[PATCH v5 01/35] perf vendor events: Update alderlake events/metrics

From: Ian Rogers
Date: Fri Mar 28 2025 - 13:53:18 EST


Update events from v1.28 to v1.29. Update event topics, addition of
PDIST counter into descriptions, metrics to be generated from the TMA
spreadsheet and other small clean ups.

Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
.../arch/x86/alderlake/adl-metrics.json | 489 +++++++++---------
.../pmu-events/arch/x86/alderlake/cache.json | 284 +++++++---
.../arch/x86/alderlake/floating-point.json | 29 +-
.../arch/x86/alderlake/frontend.json | 78 +--
.../pmu-events/arch/x86/alderlake/memory.json | 82 ++-
.../pmu-events/arch/x86/alderlake/other.json | 209 +-------
.../arch/x86/alderlake/pipeline.json | 308 +++++++----
.../arch/x86/alderlake/virtual-memory.json | 43 +-
tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +-
9 files changed, 843 insertions(+), 681 deletions(-)

diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
index 147379cae37b..377dfecd96bd 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
@@ -103,7 +103,7 @@
"MetricExpr": "tma_core_bound",
"MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
"MetricName": "tma_allocation_restriction",
- "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))",
+ "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
},
@@ -113,7 +113,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "Default;TopdownL1;tma_L1_group",
"MetricName": "tma_backend_bound",
- "MetricThreshold": "(tma_backend_bound >0.10)",
+ "MetricThreshold": "tma_backend_bound > 0.1",
"MetricgroupNoGroup": "TopdownL1;Default",
"PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count",
"ScaleUnit": "100%",
@@ -125,7 +125,7 @@
"MetricExpr": "(5 * cpu_atom@CPU_CLK_UNHALTED.CORE@ - (cpu_atom@TOPDOWN_FE_BOUND.ALL@ + cpu_atom@TOPDOWN_BE_BOUND.ALL@ + cpu_atom@TOPDOWN_RETIRING.ALL@)) / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "Default;TopdownL1;tma_L1_group",
"MetricName": "tma_bad_speculation",
- "MetricThreshold": "(tma_bad_speculation >0.15)",
+ "MetricThreshold": "tma_bad_speculation > 0.15",
"MetricgroupNoGroup": "TopdownL1;Default",
"PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
"ScaleUnit": "100%",
@@ -136,7 +136,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
"MetricName": "tma_branch_detect",
- "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
"PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
@@ -146,7 +146,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
"MetricName": "tma_branch_mispredicts",
- "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))",
+ "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
@@ -156,7 +156,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
"MetricName": "tma_branch_resteer",
- "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
},
@@ -165,7 +165,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
"MetricName": "tma_cisc",
- "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
},
@@ -174,7 +174,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
"MetricName": "tma_core_bound",
- "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))",
+ "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
@@ -184,7 +184,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
"MetricName": "tma_decode",
- "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
},
@@ -193,7 +193,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
"MetricName": "tma_fast_nuke",
- "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+ "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
},
@@ -203,7 +203,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "Default;TopdownL1;tma_L1_group",
"MetricName": "tma_frontend_bound",
- "MetricThreshold": "(tma_frontend_bound >0.20)",
+ "MetricThreshold": "tma_frontend_bound > 0.2",
"MetricgroupNoGroup": "TopdownL1;Default",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
@@ -213,7 +213,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
"MetricName": "tma_icache_misses",
- "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
},
@@ -222,7 +222,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
"MetricName": "tma_ifetch_bandwidth",
- "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))",
+ "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
@@ -232,7 +232,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
"MetricName": "tma_ifetch_latency",
- "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))",
+ "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
@@ -567,7 +567,7 @@
"BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
"MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@ / cpu_atom@CPU_CLK_UNHALTED.CORE@",
"MetricName": "tma_info_system_mux",
- "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))",
+ "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9",
"Unit": "cpu_atom"
},
{
@@ -606,7 +606,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
"MetricName": "tma_itlb_misses",
- "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
},
@@ -615,7 +615,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
"MetricName": "tma_machine_clears",
- "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))",
+ "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
@@ -625,7 +625,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
"MetricName": "tma_mem_scheduler",
- "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+ "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
},
@@ -634,7 +634,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
"MetricName": "tma_non_mem_scheduler",
- "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+ "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
},
@@ -643,7 +643,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
"MetricName": "tma_nuke",
- "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+ "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
},
@@ -652,7 +652,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
"MetricName": "tma_other_fb",
- "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
},
@@ -661,7 +661,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
"MetricName": "tma_predecode",
- "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
},
@@ -670,7 +670,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
"MetricName": "tma_register",
- "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+ "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
},
@@ -679,7 +679,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
"MetricName": "tma_reorder_buffer",
- "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+ "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
},
@@ -688,7 +688,7 @@
"MetricExpr": "tma_backend_bound - tma_core_bound",
"MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
"MetricName": "tma_resource_bound",
- "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))",
+ "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
@@ -699,7 +699,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "Default;TopdownL1;tma_L1_group",
"MetricName": "tma_retiring",
- "MetricThreshold": "(tma_retiring >0.75)",
+ "MetricThreshold": "tma_retiring > 0.75",
"MetricgroupNoGroup": "TopdownL1;Default",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
@@ -709,7 +709,7 @@
"MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
"MetricName": "tma_serialization",
- "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+ "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
"ScaleUnit": "100%",
"Unit": "cpu_atom"
},
@@ -721,7 +721,7 @@
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+ "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
"MetricExpr": "(cpu_core@UOPS_DISPATCHED.PORT_0@ + cpu_core@UOPS_DISPATCHED.PORT_1@ + cpu_core@UOPS_DISPATCHED.PORT_5_11@ + cpu_core@UOPS_DISPATCHED.PORT_6@) / (5 * tma_info_core_core_clks)",
"MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
"MetricName": "tma_alu_op_utilization",
@@ -734,13 +734,13 @@
"MetricExpr": "78 * cpu_core@xxxxxxxxxxx@ / tma_info_thread_slots",
"MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
"MetricName": "tma_assists",
- "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+ "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
"PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists",
+ "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.",
"MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots",
"MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
"MetricName": "tma_avx_assists",
@@ -751,7 +751,7 @@
{
"BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
"DefaultMetricgroupName": "TopdownL1",
- "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
"MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group",
"MetricName": "tma_backend_bound",
"MetricThreshold": "tma_backend_bound > 0.2",
@@ -768,13 +768,13 @@
"MetricName": "tma_bad_speculation",
"MetricThreshold": "tma_bad_speculation > 0.15",
"MetricgroupNoGroup": "TopdownL1;Default",
- "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",
+ "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.",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
"BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
- "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+ "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
"MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
"MetricName": "tma_bottleneck_big_code",
"MetricThreshold": "tma_bottleneck_big_code > 20",
@@ -791,7 +791,7 @@
},
{
"BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
- "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
"MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
"MetricName": "tma_bottleneck_cache_memory_bandwidth",
"MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -800,7 +800,7 @@
},
{
"BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
- "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
"MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
"MetricName": "tma_bottleneck_cache_memory_latency",
"MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -809,16 +809,16 @@
},
{
"BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
- "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+ "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
"MetricGroup": "BvCB;Cor;tma_issueComp",
"MetricName": "tma_bottleneck_compute_bound_est",
"MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
- "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy",
+ "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ",
"Unit": "cpu_core"
},
{
"BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
- "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code",
+ "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / 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) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code",
"MetricGroup": "BvFB;Fed;FetchBW;Frontend",
"MetricName": "tma_bottleneck_instruction_fetch_bw",
"MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20",
@@ -826,7 +826,7 @@
},
{
"BriefDescription": "Total pipeline cost of irregular execution (e.g",
- "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+ "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
"MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
"MetricName": "tma_bottleneck_irregular_overhead",
"MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -835,7 +835,7 @@
},
{
"BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
- "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
"MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
"MetricName": "tma_bottleneck_memory_data_tlbs",
"MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -844,16 +844,16 @@
},
{
"BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
- "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
"MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
"MetricName": "tma_bottleneck_memory_synchronization",
"MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
- "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+ "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
"Unit": "cpu_core"
},
{
"BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
- "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+ "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (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))",
"MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
"MetricName": "tma_bottleneck_mispredictions",
"MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -866,11 +866,11 @@
"MetricGroup": "BvOB;Cor;Offcore",
"MetricName": "tma_bottleneck_other_bottlenecks",
"MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
- "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls",
+ "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls.",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+ "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
"MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
"MetricGroup": "BvUW;Ret",
"MetricName": "tma_bottleneck_useful_work",
@@ -879,7 +879,7 @@
},
{
"BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
- "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
"MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
"MetricName": "tma_branch_mispredicts",
"MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
@@ -893,26 +893,26 @@
"MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches",
"MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
"MetricName": "tma_branch_resteers",
- "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
- "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+ "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)",
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).",
"MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks",
"MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
"MetricName": "tma_c01_wait",
- "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)",
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).",
"MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks",
"MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
"MetricName": "tma_c02_wait",
- "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -921,7 +921,7 @@
"MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
"MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
"MetricName": "tma_cisc",
- "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+ "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
"PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -931,26 +931,26 @@
"MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks",
"MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
"MetricName": "tma_clears_resteers",
- "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
"PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
+ "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
"MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)",
"MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
"MetricName": "tma_code_l2_hit",
- "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
+ "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
"MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD@ / tma_info_thread_clks",
"MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
"MetricName": "tma_code_l2_miss",
- "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -959,7 +959,7 @@
"MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
"MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
"MetricName": "tma_code_stlb_hit",
- "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -968,35 +968,36 @@
"MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
"MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
"MetricName": "tma_code_stlb_miss",
- "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
"MetricExpr": "tma_code_stlb_miss * cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)",
"MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
"MetricName": "tma_code_stlb_miss_2m",
- "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
"MetricExpr": "tma_code_stlb_miss * cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)",
"MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
