mirrors/linux-stable
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git synced 2024-09-29 05:44:11 +00:00
Code Issues Releases Wiki Activity

perf vendor events intel: Refresh broadwell metrics and events

Browse source 
Update the broadwell metrics and events using the new tooling from:

  https://github.com/intel/perfmon

The metrics are unchanged but the formulas differ due to parentheses,
use of exponents and removal of redundant operations like "* 1".  The
events are unchanged but unused json values are removed, implicit
umasks of 0 are dropped and duplicate short and long descriptions have
the long one dropped. This increases consistency across the json
files.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20221215064755.1620246-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Ian Rogers 2022-12-14 22:47:28 -08:00 committed by Arnaldo Carvalho de Melo
parent 6fa91f645f
commit fec57a8e4a
10 changed files with 84 additions and 2396 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

137
tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
View file

@ -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%"
}
]

957
tools/perf/pmu-events/arch/x86/broadwell/cache.json
View file

File diff suppressed because it is too large Load diff

40
tools/perf/pmu-events/arch/x86/broadwell/floating-point.json
View file

@ -1,8 +1,6 @@
[
{
"BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"SampleAfterValue": "2000003",
@ -10,8 +8,6 @@
},
{
"BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 4 calculations per element.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"SampleAfterValue": "2000003",
@ -19,8 +15,6 @@
},
{
"BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 4 calculations per element.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"SampleAfterValue": "2000003",
@ -28,8 +22,6 @@
},
{
"BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 8 calculations per element.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"SampleAfterValue": "2000003",
@ -37,8 +29,6 @@
},
{
"BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
"SampleAfterValue": "2000006",
@ -46,8 +36,6 @@
},
{
"BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* packed double and single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.PACKED",
"SampleAfterValue": "2000004",
@ -55,8 +43,6 @@
},
{
"BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation operation. Applies to SSE* and AVX* scalar double and single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR",
"SampleAfterValue": "2000003",
@ -64,8 +50,6 @@
},
{
"BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"SampleAfterValue": "2000003",
@ -73,8 +57,6 @@
},
{
"BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"SampleAfterValue": "2000003",
@ -82,8 +64,6 @@
},
{
"BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar and packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SINGLE",
"SampleAfterValue": "2000005",
@ -91,8 +71,6 @@
},
{
"BriefDescription": "Cycles with any input/output SSE or FP assist",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.ANY",
@ -102,8 +80,6 @@
},
{
"BriefDescription": "Number of SIMD FP assists due to input values",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.SIMD_INPUT",
"PublicDescription": "This event counts any input SSE* FP assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
@ -112,8 +88,6 @@
},
{
"BriefDescription": "Number of SIMD FP assists due to Output values",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.SIMD_OUTPUT",
"PublicDescription": "This event counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
@ -122,8 +96,6 @@
},
{
"BriefDescription": "Number of X87 assists due to input value.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.X87_INPUT",
"PublicDescription": "This event counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
@ -132,8 +104,6 @@
},
{
"BriefDescription": "Number of X87 assists due to output value.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.X87_OUTPUT",
"PublicDescription": "This event counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
@ -142,8 +112,6 @@
},
{
"BriefDescription": "Number of SIMD Move Elimination candidate uops that were eliminated.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x58",
"EventName": "MOVE_ELIMINATION.SIMD_ELIMINATED",
"SampleAfterValue": "1000003",
@ -151,8 +119,6 @@
},
{
"BriefDescription": "Number of SIMD Move Elimination candidate uops that were not eliminated.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x58",
"EventName": "MOVE_ELIMINATION.SIMD_NOT_ELIMINATED",
"SampleAfterValue": "1000003",
@ -160,8 +126,6 @@
},
{
"BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM30",
"EventCode": "0xC1",
"EventName": "OTHER_ASSISTS.AVX_TO_SSE",
@ -171,8 +135,6 @@
},
{
"BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM30",
"EventCode": "0xC1",
"EventName": "OTHER_ASSISTS.SSE_TO_AVX",
@ -182,8 +144,6 @@
},
{
"BriefDescription": "Micro-op dispatches cancelled due to insufficient SIMD physical register file read ports",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xA0",
"EventName": "UOP_DISPATCHES_CANCELLED.SIMD_PRF",
"PublicDescription": "This event counts the number of micro-operations cancelled after they were dispatched from the scheduler to the execution units when the total number of physical register read ports across all dispatch ports exceeds the read bandwidth of the physical register file. The SIMD_PRF subevent applies to the following instructions: VDPPS, DPPS, VPCMPESTRI, PCMPESTRI, VPCMPESTRM, PCMPESTRM, VFMADD*, VFMADDSUB*, VFMSUB*, VMSUBADD*, VFNMADD*, VFNMSUB*. See the Broadwell Optimization Guide for more information.",

