + "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "MEM_Parallel_Reads" }, { + "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches", + "MetricExpr": "1000000000 * ( UNC_M_RPQ_OCCUPANCY / UNC_M_RPQ_INSERTS ) / imc_0@event\\=0x0@", + "MetricGroup": "Mem;MemoryLat;SoC;Server", + "MetricName": "MEM_DRAM_Read_Latency" + }, + { "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", "MetricExpr": "( UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3 ) * 4 / 1000000000 / duration_time", - "MetricGroup": "IoBW;SoC;Server", + "MetricGroup": "IoBW;Mem;SoC;Server", "MetricName": "IO_Write_BW" }, { "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", "MetricExpr": "( UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3 ) * 4 / 1000000000 / duration_time", - "MetricGroup": "IoBW;SoC;Server", + "MetricGroup": "IoBW;Mem;SoC;Server", "MetricName": "IO_Read_BW" }, { |