"MetricName": "tma_code_stlb_miss_4k",
- "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
"BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
- "MetricExpr": "((28 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + (27 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+ "MetricConstraint": "NO_GROUP_EVENTS",
+ "MetricExpr": "(25 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + 24 * tma_info_system_core_frequency * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
"MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
"MetricName": "tma_contested_accesses",
- "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
- "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_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+ "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+ "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_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -1007,26 +1008,27 @@
"MetricName": "tma_core_bound",
"MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
"MetricgroupNoGroup": "TopdownL2",
- "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+ "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
"BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
- "MetricExpr": "(27 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+ "MetricConstraint": "NO_GROUP_EVENTS",
+ "MetricExpr": "24 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
"MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
"MetricName": "tma_data_sharing",
- "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
- "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_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears",
+ "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+ "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_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
"BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
- "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+ "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
"MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
"MetricName": "tma_decoder0_alone",
- "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+ "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
"PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -1036,7 +1038,7 @@
"MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks",
"MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
"MetricName": "tma_divider",
- "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
"PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -1046,7 +1048,7 @@
"MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks",
"MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
"MetricName": "tma_dram_bound",
- "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
"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_RETIRED.L3_MISS",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -1057,7 +1059,7 @@
"MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
"MetricName": "tma_dsb",
"MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
- "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+ "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -1066,28 +1068,28 @@
"MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks",
"MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
"MetricName": "tma_dsb_switches",
- "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
- "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+ "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
"BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
- "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks",
+ "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks",
"MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
"MetricName": "tma_dtlb_load",
- "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
- "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+ "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+ "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
"BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
- "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@) / tma_info_core_core_clks",
+ "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@) / tma_info_core_core_clks",
"MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
"MetricName": "tma_dtlb_store",
- "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
- "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+ "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+ "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -1096,8 +1098,8 @@
"MetricExpr": "28 * tma_info_system_core_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks",
"MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
"MetricName": "tma_false_sharing",
- "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
- "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears",
+ "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+ "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -1118,18 +1120,18 @@
"MetricName": "tma_fetch_bandwidth",
"MetricThreshold": "tma_fetch_bandwidth > 0.2",
"MetricgroupNoGroup": "TopdownL2",
- "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+ "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
"BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues",
- "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
+ "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
"MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
"MetricName": "tma_fetch_latency",
"MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
"MetricgroupNoGroup": "TopdownL2",
- "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+ "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -1149,7 +1151,7 @@
"MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
"MetricName": "tma_fp_arith",
"MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
- "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+ "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -1159,16 +1161,16 @@
"MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
"MetricName": "tma_fp_assists",
"MetricThreshold": "tma_fp_assists > 0.1",
- "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+ "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+ "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.",
"MetricExpr": "cpu_core@ARITH.FPDIV_ACTIVE@ / tma_info_thread_clks",
"MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
"MetricName": "tma_fp_divider",
- "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -1177,8 +1179,8 @@
"MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
"MetricName": "tma_fp_scalar",
- "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
- "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+ "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+ "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -1187,8 +1189,8 @@
"MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
"MetricName": "tma_fp_vector",
- "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
- "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+ "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+ "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -1197,8 +1199,8 @@
"MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
"MetricName": "tma_fp_vector_128b",
- "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
- "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+ "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+ "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -1207,41 +1209,41 @@
"MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
"MetricName": "tma_fp_vector_256b",
- "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
- "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+ "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+ "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
"BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
"DefaultMetricgroupName": "TopdownL1",
- "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
+ "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
"MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group",
"MetricName": "tma_frontend_bound",
"MetricThreshold": "tma_frontend_bound > 0.15",
"MetricgroupNoGroup": "TopdownL1;Default",
- "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
"MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
"MetricName": "tma_fused_instructions",
"MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
- "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
- "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
+ "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
"MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
"MetricName": "tma_heavy_operations",
"MetricThreshold": "tma_heavy_operations > 0.1",
"MetricgroupNoGroup": "TopdownL2",
- "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -1250,8 +1252,8 @@
"MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks",
"MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
"MetricName": "tma_icache_misses",
- "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
- "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+ "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -1264,7 +1266,7 @@
"Unit": "cpu_core"
},
{
- "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+ "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
"MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_NTAKEN@",
"MetricGroup": "Bad;BrMispredicts",
"MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
@@ -1272,7 +1274,7 @@
"Unit": "cpu_core"
},
{
- "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)",
+ "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).",
"MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN@",
"MetricGroup": "Bad;BrMispredicts",
"MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
@@ -1280,15 +1282,15 @@
"Unit": "cpu_core"
},
{
- "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+ "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
"MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.INDIRECT@",
"MetricGroup": "Bad;BrMispredicts",
"MetricName": "tma_info_bad_spec_ipmisp_indirect",
- "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000",
+ "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+ "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).",
"MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.RET@",
"MetricGroup": "Bad;BrMispredicts",
"MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -1320,7 +1322,7 @@
},
{
"BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
- "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))",
+ "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))",
"MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
"MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
"MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -1329,7 +1331,7 @@
},
{
"BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
- "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))",
+ "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))",
"MetricGroup": "DSBmiss;Fed;tma_issueFB",
"MetricName": "tma_info_botlnk_l2_dsb_misses",
"MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -1338,10 +1340,11 @@
},
{
"BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
- "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+ "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
"MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
"MetricName": "tma_info_botlnk_l2_ic_misses",
"MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+ "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ",
"Unit": "cpu_core"
},
{
@@ -1412,12 +1415,12 @@
"MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.PORT_0@ + cpu_core@FP_ARITH_DISPATCHED.PORT_1@ + cpu_core@FP_ARITH_DISPATCHED.PORT_5@) / (2 * tma_info_core_core_clks)",
"MetricGroup": "Cor;Flops;HPC",
"MetricName": "tma_info_core_fp_arith_utilization",
- "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)",
+ "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).",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
- "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+ "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
"MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
"MetricName": "tma_info_core_ilp",
"Unit": "cpu_core"
@@ -1432,22 +1435,22 @@
"Unit": "cpu_core"
},
{
- "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
- "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+ "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+ "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
"MetricGroup": "DSBmiss",
"MetricName": "tma_info_frontend_dsb_switch_cost",
"Unit": "cpu_core"
},
{
"BriefDescription": "Average number of Uops issued by front-end when it issued something",
- "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+ "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
"MetricGroup": "Fed;FetchBW",
"MetricName": "tma_info_frontend_fetch_upc",
"Unit": "cpu_core"
},
{
"BriefDescription": "Average Latency for L1 instruction cache misses",
- "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=0x1\\,edge\\=0x1@",
+ "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
"MetricGroup": "Fed;FetchLat;IcMiss",
"MetricName": "tma_info_frontend_icache_miss_latency",
"Unit": "cpu_core"
@@ -1497,14 +1500,14 @@
},
{
"BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection",
- "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+ "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@",
"MetricGroup": "Fed",
"MetricName": "tma_info_frontend_unknown_branch_cost",
- "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node",
+ "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node.",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Branch instructions per taken branch",
+ "BriefDescription": "Branch instructions per taken branch.",
"MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "tma_info_inst_mix_bptkbranch",
@@ -1524,7 +1527,7 @@
"MetricGroup": "Flops;InsType",
"MetricName": "tma_info_inst_mix_iparith",
"MetricThreshold": "tma_info_inst_mix_iparith < 10",
- "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW",
+ "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW.",
"Unit": "cpu_core"
},
{
@@ -1533,7 +1536,7 @@
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "tma_info_inst_mix_iparith_avx128",
"MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
- "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+ "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
"Unit": "cpu_core"
},
{
@@ -1542,7 +1545,7 @@
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "tma_info_inst_mix_iparith_avx256",
"MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
- "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+ "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
"Unit": "cpu_core"
},
{
@@ -1551,7 +1554,7 @@
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "tma_info_inst_mix_iparith_scalar_dp",
"MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
- "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+ "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
"Unit": "cpu_core"
},
{
@@ -1560,7 +1563,7 @@
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "tma_info_inst_mix_iparith_scalar_sp",
"MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
- "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+ "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
"Unit": "cpu_core"
},
{
@@ -1623,7 +1626,7 @@
"MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
"MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
"MetricName": "tma_info_inst_mix_iptb",
- "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1",
+ "MetricThreshold": "tma_info_inst_mix_iptb < 13",
"PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp",
"Unit": "cpu_core"
},
@@ -1769,7 +1772,7 @@
},
{
"BriefDescription": "Average Parallel L2 cache miss demand Loads",
- "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+ "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
"MetricGroup": "Memory_BW;Offcore",
"MetricName": "tma_info_memory_latency_load_l2_mlp",
"Unit": "cpu_core"
@@ -1849,7 +1852,7 @@
