{
"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",
+ "MetricGroup": "Mem;MemoryTLB;Offcore",
"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",
+ "MetricGroup": "Mem;MemoryTLB;Offcore_SMT",
"MetricName": "Memory_Data_TLBs_SMT"
},
{
"MetricName": "FLOPc_SMT"
},
{
- "BriefDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width)",
+ "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or 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) ) / ( 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."
+ "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
},
{
- "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.",
+ "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or 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) ) / ( 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."
+ "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common). 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)",
+ "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core",
"MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
"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": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
+ "MetricExpr": "( 1 - ((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_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)))) / ((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) * EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if ( ARITH.DIVIDER_ACTIVE < ( CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY ) ) else (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD) if ((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_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)))) < ((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) * EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if ( ARITH.DIVIDER_ACTIVE < ( CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY ) ) else (EXE_ACTIVITY.1_PORTS_UTIL + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD) else 1 ) if 0 > 0.5 else 0",
+ "MetricGroup": "Cor;SMT",
+ "MetricName": "Core_Bound_Likely"
},
{
- "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
- "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
- "MetricGroup": "Bad;BadSpec;BrMispredicts",
- "MetricName": "IpMispredict"
+ "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
+ "MetricExpr": "( 1 - ((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_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 ) ))))) / ((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (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)) / CPU_CLK_UNHALTED.THREAD if ( ARITH.DIVIDER_ACTIVE < ( CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY ) ) else (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) / CPU_CLK_UNHALTED.THREAD) if ((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_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 ) ))))) < ((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (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)) / CPU_CLK_UNHALTED.THREAD if ( ARITH.DIVIDER_ACTIVE < ( CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY ) ) else (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) / CPU_CLK_UNHALTED.THREAD) else 1 ) if (1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_UNHALTED.REF_XCLK_ANY / 2 )) > 0.5 else 0",
+ "MetricGroup": "Cor;SMT_SMT",
+ "MetricName": "Core_Bound_Likely_SMT"
},
{
"BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
"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 Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@",
+ "MetricGroup": "Prefetches",
+ "MetricName": "IpSWPF"
+ },
{
"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 retired in cycles where at least one uop has retired.",
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
+ "MetricGroup": "Pipeline;Ret",
+ "MetricName": "Retire"
+ },
+ {
+ "BriefDescription": "",
+ "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
+ "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
+ "MetricName": "Execute"
+ },
{
"BriefDescription": "Average number of Uops issued by front-end when it issued something",
"MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
"MetricName": "DSB_Coverage"
},
{
- "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)))",
+ "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT",
+ "MetricGroup": "DSBmiss",
+ "MetricName": "DSB_Switch_Cost"
+ },
+ {
+ "BriefDescription": "Total penalty related to DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.",
+ "MetricExpr": "100 * ( (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"
+ "MetricName": "DSB_Misses"
},
{
- "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 ) ))))",
+ "BriefDescription": "Total penalty related to DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.",
+ "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 ) ))) * (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"
+ "MetricName": "DSB_Misses_SMT"
},
{
- "BriefDescription": "Number of Instructions per non-speculative DSB miss",
+ "BriefDescription": "Number of Instructions per non-speculative DSB miss (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
"MetricGroup": "DSBmiss;Fed",
"MetricName": "IpDSB_Miss_Ret"
},
+ {
+ "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+ "MetricGroup": "Bad;BadSpec;BrMispredicts",
+ "MetricName": "IpMispredict"
+ },
+ {
+ "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": "Fraction of branches that are non-taken conditionals",
"MetricExpr": "BR_INST_RETIRED.NOT_TAKEN / BR_INST_RETIRED.ALL_BRANCHES",
"MetricName": "Jump"
},
{
- "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles)",
+ "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
"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."
