diff options
Diffstat (limited to 'tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json')
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json | 137 |
1 files changed, 78 insertions, 59 deletions
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index c220b1cf1740..c3ea39d6c944 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -110,7 +110,7 @@ }, { "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_ANY / 2) if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_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.", @@ -118,7 +118,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "(BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * tma_bad_speculation", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", @@ -142,7 +142,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "((CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if (IPC > 1.8) else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - RS_EVENTS.EMPTY_CYCLES if (tma_fetch_latency > 0.1) else RESOURCE_STALLS.SB)) * tma_backend_bound", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if IPC > 1.8 else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB)) * tma_backend_bound", "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", @@ -174,7 +174,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "(MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / CLKS", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / CLKS", "MetricGroup": "Offcore;TopdownL4;tma_l1_bound_group", "MetricName": "tma_lock_latency", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS", @@ -214,7 +214,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / CLKS", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / CLKS", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", "MetricName": "tma_l3_bound", "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", @@ -222,7 +222,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + mem_load_uops_retired.hit_lfb / ((MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS) + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + mem_load_uops_retired.hit_lfb / ((MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS) + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / CLKS", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / CLKS", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS", @@ -230,7 +230,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + mem_load_uops_retired.hit_lfb / ((MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS) + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / CLKS", + "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / CLKS", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_l3_bound_group", "MetricName": "tma_data_sharing", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS", @@ -238,7 +238,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + mem_load_uops_retired.hit_lfb / ((MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS) + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / CLKS", + "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / CLKS", "MetricGroup": "MemoryLat;TopdownL4;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", @@ -246,7 +246,7 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "((OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2) if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / CORE_CLKS", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / CORE_CLKS", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_l3_bound_group", "MetricName": "tma_sq_full", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", @@ -254,7 +254,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "(1 - (MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS))) * CYCLE_ACTIVITY.STALLS_L2_MISS / CLKS", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / CLKS", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", "MetricName": "tma_dram_bound", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", @@ -286,7 +286,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "((L2_RQSTS.RFO_HIT * 9 * (1 - (MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES))) + (1 - (MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES)) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CLKS", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CLKS", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_store_bound_group", "MetricName": "tma_store_latency", "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", @@ -334,7 +334,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if (IPC > 1.8) else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - RS_EVENTS.EMPTY_CYCLES if (tma_fetch_latency > 0.1) else RESOURCE_STALLS.SB) - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CLKS", + "MetricExpr": "((CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if IPC > 1.8 else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB)) - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CLKS", "MetricGroup": "PortsUtil;TopdownL3;tma_core_bound_group", "MetricName": "tma_ports_utilization", "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", @@ -342,7 +342,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@) / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - RS_EVENTS.EMPTY_CYCLES if (tma_fetch_latency > 0.1) else 0) / CORE_CLKS", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) / CORE_CLKS)", "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", @@ -350,7 +350,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / CORE_CLKS", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / CORE_CLKS)", "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful.", @@ -358,7 +358,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS)", "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop.", @@ -366,14 +366,14 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS", "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / (4 * CORE_CLKS)", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / SLOTS", "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "ScaleUnit": "100%" @@ -429,7 +429,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / CORE_CLKS", + "MetricExpr": "tma_port_4", "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "ScaleUnit": "100%" @@ -522,7 +522,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY) * IDQ.MS_UOPS / SLOTS", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", "MetricGroup": "MicroSeq;TopdownL3;tma_heavy_operations_group", "MetricName": "tma_microcode_sequencer", "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS", @@ -595,26 +595,26 @@ }, { "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) / CORE_CLKS", + "MetricExpr": "(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) / CORE_CLKS", "MetricGroup": "Flops;Ret", "MetricName": "FLOPc" }, { "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 * CORE_CLKS)", + "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 * CORE_CLKS)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "FP_Arith_Utilization", "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": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / ((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "ILP" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "((CPU_CLK_UNHALTED.THREAD / 2) * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK)) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2) if #SMT_on else CLKS", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else CLKS))", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, @@ -656,13 +656,13 @@ }, { "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)", + "MetricExpr": "INST_RETIRED.ANY / (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)", "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))", + "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))", "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." @@ -715,7 +715,7 @@ }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ((IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS))", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", "MetricGroup": "DSB;Fed;FetchBW", "MetricName": "DSB_Coverage" }, @@ -727,13 +727,13 @@ }, { "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": " (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * SLOTS / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * SLOTS / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;BrMispredicts", "MetricName": "Branch_Misprediction_Cost" }, { "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb)", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", "MetricGroup": "Mem;MemoryBound;MemoryLat", "MetricName": "Load_Miss_Real_Latency" }, @@ -745,43 +745,43 @@ }, { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", "MetricName": "L1MPKI" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", "MetricName": "L2MPKI" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", - "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem;Offcore", "MetricName": "L2MPKI_All" }, { "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", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", "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", + "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", "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", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", "MetricName": "L2HPKI_Load" }, { "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", "MetricName": "L3MPKI" }, @@ -794,19 +794,19 @@ }, { "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / 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", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / 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", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "L3_Cache_Fill_BW" }, @@ -836,19 +836,19 @@ }, { "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", "MetricGroup": "HPC;Summary", "MetricName": "CPU_Utilization" }, { "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * msr@tsc@ / 1000000000 / duration_time", + "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", "MetricGroup": "Power;Summary", "MetricName": "Average_Frequency" }, { "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", + "MetricExpr": "(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) / 1e9 / duration_time", "MetricGroup": "Cor;Flops;HPC", "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." @@ -861,7 +861,7 @@ }, { "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", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", "MetricName": "SMT_2T_Utilization" }, @@ -879,68 +879,87 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@) / 1000000 / duration_time / 1000", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "DRAM_BW_Use" }, { "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / arb@event\\=0x81\\,umask\\=0x1@", + "MetricExpr": "MEM_Parallel_Requests", "MetricGroup": "Mem;SoC", "MetricName": "MEM_Request_Latency" }, { "BriefDescription": "Average number of parallel requests to external memory. Accounts for all requests", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / arb@event\\=0x81\\,umask\\=0x1@", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", "MetricGroup": "Mem;SoC", "MetricName": "MEM_Parallel_Requests" }, { + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "UNC_CLOCK.SOCKET", + "MetricGroup": "SoC", + "MetricName": "Socket_CLKS" + }, + { "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "IpFarBranch" }, { + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" + }, + { "BriefDescription": "C3 residency percent per core", - "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "MetricExpr": "cstate_core@c3\\-residency@ / TSC", "MetricGroup": "Power", - "MetricName": "C3_Core_Residency" + "MetricName": "C3_Core_Residency", + "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per core", - "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", "MetricGroup": "Power", - "MetricName": "C6_Core_Residency" + "MetricName": "C6_Core_Residency", + "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per core", - "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", "MetricGroup": "Power", - "MetricName": "C7_Core_Residency" + "MetricName": "C7_Core_Residency", + "ScaleUnit": "100%" }, { "BriefDescription": "C2 residency percent per package", - "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency" + "MetricName": "C2_Pkg_Residency", + "ScaleUnit": "100%" }, { "BriefDescription": "C3 residency percent per package", - "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency" + "MetricName": "C3_Pkg_Residency", + "ScaleUnit": "100%" }, { "BriefDescription": "C6 residency percent per package", - "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency" + "MetricName": "C6_Pkg_Residency", + "ScaleUnit": "100%" }, { "BriefDescription": "C7 residency percent per package", - "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency" + "MetricName": "C7_Pkg_Residency", + "ScaleUnit": "100%" } ] |