},
{
"BriefDescription": "",
- "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+ "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
"MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
"MetricName": "tma_info_pipeline_execute",
"Unit": "cpu_core"
@@ -1880,20 +1883,20 @@
"MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@xxxxxxxxxxx@",
"MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
"MetricName": "tma_info_pipeline_ipassist",
- "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+ "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
"PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
- "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+ "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+ "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
"MetricGroup": "Pipeline;Ret",
"MetricName": "tma_info_pipeline_retire",
"Unit": "cpu_core"
},
{
"BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
- "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+ "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
"MetricGroup": "MicroSeq;Pipeline;Ret",
"MetricName": "tma_info_pipeline_strings_cycles",
"MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1",
@@ -1946,23 +1949,22 @@
},
{
"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": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.FAR_BRANCH:u",
+ "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
"MetricGroup": "Branches;OS",
"MetricName": "tma_info_system_ipfarbranch",
- "MetricThreshold": "tma_info_system_ipfarbranch < 1000000",
+ "MetricThreshold": "tma_info_system_ipfarbranch < 1e6",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
- "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
+ "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@INST_RETIRED.ANY_P@k",
"MetricGroup": "OS",
"MetricName": "tma_info_system_kernel_cpi",
- "ScaleUnit": "1per_instr",
"Unit": "cpu_core"
},
{
"BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
- "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@CPU_CLK_UNHALTED.THREAD@",
+ "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@CPU_CLK_UNHALTED.THREAD@",
"MetricGroup": "OS",
"MetricName": "tma_info_system_kernel_utilization",
"MetricThreshold": "tma_info_system_kernel_utilization > 0.05",
@@ -2030,7 +2032,7 @@
"Unit": "cpu_core"
},
{
- "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+ "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
"MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@",
"MetricGroup": "Pipeline",
"MetricName": "tma_info_thread_clks",
@@ -2041,7 +2043,6 @@
"MetricExpr": "1 / tma_info_thread_ipc",
"MetricGroup": "Mem;Pipeline",
"MetricName": "tma_info_thread_cpi",
- "ScaleUnit": "1per_instr",
"Unit": "cpu_core"
},
{
@@ -2049,7 +2050,7 @@
"MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_ISSUED.ANY@",
"MetricGroup": "Cor;Pipeline",
"MetricName": "tma_info_thread_execute_per_issue",
- "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage",
+ "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.",
"Unit": "cpu_core"
},
{
@@ -2061,14 +2062,14 @@
},
{
"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
- "MetricExpr": "slots",
+ "MetricExpr": "cpu_core@TOPDOWN.SLOTS@",
"MetricGroup": "TmaL1;tma_L1_group",
"MetricName": "tma_info_thread_slots",
"Unit": "cpu_core"
},
{
"BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
- "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)",
+ "MetricExpr": "(tma_info_thread_slots / (cpu_core@TOPDOWN.SLOTS@ / 2) if #SMT_on else 1)",
"MetricGroup": "SMT;TmaL1;tma_L1_group",
"MetricName": "tma_info_thread_slots_utilization",
"Unit": "cpu_core"
@@ -2086,15 +2087,15 @@
"MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
"MetricGroup": "Branches;Fed;FetchBW",
"MetricName": "tma_info_thread_uptb",
- "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5",
+ "MetricThreshold": "tma_info_thread_uptb < 9",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+ "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.",
"MetricExpr": "tma_divider - tma_fp_divider",
"MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
"MetricName": "tma_int_divider",
- "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2104,7 +2105,7 @@
"MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
"MetricName": "tma_int_operations",
"MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6",
- "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain",
+ "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2113,8 +2114,8 @@
"MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@) / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
"MetricName": "tma_int_vector_128b",
- "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
- "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+ "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+ "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2123,8 +2124,8 @@
"MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
"MetricName": "tma_int_vector_256b",
- "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
- "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+ "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+ "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2133,8 +2134,8 @@
"MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks",
"MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
"MetricName": "tma_itlb_misses",
- "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
- "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+ "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2143,7 +2144,7 @@
"MetricExpr": "max((cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@) / tma_info_thread_clks, 0)",
"MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
"MetricName": "tma_l1_bound",
- "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
"PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -2153,7 +2154,7 @@
"MetricExpr": "min(2 * (cpu_core@MEM_INST_RETIRED.ALL_LOADS@ - cpu_core@MEM_LOAD_RETIRED.FB_HIT@ - cpu_core@MEM_LOAD_RETIRED.L1_MISS@) * 20 / 100, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks",
"MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
"MetricName": "tma_l1_latency_dependency",
- "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
"PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -2163,17 +2164,18 @@
"MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@) / tma_info_thread_clks",
"MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
"MetricName": "tma_l2_bound",
- "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
"PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
"BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)",
+ "MetricConstraint": "NO_GROUP_EVENTS",
"MetricExpr": "3 * tma_info_system_core_frequency * cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
"MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
"MetricName": "tma_l2_hit_latency",
- "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
"PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -2183,18 +2185,19 @@
"MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks",
"MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
"MetricName": "tma_l3_bound",
- "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
- "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_RETIRED.L3_HIT",
+ "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+ "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_RETIRED.L3_HIT_PS",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
"BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
- "MetricExpr": "(12 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * (cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2)) / tma_info_thread_clks",
+ "MetricConstraint": "NO_GROUP_EVENTS",
+ "MetricExpr": "9 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2)) / tma_info_thread_clks",
"MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
"MetricName": "tma_l3_hit_latency",
- "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
- "PublicDescription": "This metric estimates 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_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+ "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+ "PublicDescription": "This metric estimates 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_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2203,19 +2206,19 @@
"MetricExpr": "cpu_core@xxxxxxxxxx@ / tma_info_thread_clks",
"MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
"MetricName": "tma_lcp",
- "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
- "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+ "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+ "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
"MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
"MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
"MetricName": "tma_light_operations",
"MetricThreshold": "tma_light_operations > 0.6",
"MetricgroupNoGroup": "TopdownL2",
- "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2234,7 +2237,7 @@
"MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
"MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
"MetricName": "tma_load_stlb_hit",
- "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2243,34 +2246,34 @@
"MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
"MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
"MetricName": "tma_load_stlb_miss",
- "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
"MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
"MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
"MetricName": "tma_load_stlb_miss_1g",
- "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
"MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
"MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
"MetricName": "tma_load_stlb_miss_2m",
- "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
"MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
"MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
"MetricName": "tma_load_stlb_miss_4k",
- "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2279,7 +2282,7 @@
"MetricExpr": "(16 * max(0, cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ - cpu_core@L2_RQSTS.ALL_RFO@) + cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@ * (10 * cpu_core@L2_RQSTS.RFO_HIT@ + min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@))) / tma_info_thread_clks",
"MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
"MetricName": "tma_lock_latency",
- "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
"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_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -2290,7 +2293,7 @@
"MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
"MetricName": "tma_lsd",
"MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2",
- "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure",
+ "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2301,16 +2304,16 @@
"MetricName": "tma_machine_clears",
"MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
"MetricgroupNoGroup": "TopdownL2",
- "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+ "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
"BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
- "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+ "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
"MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
"MetricName": "tma_mem_bandwidth",
- "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
"PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -2320,34 +2323,34 @@
"MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth",
"MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
"MetricName": "tma_mem_latency",
- "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
"PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
"BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
- "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
"MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
"MetricName": "tma_memory_bound",
"MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
"MetricgroupNoGroup": "TopdownL2",
- "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)",
+ "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).",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions",
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
"MetricConstraint": "NO_GROUP_EVENTS_NMI",
"MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks",
"MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
"MetricName": "tma_memory_fence",
- "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
"MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
"MetricName": "tma_memory_operations",
@@ -2370,7 +2373,7 @@
"MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks",
"MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
"MetricName": "tma_mispredicts_resteers",
- "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
"PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -2386,18 +2389,18 @@
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+ "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
"MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_clks",
"MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
"MetricName": "tma_mixing_vectors",
"MetricThreshold": "tma_mixing_vectors > 0.05",
- "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+ "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
- "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2",
+ "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.",
+ "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2",
"MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
"MetricName": "tma_ms",
"MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2",
@@ -2406,10 +2409,10 @@
},
{
"BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)",
- "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks",
+ "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks",
"MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
"MetricName": "tma_ms_switches",
- "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
"PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -2420,7 +2423,7 @@
"MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
"MetricName": "tma_non_fused_branches",
"MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
- "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2429,7 +2432,7 @@
"MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
"MetricName": "tma_nop_instructions",
- "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+ "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
"PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -2445,20 +2448,20 @@
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+ "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
"MetricExpr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MISC.CLEARS_COUNT@ - cpu_core@MACHINE_CLEARS.COUNT@)), 0.0001)",
"MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
"MetricName": "tma_other_mispredicts",
- "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+ "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
"MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@MACHINE_CLEARS.COUNT@), 0.0001)",
"MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
"MetricName": "tma_other_nukes",
- "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+ "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2468,7 +2471,7 @@
"MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group",
"MetricName": "tma_page_faults",
"MetricThreshold": "tma_page_faults > 0.05",
- "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost",
+ "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2478,7 +2481,7 @@
"MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
"MetricName": "tma_port_0",
"MetricThreshold": "tma_port_0 > 0.6",
- "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2",
+ "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2488,7 +2491,7 @@
"MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
"MetricName": "tma_port_1",
"MetricThreshold": "tma_port_1 > 0.6",