56
tools/perf/pmu-events/arch/x86/broadwell/frontend.json
View file

@ -1,8 +1,6 @@
[
{
"BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xe6",
"EventName": "BACLEARS.ANY",
"SampleAfterValue": "100003",
@ -10,8 +8,6 @@
},
{
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xAB",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
@ -20,8 +16,6 @@
},
{
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.HIT",
"PublicDescription": "This event counts the number of both cacheable and noncacheable Instruction Cache, Streaming Buffer and Victim Cache Reads including UC fetches.",
@ -30,8 +24,6 @@
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.IFDATA_STALL",
"PublicDescription": "This event counts cycles during which the demand fetch waits for data (wfdM104H) from L2 or iSB (opportunistic hit).",
@ -40,8 +32,6 @@
},
{
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Misses. Includes Uncacheable accesses.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.MISSES",
"PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes UC accesses.",
@ -50,8 +40,6 @@
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
@ -61,8 +49,6 @@
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
@ -72,8 +58,6 @@
},
{
"BriefDescription": "Cycles MITE is delivering 4 Uops",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
@ -83,8 +67,6 @@
},
{
"BriefDescription": "Cycles MITE is delivering any Uop",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
@ -94,8 +76,6 @@
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES",
@ -105,8 +85,6 @@
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.DSB_UOPS",
"PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
@ -115,8 +93,6 @@
},
{
"BriefDescription": "Instruction Decode Queue (IDQ) empty cycles",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.EMPTY",
"PublicDescription": "This counts the number of cycles that the instruction decoder queue is empty and can indicate that the application may be bound in the front end. It does not determine whether there are uops being delivered to the Alloc stage since uops can be delivered by bypass skipping the Instruction Decode Queue (IDQ) when it is empty.",
@ -125,8 +101,6 @@
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MITE_ALL_UOPS",
"PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
@ -135,8 +109,6 @@
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES",
@ -146,8 +118,6 @@
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MITE_UOPS",
"PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
@ -156,8 +126,6 @@
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_CYCLES",
@ -167,8 +135,6 @@
},
{
"BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_CYCLES",
@ -178,8 +144,6 @@
},
{
"BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
@ -190,8 +154,6 @@
},
{
"BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_UOPS",
"PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
@ -200,8 +162,6 @@
},
{
"BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_MITE_UOPS",
"PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ.",
@ -210,8 +170,6 @@
},
{
"BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
@ -221,8 +179,6 @@
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_UOPS",
"PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
@ -231,8 +187,6 @@
},
{
"BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
"PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
@ -241,8 +195,6 @@
},
{
"BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "4",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
@ -252,8 +204,6 @@
},
{
"BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
@ -263,8 +213,6 @@
},
{
"BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "3",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
@ -274,8 +222,6 @@
},
{
"BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "2",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
@ -284,8 +230,6 @@
},
{
"BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",