+ "MetricName": "Load_Miss_Real_Latency"
},
{
"BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
"MetricGroup": "Mem;MemoryBound;MemoryBW",
"MetricName": "MLP"
},
- {
- "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
- "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
- "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": "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": "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": "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",
"MetricName": "L2MPKI"
},
{
- "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+ "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses;Offcore",
"MetricName": "L2MPKI_All"
},
{
- "BriefDescription": "L2 cache misses per kilo instruction for all demand loads (including speculative)",
+ "BriefDescription": "L2 cache ([RKL+] true) 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"
"MetricName": "L3MPKI"
},
{
- "BriefDescription": "Fill Buffer (FB) true hits per kilo instructions for retired demand loads",
+ "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)",
"MetricExpr": "1000 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "FB_HPKI"
"MetricGroup": "Mem;MemoryTLB_SMT",
"MetricName": "Page_Walks_Utilization_SMT"
},
+ {
+ "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
+ "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+ "MetricGroup": "Mem;MemoryBW",
+ "MetricName": "L1D_Cache_Fill_BW"
+ },
+ {
+ "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
+ "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+ "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": "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": "Mem;MemoryBW;Offcore",
+ "MetricName": "L3_Cache_Access_BW"
+ },
+ {
+ "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
+ "MetricExpr": "(64 * L1D.REPLACEMENT / 1000000000 / duration_time)",
+ "MetricGroup": "Mem;MemoryBW",
+ "MetricName": "L1D_Cache_Fill_BW_1T"
+ },
+ {
+ "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
+ "MetricExpr": "(64 * L2_LINES_IN.ALL / 1000000000 / duration_time)",
+ "MetricGroup": "Mem;MemoryBW",
+ "MetricName": "L2_Cache_Fill_BW_1T"
+ },
+ {
+ "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricExpr": "(64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time)",
+ "MetricGroup": "Mem;MemoryBW",
+ "MetricName": "L3_Cache_Fill_BW_1T"
+ },
+ {
+ "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]",
+ "MetricExpr": "(64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time)",
+ "MetricGroup": "Mem;MemoryBW;Offcore",
+ "MetricName": "L3_Cache_Access_BW_1T"
+ },
{
"BriefDescription": "Average CPU Utilization",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
"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 ) / 1000000000 ) / duration_time",
"MetricGroup": "Cor;Flops;HPC",
- "MetricName": "GFLOPs"
+ "MetricName": "GFLOPs",
+ "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine."
},
{
"BriefDescription": "Average Frequency Utilization relative nominal frequency",
--- /dev/null
+[
+ {
+ "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state",
+ "Counter": "0,1",
+ "EventCode": "0x34",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES",
+ "PerPkg": "1",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
+ "UMask": "0x86",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "L3 Lookup any request that access cache and found line in I-state",
+ "Counter": "0,1",
+ "EventCode": "0x34",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I",
+ "PerPkg": "1",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.",
+ "UMask": "0x88",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "L3 Lookup any request that access cache and found line in M-state",
+ "Counter": "0,1",
+ "EventCode": "0x34",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M",
+ "PerPkg": "1",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.",
+ "UMask": "0x81",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state",
+ "Counter": "0,1",
+ "EventCode": "0x34",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI",
+ "PerPkg": "1",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
+ "UMask": "0x8f",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state",
+ "Counter": "0,1",
+ "EventCode": "0x34",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES",
+ "PerPkg": "1",
+ "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
+ "UMask": "0x16",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "L3 Lookup read request that access cache and found line in I-state",
+ "Counter": "0,1",
+ "EventCode": "0x34",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I",
+ "PerPkg": "1",
+ "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.",
+ "UMask": "0x18",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state",
+ "Counter": "0,1",
+ "EventCode": "0x34",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI",
+ "PerPkg": "1",
+ "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
+ "UMask": "0x1f",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state",
+ "Counter": "0,1",
+ "EventCode": "0x34",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES",
+ "PerPkg": "1",
+ "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
+ "UMask": "0x26",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "L3 Lookup write request that access cache and found line in M-state",
+ "Counter": "0,1",
+ "EventCode": "0x34",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M",
+ "PerPkg": "1",
+ "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.",
+ "UMask": "0x21",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state",
+ "Counter": "0,1",
+ "EventCode": "0x34",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI",
+ "PerPkg": "1",
+ "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
+ "UMask": "0x2f",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+ "Counter": "0,1",
+ "EventCode": "0x22",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE",
+ "PerPkg": "1",
+ "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+ "UMask": "0x48",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+ "Counter": "0,1",