- "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2",
+ "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2498,7 +2501,7 @@
"MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
"MetricName": "tma_port_6",
"MetricThreshold": "tma_port_6 > 0.6",
- "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2",
+ "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2507,8 +2510,8 @@
"MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)",
"MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
"MetricName": "tma_ports_utilization",
- "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
- "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",
+ "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+ "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.",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2517,8 +2520,8 @@
"MetricExpr": "(cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + max(cpu_core@RS.EMPTY_RESOURCE@ - cpu_core@RESOURCE_STALLS.SCOREBOARD@, 0)) / tma_info_thread_clks * (cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@) / tma_info_thread_clks",
"MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
"MetricName": "tma_ports_utilized_0",
- "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
- "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",
+ "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+ "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.",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2527,7 +2530,7 @@
"MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks",
"MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
"MetricName": "tma_ports_utilized_1",
- "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
"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. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -2538,8 +2541,8 @@
"MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks",
"MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
"MetricName": "tma_ports_utilized_2",
- "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
- "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. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6",
+ "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+ "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. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2549,7 +2552,7 @@
"MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks",
"MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
"MetricName": "tma_ports_utilized_3m",
- "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
"PublicDescription": "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). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -2557,7 +2560,7 @@
{
"BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
"DefaultMetricgroupName": "TopdownL1",
- "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
"MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
"MetricName": "tma_retiring",
"MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -2571,7 +2574,7 @@
"MetricExpr": "cpu_core@RESOURCE_STALLS.SCOREBOARD@ / tma_info_thread_clks + tma_c02_wait",
"MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
"MetricName": "tma_serializing_operation",
- "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
"PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -2581,8 +2584,8 @@
"MetricExpr": "tma_light_operations * cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
"MetricName": "tma_shuffles_256b",
- "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
- "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers",
+ "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2592,7 +2595,7 @@
"MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks",
"MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
"MetricName": "tma_slow_pause",
- "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
"PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -2603,7 +2606,7 @@
"MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
"MetricName": "tma_split_loads",
"MetricThreshold": "tma_split_loads > 0.3",
- "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+ "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2612,8 +2615,8 @@
"MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ / tma_info_core_core_clks",
"MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
"MetricName": "tma_split_stores",
- "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
- "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+ "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+ "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2622,7 +2625,7 @@
"MetricExpr": "(cpu_core@XQ.FULL_CYCLES@ + cpu_core@L1D_PEND_MISS.L2_STALLS@) / tma_info_thread_clks",
"MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
"MetricName": "tma_sq_full",
- "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
"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). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -2632,8 +2635,8 @@
"MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks",
"MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
"MetricName": "tma_store_bound",
- "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
- "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+ "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+ "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2642,8 +2645,8 @@
"MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks",
"MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
"MetricName": "tma_store_fwd_blk",
- "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
- "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+ "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+ "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2652,8 +2655,8 @@
"MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks",
"MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
"MetricName": "tma_store_latency",
- "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
- "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). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+ "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+ "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). Related metrics: tma_fb_full, tma_lock_latency",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2672,7 +2675,7 @@
"MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
"MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
"MetricName": "tma_store_stlb_hit",
- "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2681,34 +2684,34 @@
"MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_core_core_clks",
"MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
"MetricName": "tma_store_stlb_miss",
- "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
"MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
"MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
"MetricName": "tma_store_stlb_miss_1g",
- "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
"MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
"MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
"MetricName": "tma_store_stlb_miss_2m",
- "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
"MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
"MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
"MetricName": "tma_store_stlb_miss_4k",
- "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
"ScaleUnit": "100%",
"Unit": "cpu_core"
},
@@ -2717,7 +2720,7 @@
"MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_clks",
"MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
"MetricName": "tma_streaming_stores",
- "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
"PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -2727,7 +2730,7 @@
"MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks",
"MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
"MetricName": "tma_unknown_branches",
- "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
"PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
"ScaleUnit": "100%",
"Unit": "cpu_core"
@@ -2737,8 +2740,8 @@
"MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / cpu_core@UOPS_EXECUTED.THREAD@",
"MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
"MetricName": "tma_x87_use",
- "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
- "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+ "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+ "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
"ScaleUnit": "100%",
"Unit": "cpu_core"
}
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/cache.json b/tools/perf/pmu-events/arch/x86/alderlake/cache.json
index a20e19738046..c2802fbb853b 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/cache.json
@@ -4,6 +4,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x51",
"EventName": "L1D.HWPF_MISS",
+ "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -13,7 +14,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x51",
"EventName": "L1D.REPLACEMENT",
- "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
+ "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -23,7 +24,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.FB_FULL",
- "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+ "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -35,7 +36,7 @@
"EdgeDetect": "1",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.FB_FULL_PERIODS",
- "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+ "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -46,6 +47,7 @@
"Deprecated": "1",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.L2_STALL",
+ "PublicDescription": "This event is deprecated. Refer to new event L1D_PEND_MISS.L2_STALLS Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -55,7 +57,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.L2_STALLS",
- "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+ "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -65,7 +67,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.PENDING",
- "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+ "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -76,7 +78,7 @@
"CounterMask": "1",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.PENDING_CYCLES",
- "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+ "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -86,7 +88,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x25",
"EventName": "L2_LINES_IN.ALL",
- "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
+ "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1f",
"Unit": "cpu_core"
@@ -96,7 +98,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x26",
"EventName": "L2_LINES_OUT.NON_SILENT",
- "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
+ "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -106,7 +108,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x26",
"EventName": "L2_LINES_OUT.SILENT",
- "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.",
+ "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -116,7 +118,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x26",
"EventName": "L2_LINES_OUT.USELESS_HWPF",
- "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache",
+ "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -135,7 +137,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_REQUEST.ALL",
- "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]",
+ "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xff",
"Unit": "cpu_core"
@@ -165,7 +167,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_REQUEST.MISS",
- "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]",
+ "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x3f",
"Unit": "cpu_core"
@@ -175,7 +177,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_CODE_RD",
- "PublicDescription": "Counts the total number of L2 code requests.",
+ "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xe4",
"Unit": "cpu_core"
@@ -185,7 +187,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
- "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.",
+ "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xe1",
"Unit": "cpu_core"
@@ -195,7 +197,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_DEMAND_MISS",
- "PublicDescription": "Counts demand requests that miss L2 cache.",
+ "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x27",
"Unit": "cpu_core"
@@ -205,6 +207,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_HWPF",
+ "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xf0",
"Unit": "cpu_core"
@@ -214,7 +217,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_RFO",
- "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
+ "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xe2",
"Unit": "cpu_core"
@@ -224,7 +227,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.CODE_RD_HIT",
- "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
+ "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xc4",
"Unit": "cpu_core"
@@ -234,7 +237,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.CODE_RD_MISS",
- "PublicDescription": "Counts L2 cache misses when fetching instructions.",
+ "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x24",
"Unit": "cpu_core"
@@ -244,7 +247,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
- "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
+ "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xc1",
"Unit": "cpu_core"
@@ -254,7 +257,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
- "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.",
+ "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x21",
"Unit": "cpu_core"
@@ -264,6 +267,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.HWPF_MISS",
+ "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x30",
"Unit": "cpu_core"
@@ -273,7 +277,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.MISS",
- "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]",
+ "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x3f",
"Unit": "cpu_core"
@@ -283,7 +287,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.REFERENCES",
- "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]",
+ "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xff",
"Unit": "cpu_core"
@@ -293,7 +297,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.RFO_HIT",
- "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
+ "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xc2",
"Unit": "cpu_core"
@@ -303,7 +307,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.RFO_MISS",
- "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
+ "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x22",
"Unit": "cpu_core"
@@ -313,7 +317,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.SWPF_HIT",
- "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+ "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xc8",
"Unit": "cpu_core"
@@ -323,7 +327,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.SWPF_MISS",
- "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+ "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x28",
"Unit": "cpu_core"
@@ -333,7 +337,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x23",
"EventName": "L2_TRANS.L2_WB",
- "PublicDescription": "Counts L2 writebacks that access L2 cache.",
+ "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x40",
"Unit": "cpu_core"
@@ -353,7 +357,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x2e",
"EventName": "LONGEST_LAT_CACHE.MISS",
- "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+ "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x41",
"Unit": "cpu_core"
@@ -373,7 +377,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x2e",
"EventName": "LONGEST_LAT_CACHE.REFERENCE",
- "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+ "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x4f",
"Unit": "cpu_core"
@@ -461,7 +465,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.ALL_LOADS",
- "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
+ "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x81",
"Unit": "cpu_core"
@@ -472,7 +476,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.ALL_STORES",