890
tools/perf/pmu-events/arch/x86/broadwell/memory.json
View file

File diff suppressed because it is too large Load diff

8
tools/perf/pmu-events/arch/x86/broadwell/other.json
View file

@ -1,8 +1,6 @@
[
{
"BriefDescription": "Unhalted core cycles when the thread is in ring 0",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING0",
"PublicDescription": "This event counts the unhalted core cycles during which the thread is in the ring 0 privileged mode.",
@ -11,8 +9,6 @@
},
{
"BriefDescription": "Number of intervals between processor halts while thread is in ring 0",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x5C",
@ -23,8 +19,6 @@
},
{
"BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING123",
"PublicDescription": "This event counts unhalted core cycles during which the thread is in rings 1, 2, or 3.",
@ -33,8 +27,6 @@
},
{
"BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x63",
"EventName": "LOCK_CYCLES.SPLIT_LOCK_UC_LOCK_DURATION",
"PublicDescription": "This event counts cycles in which the L1 and L2 are locked due to a UC lock or split lock. A lock is asserted in case of locked memory access, due to noncacheable memory, locked operation that spans two cache lines, or a page walk from the noncacheable page table. L1D and L2 locks have a very high performance penalty and it is highly recommended to avoid such access.",

272
tools/perf/pmu-events/arch/x86/broadwell/pipeline.json
View file

File diff suppressed because it is too large Load diff

19
tools/perf/pmu-events/arch/x86/broadwell/uncore-cache.json
View file

@ -1,7 +1,6 @@
[
{
"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",
@ -11,7 +10,6 @@
},
{
"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",
@ -21,7 +19,6 @@
},
{
"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",
@ -31,7 +28,6 @@
},
{
"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",
@ -41,7 +37,6 @@
},
{
"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",
@ -51,7 +46,6 @@
},
{
"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",
@ -61,7 +55,6 @@
},
{
"BriefDescription": "L3 Lookup read request that access cache and found line in M-state",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.READ_M",
"PerPkg": "1",
@ -71,7 +64,6 @@
},
{
"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",
@ -81,7 +73,6 @@
},
{
"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",
@ -91,7 +82,6 @@
},
{
"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",
@ -101,7 +91,6 @@
},
{
"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",
@ -111,41 +100,33 @@
},
{
"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"
}

25
tools/perf/pmu-events/arch/x86/broadwell/uncore-other.json
View file

@ -1,78 +1,65 @@
[
{
"BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
"Counter": "0,1",
"EventCode": "0x84",
"EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
"PerPkg": "1",
"PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
"UMask": "0x01",
"UMask": "0x1",
"Unit": "ARB"
},
{
"BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
"Counter": "0,",
"EventCode": "0x80",
"EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
"PerPkg": "1",
"PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
"UMask": "0x01",
"UMask": "0x1",
"Unit": "ARB"
},
{
"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.;",
"Counter": "0,",
"CounterMask": "1",
"EventCode": "0x80",
"EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
"PerPkg": "1",
"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.",
"UMask": "0x01",
"UMask": "0x1",
"Unit": "ARB"
},
{
"BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.",
"Counter": "0,",
"EventCode": "0x80",
"EventName": "UNC_ARB_TRK_OCCUPANCY.DRD_DIRECT",
"PerPkg": "1",
"PublicDescription": "Each cycle count number of valid coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.",
"UMask": "0x02",
"UMask": "0x2",
"Unit": "ARB"
},
{
"BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
"Counter": "0,1",
"EventCode": "0x81",
"EventName": "UNC_ARB_TRK_REQUESTS.ALL",
"PerPkg": "1",
"PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
"UMask": "0x01",
"UMask": "0x1",
"Unit": "ARB"
},
{
"BriefDescription": "Number of Core coherent Data Read entries allocated in DirectData mode",
"Counter": "0,1",
"EventCode": "0x81",
"EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT",
"PerPkg": "1",
"PublicDescription": "Number of Core coherent Data Read entries allocated in DirectData mode.",
"UMask": "0x02",
"UMask": "0x2",
"Unit": "ARB"
},
{
"BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
"Counter": "0,1",
"EventCode": "0x81",
"EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
"PerPkg": "1",
"PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
"UMask": "0x20",
"Unit": "ARB"
},
{
"BriefDescription": "This 48-bit fixed counter counts the UCLK cycles",
"Counter": "FIXED",
"EventCode": "0xff",
"EventName": "UNC_CLOCK.SOCKET",
"PerPkg": "1",