+ "EventCode": "0x22",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE",
+ "PerPkg": "1",
+ "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+ "UMask": "0x44",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+ "Counter": "0,1",
+ "EventCode": "0x22",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION",
+ "PerPkg": "1",
+ "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+ "UMask": "0x81",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+ "Counter": "0,1",
+ "EventCode": "0x22",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE",
+ "PerPkg": "1",
+ "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+ "UMask": "0x41",
+ "Unit": "CBO"
+ }
+]
+++ /dev/null
-[
- {
- "Unit": "CBO",
- "EventCode": "0x22",
- "UMask": "0x41",
- "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE",
- "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
- "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "CBO",
- "EventCode": "0x22",
- "UMask": "0x81",
- "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION",
- "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
- "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "CBO",
- "EventCode": "0x22",
- "UMask": "0x44",
- "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE",
- "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
- "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "CBO",
- "EventCode": "0x22",
- "UMask": "0x48",
- "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE",
- "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
- "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "CBO",
- "EventCode": "0x34",
- "UMask": "0x21",
- "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M",
- "BriefDescription": "L3 Lookup write request that access cache and found line in M-state",
- "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "CBO",
- "EventCode": "0x34",
- "UMask": "0x81",
- "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M",
- "BriefDescription": "L3 Lookup any request that access cache and found line in M-state",
- "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "CBO",
- "EventCode": "0x34",
- "UMask": "0x18",
- "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I",
- "BriefDescription": "L3 Lookup read request that access cache and found line in I-state",
- "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "CBO",
- "EventCode": "0x34",
- "UMask": "0x88",
- "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I",
- "BriefDescription": "L3 Lookup any request that access cache and found line in I-state",
- "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "CBO",
- "EventCode": "0x34",
- "UMask": "0x1f",
- "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI",
- "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state",
- "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "CBO",
- "EventCode": "0x34",
- "UMask": "0x2f",
- "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI",
- "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state",
- "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "CBO",
- "EventCode": "0x34",
- "UMask": "0x8f",
- "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI",
- "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state",
- "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "CBO",
- "EventCode": "0x34",
- "UMask": "0x86",
- "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES",
- "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state",
- "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "CBO",
- "EventCode": "0x34",
- "UMask": "0x16",
- "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES",
- "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state",
- "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "CBO",
- "EventCode": "0x34",
- "UMask": "0x26",
- "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES",
- "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state",
- "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "iMPH-U",
- "EventCode": "0x80",
- "UMask": "0x01",
- "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
- "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
- "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
- "Counter": "0",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "iMPH-U",
- "EventCode": "0x81",
- "UMask": "0x01",
- "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
- "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
- "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "iMPH-U",
- "EventCode": "0x81",
- "UMask": "0x02",
- "EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT",
- "BriefDescription": "Number of Core coherent Data Read entries allocated in DirectData mode",
- "PublicDescription": "Number of Core coherent Data Read entries allocated in DirectData mode.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "iMPH-U",
- "EventCode": "0x81",
- "UMask": "0x20",
- "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
- "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
- "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "iMPH-U",
- "EventCode": "0x84",
- "UMask": "0x01",
- "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
- "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
- "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
- "Counter": "0,1",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "iMPH-U",
- "EventCode": "0x80",
- "UMask": "0x01",
- "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
- "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.;",
- "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
- "Counter": "0",
- "CounterMask": "1",
- "Invert": "0",
- "EdgeDetect": "0"
- },
- {
- "Unit": "NCU",
- "EventCode": "0x0",
- "UMask": "0x01",
- "EventName": "UNC_CLOCK.SOCKET",
- "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles",
- "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
- "Counter": "FIXED",
- "CounterMask": "0",
- "Invert": "0",
- "EdgeDetect": "0"
- }
-]
\ No newline at end of file
projects / kernel.git / commitdiff