- "PublicDescription": "Counts all retired store instructions.",
+ "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x82",
"Unit": "cpu_core"
@@ -483,7 +487,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.ANY",
- "PublicDescription": "Counts all retired memory instructions - loads and stores.",
+ "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x83",
"Unit": "cpu_core"
@@ -494,7 +498,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.LOCK_LOADS",
- "PublicDescription": "Counts retired load instructions with locked access.",
+ "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x21",
"Unit": "cpu_core"
@@ -505,7 +509,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
- "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
+ "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x41",
"Unit": "cpu_core"
@@ -516,7 +520,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.SPLIT_STORES",
- "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
+ "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x42",
"Unit": "cpu_core"
@@ -527,7 +531,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
- "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
+ "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x11",
"Unit": "cpu_core"
@@ -538,7 +542,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
- "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
+ "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x12",
"Unit": "cpu_core"
@@ -548,7 +552,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x43",
"EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY",
- "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)",
+ "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0xfd",
"Unit": "cpu_core"
@@ -559,7 +563,7 @@
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
- "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
+ "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0",
"SampleAfterValue": "20011",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -570,7 +574,7 @@
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT",
- "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+ "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0",
"SampleAfterValue": "20011",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -581,7 +585,7 @@
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
- "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
+ "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0",
"SampleAfterValue": "20011",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -592,7 +596,7 @@
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
- "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+ "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0",
"SampleAfterValue": "20011",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -603,7 +607,7 @@
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
- "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
+ "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -614,7 +618,7 @@
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
- "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+ "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0",
"SampleAfterValue": "20011",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -625,7 +629,7 @@
"Data_LA": "1",
"EventCode": "0xd3",
"EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
- "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
+ "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -636,7 +640,7 @@
"Data_LA": "1",
"EventCode": "0xd4",
"EventName": "MEM_LOAD_MISC_RETIRED.UC",
- "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
+ "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -647,7 +651,7 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.FB_HIT",
- "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
+ "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x40",
"Unit": "cpu_core"
@@ -658,7 +662,7 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L1_HIT",
- "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+ "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -669,7 +673,7 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L1_MISS",
- "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+ "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -680,7 +684,7 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L2_HIT",
- "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
+ "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -691,7 +695,7 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L2_MISS",
- "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
+ "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0",
"SampleAfterValue": "100021",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -702,7 +706,7 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L3_HIT",
- "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
+ "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0",
"SampleAfterValue": "100021",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -713,7 +717,7 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L3_MISS",
- "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
+ "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0",
"SampleAfterValue": "50021",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -724,6 +728,7 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
+ "PublicDescription": "Counts the number of load uops retired that hit in DRAM. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x80",
"Unit": "cpu_atom"
@@ -734,6 +739,7 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
+ "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required and modified data was forwarded from another core or module. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x20",
"Unit": "cpu_atom"
@@ -744,6 +750,7 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
+ "PublicDescription": "Counts the number of load uops retired that hit in the L1 data cache. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -754,6 +761,7 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
+ "PublicDescription": "Counts the number of load uops retired that miss in the L1 data cache. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x8",
"Unit": "cpu_atom"
@@ -764,6 +772,7 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
+ "PublicDescription": "Counts the number of load uops retired that hit in the L2 cache. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x2",
"Unit": "cpu_atom"
@@ -774,6 +783,7 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
+ "PublicDescription": "Counts the number of load uops retired that miss in the L2 cache. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x10",
"Unit": "cpu_atom"
@@ -784,6 +794,7 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
+ "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x4",
"Unit": "cpu_atom"
@@ -794,6 +805,7 @@
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_UOPS_RETIRED_MISC.HIT_E_F",
+ "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required, and non-modified data was forwarded. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x40",
"Unit": "cpu_atom"
@@ -804,6 +816,7 @@
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_UOPS_RETIRED_MISC.L3_MISS",
+ "PublicDescription": "Counts the number of load uops retired that miss in the L3 cache. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_atom"
@@ -849,6 +862,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x44",
"EventName": "MEM_STORE_RETIRED.L2_HIT",
+ "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -859,7 +873,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
- "PublicDescription": "Counts the total number of load uops retired.",
+ "PublicDescription": "Counts the total number of load uops retired. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x81",
"Unit": "cpu_atom"
@@ -870,7 +884,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.ALL_STORES",
- "PublicDescription": "Counts the total number of store uops retired.",
+ "PublicDescription": "Counts the total number of store uops retired. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x82",
"Unit": "cpu_atom"
@@ -883,7 +897,7 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"MSRValue": "0x80",
- "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+ "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -896,7 +910,7 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"MSRValue": "0x10",
- "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+ "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -909,7 +923,7 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"MSRValue": "0x100",
- "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+ "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -922,7 +936,7 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"MSRValue": "0x20",
- "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+ "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -935,7 +949,7 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"MSRValue": "0x4",
- "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+ "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -948,7 +962,7 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"MSRValue": "0x200",
- "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+ "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -961,7 +975,7 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"MSRValue": "0x40",
- "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+ "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -974,7 +988,7 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"MSRValue": "0x8",
- "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+ "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -985,6 +999,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
+ "PublicDescription": "Counts the number of load uops retired that performed one or more locks. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x21",
"Unit": "cpu_atom"
@@ -995,6 +1010,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
+ "PublicDescription": "Counts the number of retired split load uops. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x41",
"Unit": "cpu_atom"
@@ -1005,6 +1021,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.STLB_MISS",
+ "PublicDescription": "Counts the total number of load and store uops retired that missed in the second level TLB. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x13",
"Unit": "cpu_atom"
@@ -1015,6 +1032,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
+ "PublicDescription": "Counts the number of load ops retired that miss in the second Level TLB. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x11",
"Unit": "cpu_atom"
@@ -1025,6 +1043,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
+ "PublicDescription": "Counts the number of store ops retired that miss in the second level TLB. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x12",
"Unit": "cpu_atom"
@@ -1035,7 +1054,7 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.STORE_LATENCY",
- "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly.",
+ "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x6",
"Unit": "cpu_atom"
@@ -1045,11 +1064,35 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe5",
"EventName": "MEM_UOP_RETIRED.ANY",
- "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses",
+ "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x3",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.COREWB_M.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10008",
+ "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response. Available PDIST counters: 0",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10004",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache.",
"Counter": "0,1,2,3,4,5",
@@ -1057,6 +1100,7 @@
"EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1F803C0004",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1068,6 +1112,7 @@
"EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0004",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1079,6 +1124,7 @@
"EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x4003C0004",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1090,10 +1136,35 @@
"EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x8003C0004",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts demand data reads that have any type of response.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10001",
+ "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts demand data reads that have any type of response.",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2A,0x2B",
+ "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10001",
+ "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
{
"BriefDescription": "Counts demand data reads that were supplied by the L3 cache.",
"Counter": "0,1,2,3,4,5",
@@ -1101,6 +1172,7 @@
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1F803C0001",
+ "PublicDescription": "Counts demand data reads that were supplied by the L3 cache. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1112,6 +1184,7 @@
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0001",
+ "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1123,6 +1196,7 @@
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0001",
+ "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1134,6 +1208,7 @@
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x4003C0001",
+ "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1145,6 +1220,7 @@
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x8003C0001",
+ "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1156,6 +1232,31 @@
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x8003C0001",
+ "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10002",
+ "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2A,0x2B",
+ "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10002",
+ "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1167,6 +1268,7 @@
"EventName": "OCR.DEMAND_RFO.L3_HIT",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1F803C0002",
+ "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1178,6 +1280,7 @@
"EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0002",
+ "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1189,6 +1292,7 @@
"EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0002",
+ "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1200,6 +1304,7 @@
"EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x4003C0002",
+ "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1211,6 +1316,19 @@
"EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x8003C0002",
+ "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.SWPF_RD.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x14000",
+ "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1222,6 +1340,7 @@
"EventName": "OCR.SWPF_RD.L3_HIT",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1F803C4000",
+ "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1233,6 +1352,7 @@
"EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C4000",
+ "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1244,6 +1364,7 @@
"EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x4003C4000",
+ "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1255,6 +1376,7 @@
"EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x8003C4000",
+ "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1264,6 +1386,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
+ "PublicDescription": "OFFCORE_REQUESTS.ALL_REQUESTS Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x80",
"Unit": "cpu_core"
@@ -1273,7 +1396,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.DATA_RD",
- "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+ "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -1283,7 +1406,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
- "PublicDescription": "Counts both cacheable and non-cacheable code read requests.",
+ "PublicDescription": "Counts both cacheable and non-cacheable code read requests. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -1293,7 +1416,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