76
tools/perf/pmu-events/arch/x86/broadwell/virtual-memory.json
View file

@ -1,8 +1,6 @@
[
{
"BriefDescription": "Load misses in all DTLB levels that cause page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
@ -12,8 +10,6 @@
},
{
"BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"SampleAfterValue": "2000003",
@ -21,8 +17,6 @@
},
{
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_2M",
"SampleAfterValue": "2000003",
@ -30,8 +24,6 @@
},
{
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_4K",
"SampleAfterValue": "2000003",
@ -39,8 +31,6 @@
},
{
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
@ -49,8 +39,6 @@
},
{
"BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (1G)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
@ -60,8 +48,6 @@
},
{
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (2M/4M).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
@ -71,8 +57,6 @@
},
{
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (4K).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
@ -82,8 +66,6 @@
},
{
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
@ -93,8 +75,6 @@
},
{
"BriefDescription": "Store misses in all DTLB levels that cause page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
@ -104,8 +84,6 @@
},
{
"BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"SampleAfterValue": "100003",
@ -113,8 +91,6 @@
},
{
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_2M",
"SampleAfterValue": "100003",
@ -122,8 +98,6 @@
},
{
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_4K",
"SampleAfterValue": "100003",
@ -131,8 +105,6 @@
},
{
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
@ -141,8 +113,6 @@
},
{
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (1G)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
@ -152,8 +122,6 @@
},
{
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
@ -163,8 +131,6 @@
},
{
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
@ -174,8 +140,6 @@
},
{
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_DURATION",
@ -185,8 +149,6 @@
},
{
"BriefDescription": "Cycle count for an Extended Page table walk.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x4F",
"EventName": "EPT.WALK_CYCLES",
"PublicDescription": "This event counts cycles for an extended page table walk. The Extended Page directory cache differs from standard TLB caches by the operating system that use it. Virtual machine operating systems use the extended page directory cache, while guest operating systems use the standard TLB caches.",
@ -195,8 +157,6 @@
},
{
"BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xAE",
"EventName": "ITLB.ITLB_FLUSH",
"PublicDescription": "This event counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).",
@ -205,8 +165,6 @@
},
{
"BriefDescription": "Misses at all ITLB levels that cause page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
@ -216,8 +174,6 @@
},
{
"BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT",
"SampleAfterValue": "100003",
@ -225,8 +181,6 @@
},
{
"BriefDescription": "Code misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT_2M",
"SampleAfterValue": "100003",
@ -234,8 +188,6 @@
},
{
"BriefDescription": "Core misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT_4K",
"SampleAfterValue": "100003",
@ -243,8 +195,6 @@
},
{
"BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
@ -253,8 +203,6 @@
},
{
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (1G)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
@ -264,8 +212,6 @@
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
@ -275,8 +221,6 @@
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
@ -286,8 +230,6 @@
},
{
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_DURATION",
@ -297,8 +239,6 @@
},
{
"BriefDescription": "Number of DTLB page walker hits in the L1+FB.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L1",
@ -307,8 +247,6 @@
},
{
"BriefDescription": "Number of DTLB page walker hits in the L2.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L2",
@ -317,8 +255,6 @@
},
{
"BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L3",
@ -327,8 +263,6 @@
},
{
"BriefDescription": "Number of DTLB page walker hits in Memory.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
@ -337,8 +271,6 @@
},
{
"BriefDescription": "Number of ITLB page walker hits in the L1+FB.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L1",
@ -347,8 +279,6 @@
},
{
"BriefDescription": "Number of ITLB page walker hits in the L2.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L2",
@ -357,8 +287,6 @@
},
{
"BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L3",
@ -367,8 +295,6 @@
},
{
"BriefDescription": "DTLB flush attempts of the thread-specific entries",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.DTLB_THREAD",
"PublicDescription": "This event counts the number of DTLB flush attempts of the thread-specific entries.",
@ -377,8 +303,6 @@
},
{
"BriefDescription": "STLB flush attempts",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.STLB_ANY",
"PublicDescription": "This event counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, and so on).",