- "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
+ "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1303,7 +1426,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
- "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
+ "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -1315,6 +1438,7 @@
"Errata": "ADL038",
"EventCode": "0x20",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+ "PublicDescription": "This event is deprecated. Refer to new event OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -1326,6 +1450,7 @@
"Errata": "ADL038",
"EventCode": "0x20",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+ "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -1336,7 +1461,7 @@
"CounterMask": "1",
"EventCode": "0x20",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
- "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+ "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -1347,6 +1472,7 @@
"CounterMask": "1",
"EventCode": "0x20",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+ "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1357,7 +1483,7 @@
"CounterMask": "1",
"EventCode": "0x20",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
- "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+ "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -1368,6 +1494,7 @@
"Errata": "ADL038",
"EventCode": "0x20",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD",
+ "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -1377,7 +1504,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x20",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
- "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+ "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -1387,7 +1514,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x20",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
- "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
+ "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1397,7 +1524,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x2c",
"EventName": "SQ_MISC.BUS_LOCK",
- "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
+ "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -1407,6 +1534,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x40",
"EventName": "SW_PREFETCH_ACCESS.ANY",
+ "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0xf",
"Unit": "cpu_core"
@@ -1416,7 +1544,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x40",
"EventName": "SW_PREFETCH_ACCESS.NTA",
- "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
+ "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1426,7 +1554,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x40",
"EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
- "PublicDescription": "Counts the number of PREFETCHW instructions executed.",
+ "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -1436,7 +1564,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x40",
"EventName": "SW_PREFETCH_ACCESS.T0",
- "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
+ "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -1446,7 +1574,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x40",
"EventName": "SW_PREFETCH_ACCESS.T1_T2",
- "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+ "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json b/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json
index 62fd70f220e5..ce570b96360a 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json
@@ -14,6 +14,7 @@
"CounterMask": "1",
"EventCode": "0xb0",
"EventName": "ARITH.FPDIV_ACTIVE",
+ "PublicDescription": "ARITH.FPDIV_ACTIVE Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -32,7 +33,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc1",
"EventName": "ASSISTS.FP",
- "PublicDescription": "Counts all microcode Floating Point assists.",
+ "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -42,6 +43,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc1",
"EventName": "ASSISTS.SSE_AVX_MIX",
+ "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -51,6 +53,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.PORT_0",
+ "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -60,6 +63,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.PORT_1",
+ "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -69,6 +73,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.PORT_5",
+ "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -78,6 +83,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.V0",
+ "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -87,6 +93,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.V1",
+ "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -96,6 +103,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.V2",
+ "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -105,7 +113,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
- "PublicDescription": "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. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "PublicDescription": "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. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -115,7 +123,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
- "PublicDescription": "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 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "PublicDescription": "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 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -125,7 +133,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
- "PublicDescription": "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 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "PublicDescription": "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 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -135,7 +143,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
- "PublicDescription": "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 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "PublicDescription": "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 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -145,7 +153,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
- "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x18",
"Unit": "cpu_core"
@@ -155,7 +163,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR",
- "PublicDescription": "Number of SSE/AVX computational scalar single precision and 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 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 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "PublicDescription": "Number of SSE/AVX computational scalar single precision and 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 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 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x3",
"Unit": "cpu_core"
@@ -165,7 +173,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
- "PublicDescription": "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 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "PublicDescription": "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 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -175,7 +183,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
- "PublicDescription": "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 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "PublicDescription": "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 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -185,7 +193,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.VECTOR",
- "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0xfc",
"Unit": "cpu_core"
@@ -205,6 +213,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.FPDIV",
+ "PublicDescription": "Counts the number of floating point divide uops retired (x87 and SSE, including x87 sqrt). Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_atom"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json
index c5b3818ad479..dae3174a74fb 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json
@@ -14,7 +14,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x60",
"EventName": "BACLEARS.ANY",
- "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+ "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -24,7 +24,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x87",
"EventName": "DECODE.LCP",
- "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
+ "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0",
"SampleAfterValue": "500009",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -34,6 +34,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x87",
"EventName": "DECODE.MS_BUSY",
+ "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0",
"SampleAfterValue": "500009",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -43,7 +44,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x61",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
- "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
+ "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -55,7 +56,7 @@
"EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x1",
- "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+ "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -67,7 +68,7 @@
"EventName": "FRONTEND_RETIRED.DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x11",
- "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
+ "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -79,7 +80,7 @@
"EventName": "FRONTEND_RETIRED.ITLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x14",
- "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+ "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -91,7 +92,7 @@
"EventName": "FRONTEND_RETIRED.L1I_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x12",
- "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
+ "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -103,7 +104,7 @@
"EventName": "FRONTEND_RETIRED.L2_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x13",
- "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
+ "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -115,7 +116,7 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x600106",
- "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
+ "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -127,7 +128,7 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
"MSRIndex": "0x3F7",
"MSRValue": "0x608006",
- "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+ "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -139,7 +140,7 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
"MSRIndex": "0x3F7",
"MSRValue": "0x601006",
- "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -151,7 +152,7 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
"MSRIndex": "0x3F7",
"MSRValue": "0x600206",
- "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
+ "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -163,7 +164,7 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
"MSRIndex": "0x3F7",
"MSRValue": "0x610006",
- "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+ "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -175,7 +176,7 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x100206",
- "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -187,7 +188,7 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
"MSRIndex": "0x3F7",
"MSRValue": "0x602006",
- "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -199,7 +200,7 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
"MSRIndex": "0x3F7",
"MSRValue": "0x600406",
- "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+ "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -211,7 +212,7 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
"MSRIndex": "0x3F7",
"MSRValue": "0x620006",
- "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+ "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -223,7 +224,7 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
"MSRIndex": "0x3F7",
"MSRValue": "0x604006",
- "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+ "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -235,7 +236,7 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
"MSRIndex": "0x3F7",
"MSRValue": "0x600806",
- "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -247,6 +248,7 @@
"EventName": "FRONTEND_RETIRED.MS_FLOWS",
"MSRIndex": "0x3F7",
"MSRValue": "0x8",
+ "PublicDescription": "FRONTEND_RETIRED.MS_FLOWS Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -258,7 +260,7 @@
"EventName": "FRONTEND_RETIRED.STLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x15",
- "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+ "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -270,6 +272,7 @@
"EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
"MSRIndex": "0x3F7",
"MSRValue": "0x17",
+ "PublicDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -299,7 +302,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "ICACHE_DATA.STALLS",
- "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.",
+ "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0",
"SampleAfterValue": "500009",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -311,6 +314,7 @@
"EdgeDetect": "1",
"EventCode": "0x80",
"EventName": "ICACHE_DATA.STALL_PERIODS",
+ "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0",
"SampleAfterValue": "500009",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -320,7 +324,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x83",
"EventName": "ICACHE_TAG.STALLS",
- "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
+ "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -331,7 +335,7 @@
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_ANY",
- "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+ "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -342,7 +346,7 @@
"CounterMask": "6",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_OK",
- "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
+ "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -352,7 +356,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.DSB_UOPS",
- "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+ "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -363,7 +367,7 @@
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_ANY",
- "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+ "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -374,7 +378,7 @@
"CounterMask": "6",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_OK",
- "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+ "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -384,7 +388,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.MITE_UOPS",
- "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+ "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -395,7 +399,7 @@
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_CYCLES_ANY",
- "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+ "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -407,7 +411,7 @@
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_SWITCHES",
- "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+ "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -417,7 +421,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.MS_UOPS",
- "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS).",
+ "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -427,7 +431,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x9c",
"EventName": "IDQ_BUBBLES.CORE",
- "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]",
+ "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE] Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -438,7 +442,7 @@
"CounterMask": "6",
"EventCode": "0x9c",
"EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE",
- "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
+ "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -450,7 +454,7 @@
"EventCode": "0x9c",
"EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK",
"Invert": "1",
- "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
+ "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -460,7 +464,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
- "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]",
+ "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE] Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -471,7 +475,7 @@
"CounterMask": "6",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
- "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
+ "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -483,7 +487,7 @@
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"Invert": "1",
- "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
+ "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/memory.json b/tools/perf/pmu-events/arch/x86/alderlake/memory.json
index fa15f5797bed..07f5786bdbc0 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/memory.json
@@ -5,6 +5,7 @@
"CounterMask": "6",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
+ "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x6",
"Unit": "cpu_core"
@@ -78,7 +79,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
- "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
+ "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -89,6 +90,7 @@
"CounterMask": "2",
"EventCode": "0x47",
"EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS",
+ "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -99,6 +101,7 @@
"CounterMask": "3",
"EventCode": "0x47",
"EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS",
+ "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x3",
"Unit": "cpu_core"
@@ -109,7 +112,7 @@
"CounterMask": "5",
"EventCode": "0x47",
"EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS",
- "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+ "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_core"
@@ -120,7 +123,7 @@
"CounterMask": "9",
"EventCode": "0x47",
"EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS",
- "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+ "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x9",
"Unit": "cpu_core"
@@ -248,11 +251,23 @@
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
- "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8",
+ "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x784000004",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache.",
"Counter": "0,1,2,3,4,5",
@@ -260,10 +275,35 @@
"EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F84400004",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x784000001",
+ "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2A,0x2B",
+ "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x184000001",
+ "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
{
"BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
"Counter": "0,1,2,3,4,5",
@@ -271,6 +311,7 @@
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F84400001",
+ "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -282,6 +323,7 @@
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FBFC00001",
+ "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -293,6 +335,19 @@
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F84400001",
+ "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS] Available PDIST counters: 0",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_RFO.DRAM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x784000002",
+ "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -304,6 +359,7 @@
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F84400002",
+ "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -315,6 +371,7 @@
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FBFC00002",
+ "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -326,6 +383,19 @@
"EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F84400002",
+ "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS] Available PDIST counters: 0",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.SWPF_RD.DRAM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x784004000",
+ "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -337,6 +407,7 @@
"EventName": "OCR.SWPF_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F84404000",
+ "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -346,6 +417,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+ "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -355,7 +427,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x20",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
- "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.",
+ "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x10",
"Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/other.json b/tools/perf/pmu-events/arch/x86/alderlake/other.json
index a8b23e92408c..e4e75b088ccc 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/other.json
@@ -4,7 +4,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc1",
"EventName": "ASSISTS.HARDWARE",
- "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count.",
+ "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -14,6 +14,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc1",
"EventName": "ASSISTS.PAGE_FAULT",
+ "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -23,6 +24,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x28",
"EventName": "CORE_POWER.LICENSE_1",
+ "PublicDescription": "CORE_POWER.LICENSE_1 Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -32,6 +34,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x28",
"EventName": "CORE_POWER.LICENSE_2",
+ "PublicDescription": "CORE_POWER.LICENSE_2 Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -41,6 +44,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x28",
"EventName": "CORE_POWER.LICENSE_3",
+ "PublicDescription": "CORE_POWER.LICENSE_3 Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -51,120 +55,11 @@
"Deprecated": "1",
"EventCode": "0xe4",
"EventName": "LBR_INSERTS.ANY",
+ "PublicDescription": "This event is deprecated. [This event is alias to MISC_RETIRED.LBR_INSERTS] Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
- {
- "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.COREWB_M.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x10008",
- "SampleAfterValue": "100003",
- "UMask": "0x1",
- "Unit": "cpu_atom"
- },
- {
- "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x10004",
- "SampleAfterValue": "100003",
- "UMask": "0x1",
- "Unit": "cpu_atom"
- },
- {
- "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.DEMAND_CODE_RD.DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x784000004",
- "SampleAfterValue": "100003",
- "UMask": "0x1",
- "Unit": "cpu_atom"
- },
- {
- "BriefDescription": "Counts demand data reads that have any type of response.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x10001",
- "SampleAfterValue": "100003",
- "UMask": "0x1",
- "Unit": "cpu_atom"
- },
- {
- "BriefDescription": "Counts demand data reads that have any type of response.",
- "Counter": "0,1,2,3",
- "EventCode": "0x2A,0x2B",
- "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x10001",
- "SampleAfterValue": "100003",
- "UMask": "0x1",
- "Unit": "cpu_core"
- },
- {
- "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.DEMAND_DATA_RD.DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x784000001",
- "SampleAfterValue": "100003",
- "UMask": "0x1",
- "Unit": "cpu_atom"
- },
- {
- "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
- "Counter": "0,1,2,3",
- "EventCode": "0x2A,0x2B",
- "EventName": "OCR.DEMAND_DATA_RD.DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x184000001",
- "SampleAfterValue": "100003",
- "UMask": "0x1",
- "Unit": "cpu_core"
- },
- {
- "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x10002",
- "SampleAfterValue": "100003",
- "UMask": "0x1",
- "Unit": "cpu_atom"
- },
- {
- "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
- "Counter": "0,1,2,3",
- "EventCode": "0x2A,0x2B",
- "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x10002",
- "SampleAfterValue": "100003",
- "UMask": "0x1",
- "Unit": "cpu_core"
- },
- {
- "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.DEMAND_RFO.DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x784000002",
- "SampleAfterValue": "100003",
- "UMask": "0x1",
- "Unit": "cpu_atom"
- },
{
"BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.",
"Counter": "0,1,2,3,4,5",
@@ -172,6 +67,7 @@
"EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x800000010000",
+ "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -183,6 +79,7 @@
"EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x400000010000",
+ "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -194,6 +91,7 @@
"EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10800",
+ "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -205,103 +103,18 @@
"EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10800",
+ "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
- {
- "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.SWPF_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x14000",
- "SampleAfterValue": "100003",
- "UMask": "0x1",
- "Unit": "cpu_atom"
- },
- {
- "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.SWPF_RD.DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x784004000",
- "SampleAfterValue": "100003",
- "UMask": "0x1",
- "Unit": "cpu_atom"
- },
- {
- "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
- "Counter": "0,1,2,3,4,5,6,7",
- "EventCode": "0xa5",
- "EventName": "RS.EMPTY",
- "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
- "SampleAfterValue": "1000003",
- "UMask": "0x7",
- "Unit": "cpu_core"
- },
- {
- "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
- "Counter": "0,1,2,3,4,5,6,7",
- "CounterMask": "1",
- "EdgeDetect": "1",
- "EventCode": "0xa5",
- "EventName": "RS.EMPTY_COUNT",
- "Invert": "1",
- "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
- "SampleAfterValue": "100003",
- "UMask": "0x7",
- "Unit": "cpu_core"
- },
- {
- "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end",
- "Counter": "0,1,2,3,4,5,6,7",
- "EventCode": "0xa5",
- "EventName": "RS.EMPTY_RESOURCE",
- "SampleAfterValue": "1000003",
- "UMask": "0x1",
- "Unit": "cpu_core"
- },
- {
- "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT",
- "Counter": "0,1,2,3,4,5,6,7",
- "CounterMask": "1",
- "Deprecated": "1",
- "EdgeDetect": "1",
- "EventCode": "0xa5",
- "EventName": "RS_EMPTY.COUNT",
- "Invert": "1",
- "SampleAfterValue": "100003",
- "UMask": "0x7",
- "Unit": "cpu_core"
- },
- {
- "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY",
- "Counter": "0,1,2,3,4,5,6,7",
- "Deprecated": "1",
- "EventCode": "0xa5",
- "EventName": "RS_EMPTY.CYCLES",
- "SampleAfterValue": "1000003",
- "UMask": "0x7",
- "Unit": "cpu_core"
- },
- {
- "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0x75",
- "EventName": "SERIALIZATION.C01_MS_SCB",
- "SampleAfterValue": "200003",
- "UMask": "0x4",
- "Unit": "cpu_atom"
- },
{
"BriefDescription": "Cycles the uncore cannot take further requests",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x2d",
"EventName": "XQ.FULL_CYCLES",
- "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).",
+ "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json
index f5bf0816f190..7e0e33792c45 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json
@@ -6,6 +6,7 @@
"Deprecated": "1",
"EventCode": "0xb0",
"EventName": "ARITH.DIVIDER_ACTIVE",
+ "PublicDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x9",
"Unit": "cpu_core"
@@ -26,7 +27,7 @@
"CounterMask": "1",
"EventCode": "0xb0",
"EventName": "ARITH.DIV_ACTIVE",
- "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
+ "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x9",
"Unit": "cpu_core"
@@ -56,6 +57,7 @@
"Deprecated": "1",
"EventCode": "0xb0",
"EventName": "ARITH.FP_DIVIDER_ACTIVE",
+ "PublicDescription": "This event is deprecated. Refer to new event ARITH.FPDIV_ACTIVE Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -76,6 +78,7 @@
"CounterMask": "1",
"EventCode": "0xb0",
"EventName": "ARITH.IDIV_ACTIVE",
+ "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -105,6 +108,7 @@
"Deprecated": "1",
"EventCode": "0xb0",
"EventName": "ARITH.INT_DIVIDER_ACTIVE",
+ "PublicDescription": "This event is deprecated. Refer to new event ARITH.IDIV_ACTIVE Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -114,7 +118,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc1",
"EventName": "ASSISTS.ANY",
- "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.",
+ "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1b",
"Unit": "cpu_core"
@@ -124,7 +128,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.ALL_BRANCHES",
- "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.",
+ "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"Unit": "cpu_atom"
},
@@ -133,7 +137,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.ALL_BRANCHES",
- "PublicDescription": "Counts all branch instructions retired.",
+ "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "400009",
"Unit": "cpu_core"
},
@@ -143,6 +147,7 @@
"Deprecated": "1",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.CALL",
+ "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.NEAR_CALL Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xf9",
"Unit": "cpu_atom"
@@ -152,6 +157,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.COND",
+ "PublicDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x7e",
"Unit": "cpu_atom"
@@ -161,7 +167,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.COND",
- "PublicDescription": "Counts conditional branch instructions retired.",
+ "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "400009",
"UMask": "0x11",
"Unit": "cpu_core"
@@ -171,7 +177,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.COND_NTAKEN",
- "PublicDescription": "Counts not taken branch instructions retired.",
+ "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "400009",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -181,6 +187,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.COND_TAKEN",
+ "PublicDescription": "Counts the number of taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xfe",
"Unit": "cpu_atom"
@@ -190,7 +197,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.COND_TAKEN",
- "PublicDescription": "Counts taken conditional branch instructions retired.",
+ "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "400009",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -200,6 +207,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.FAR_BRANCH",
+ "PublicDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xbf",
"Unit": "cpu_atom"
@@ -209,7 +217,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.FAR_BRANCH",
- "PublicDescription": "Counts far branch instructions retired.",
+ "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x40",
"Unit": "cpu_core"
@@ -219,6 +227,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.INDIRECT",
+ "PublicDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xeb",
"Unit": "cpu_atom"
@@ -228,7 +237,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.INDIRECT",
- "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+ "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x80",
"Unit": "cpu_core"
@@ -238,6 +247,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.INDIRECT_CALL",
+ "PublicDescription": "Counts the number of near indirect CALL branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xfb",
"Unit": "cpu_atom"
@@ -248,6 +258,7 @@
"Deprecated": "1",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.IND_CALL",
+ "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT_CALL Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xfb",
"Unit": "cpu_atom"
@@ -258,6 +269,7 @@
"Deprecated": "1",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.JCC",
+ "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.COND Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x7e",
"Unit": "cpu_atom"
@@ -267,6 +279,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_CALL",
+ "PublicDescription": "Counts the number of near CALL branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xf9",
"Unit": "cpu_atom"
@@ -276,7 +289,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_CALL",
- "PublicDescription": "Counts both direct and indirect near call instructions retired.",
+ "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -286,6 +299,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_RETURN",
+ "PublicDescription": "Counts the number of near RET branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xf7",
"Unit": "cpu_atom"
@@ -295,7 +309,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_RETURN",
- "PublicDescription": "Counts return instructions retired.",
+ "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -305,6 +319,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+ "PublicDescription": "Counts the number of near taken branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xc0",
"Unit": "cpu_atom"
@@ -314,7 +329,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_TAKEN",
- "PublicDescription": "Counts taken branch instructions retired.",
+ "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "400009",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -325,6 +340,7 @@
"Deprecated": "1",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NON_RETURN_IND",
+ "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xeb",
"Unit": "cpu_atom"
@@ -334,6 +350,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.REL_CALL",
+ "PublicDescription": "Counts the number of near relative CALL branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xfd",
"Unit": "cpu_atom"
@@ -344,6 +361,7 @@
"Deprecated": "1",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.RETURN",
+ "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.NEAR_RETURN Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xf7",
"Unit": "cpu_atom"
@@ -354,6 +372,7 @@
"Deprecated": "1",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.TAKEN_JCC",
+ "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.COND_TAKEN Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xfe",
"Unit": "cpu_atom"
@@ -363,7 +382,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
- "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.",
+ "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"Unit": "cpu_atom"
},
@@ -372,7 +391,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
- "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+ "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0",
"SampleAfterValue": "400009",
"Unit": "cpu_core"
},
@@ -381,6 +400,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND",
+ "PublicDescription": "Counts the number of mispredicted JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x7e",
"Unit": "cpu_atom"
@@ -390,7 +410,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND",
- "PublicDescription": "Counts mispredicted conditional branch instructions retired.",
+ "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "400009",
"UMask": "0x11",
"Unit": "cpu_core"
@@ -400,7 +420,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND_NTAKEN",
- "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
+ "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0",
"SampleAfterValue": "400009",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -410,6 +430,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND_TAKEN",
+ "PublicDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xfe",
"Unit": "cpu_atom"
@@ -419,7 +440,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND_TAKEN",
- "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
+ "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "400009",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -429,6 +450,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.INDIRECT",
+ "PublicDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xeb",
"Unit": "cpu_atom"
@@ -438,7 +460,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.INDIRECT",
- "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+ "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x80",
"Unit": "cpu_core"
@@ -448,6 +470,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
+ "PublicDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xfb",
"Unit": "cpu_atom"
@@ -457,7 +480,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
- "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
+ "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0",
"SampleAfterValue": "400009",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -468,6 +491,7 @@
"Deprecated": "1",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.IND_CALL",
+ "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.INDIRECT_CALL Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xfb",
"Unit": "cpu_atom"
@@ -478,6 +502,7 @@
"Deprecated": "1",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.JCC",
+ "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.COND Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x7e",
"Unit": "cpu_atom"
@@ -487,6 +512,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+ "PublicDescription": "Counts the number of mispredicted near taken branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x80",
"Unit": "cpu_atom"
@@ -496,7 +522,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
- "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
+ "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0",
"SampleAfterValue": "400009",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -507,6 +533,7 @@
"Deprecated": "1",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
+ "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.INDIRECT Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xeb",
"Unit": "cpu_atom"
@@ -516,7 +543,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.RET",
- "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
+ "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -526,6 +553,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.RETURN",
+ "PublicDescription": "Counts the number of mispredicted near RET branch instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xf7",
"Unit": "cpu_atom"
@@ -536,6 +564,7 @@
"Deprecated": "1",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.TAKEN_JCC",
+ "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.COND_TAKEN Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0xfe",
"Unit": "cpu_atom"
@@ -545,7 +574,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xec",
"EventName": "CPU_CLK_UNHALTED.C01",
- "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.",
+ "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -555,7 +584,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xec",
"EventName": "CPU_CLK_UNHALTED.C02",
- "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.",
+ "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -565,7 +594,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xec",
"EventName": "CPU_CLK_UNHALTED.C0_WAIT",
- "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.",
+ "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x70",
"Unit": "cpu_core"
@@ -593,7 +622,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xec",
"EventName": "CPU_CLK_UNHALTED.DISTRIBUTED",
- "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+ "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -603,7 +632,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x3c",
"EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
- "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.",
+ "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0",
"SampleAfterValue": "25003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -613,6 +642,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xec",
"EventName": "CPU_CLK_UNHALTED.PAUSE",
+ "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x40",
"Unit": "cpu_core"
@@ -624,6 +654,7 @@
"EdgeDetect": "1",
"EventCode": "0xec",
"EventName": "CPU_CLK_UNHALTED.PAUSE_INST",
+ "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x40",
"Unit": "cpu_core"
@@ -643,7 +674,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x3c",
"EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED",
- "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+ "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -681,7 +712,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x3c",
"EventName": "CPU_CLK_UNHALTED.REF_TSC_P",
- "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+ "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -718,7 +749,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x3c",
"EventName": "CPU_CLK_UNHALTED.THREAD_P",
- "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+ "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"Unit": "cpu_core"
},
@@ -728,6 +759,7 @@
"CounterMask": "8",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+ "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -738,6 +770,7 @@
"CounterMask": "1",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+ "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -748,6 +781,7 @@
"CounterMask": "16",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+ "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -758,6 +792,7 @@
"CounterMask": "12",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+ "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0xc",
"Unit": "cpu_core"
@@ -768,6 +803,7 @@
"CounterMask": "5",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+ "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_core"
@@ -778,6 +814,7 @@
"CounterMask": "4",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+ "PublicDescription": "Total execution stalls. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -787,7 +824,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa6",
"EventName": "EXE_ACTIVITY.1_PORTS_UTIL",
- "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
+ "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -797,6 +834,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa6",
"EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL",
+ "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0xc",
"Unit": "cpu_core"
@@ -806,7 +844,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa6",
"EventName": "EXE_ACTIVITY.2_PORTS_UTIL",
- "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
+ "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -816,7 +854,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa6",
"EventName": "EXE_ACTIVITY.3_PORTS_UTIL",
- "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
+ "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -826,7 +864,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa6",
"EventName": "EXE_ACTIVITY.4_PORTS_UTIL",
- "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
+ "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -837,6 +875,7 @@
"CounterMask": "5",
"EventCode": "0xa6",
"EventName": "EXE_ACTIVITY.BOUND_ON_LOADS",
+ "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x21",
"Unit": "cpu_core"
@@ -847,7 +886,7 @@
"CounterMask": "2",
"EventCode": "0xa6",
"EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
- "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.",
+ "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x40",
"Unit": "cpu_core"
@@ -857,7 +896,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa6",
"EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS",
- "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.",
+ "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x80",
"Unit": "cpu_core"
@@ -867,7 +906,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x75",
"EventName": "INST_DECODED.DECODERS",
- "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.",
+ "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -876,7 +915,7 @@
"BriefDescription": "Counts the total number of instructions retired. (Fixed event)",
"Counter": "Fixed counter 0",
"EventName": "INST_RETIRED.ANY",
- "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0.",
+ "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. Available PDIST counters: 32",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -885,7 +924,7 @@
"BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
"Counter": "Fixed counter 0",
"EventName": "INST_RETIRED.ANY",
- "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+ "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -895,7 +934,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc0",
"EventName": "INST_RETIRED.ANY_P",
- "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter.",
+ "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"Unit": "cpu_atom"
},
@@ -913,6 +952,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc0",
"EventName": "INST_RETIRED.MACRO_FUSED",
+ "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -922,7 +962,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc0",
"EventName": "INST_RETIRED.NOP",
- "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions",
+ "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -931,7 +971,7 @@
"BriefDescription": "Precise instruction retired with PEBS precise-distribution",
"Counter": "Fixed counter 0",
"EventName": "INST_RETIRED.PREC_DIST",
- "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.",
+ "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -941,7 +981,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc0",
"EventName": "INST_RETIRED.REP_ITERATION",
- "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
+ "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -953,7 +993,7 @@
"EdgeDetect": "1",
"EventCode": "0xad",
"EventName": "INT_MISC.CLEARS_COUNT",
- "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears",
+ "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0",
"SampleAfterValue": "500009",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -963,7 +1003,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xad",
"EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
- "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.",
+ "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0",
"SampleAfterValue": "500009",
"UMask": "0x80",
"Unit": "cpu_core"
@@ -973,7 +1013,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xad",
"EventName": "INT_MISC.RECOVERY_CYCLES",
- "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
+ "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0",
"SampleAfterValue": "500009",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -985,6 +1025,7 @@
"EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
"MSRIndex": "0x3F7",
"MSRValue": "0x7",
+ "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x40",
"Unit": "cpu_core"
@@ -994,7 +1035,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xad",
"EventName": "INT_MISC.UOP_DROPPING",
- "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons",
+ "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -1004,6 +1045,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe7",
"EventName": "INT_VEC_RETIRED.128BIT",
+ "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x13",
"Unit": "cpu_core"
@@ -1013,6 +1055,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe7",
"EventName": "INT_VEC_RETIRED.256BIT",
+ "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0xac",
"Unit": "cpu_core"
@@ -1022,7 +1065,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe7",
"EventName": "INT_VEC_RETIRED.ADD_128",
- "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.",
+ "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x3",
"Unit": "cpu_core"
@@ -1032,7 +1075,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe7",
"EventName": "INT_VEC_RETIRED.ADD_256",
- "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.",
+ "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0xc",
"Unit": "cpu_core"
@@ -1042,6 +1085,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe7",
"EventName": "INT_VEC_RETIRED.MUL_256",
+ "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x80",
"Unit": "cpu_core"
@@ -1051,6 +1095,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe7",
"EventName": "INT_VEC_RETIRED.SHUFFLES",
+ "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x40",
"Unit": "cpu_core"
@@ -1060,6 +1105,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe7",
"EventName": "INT_VEC_RETIRED.VNNI_128",
+ "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -1069,6 +1115,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe7",
"EventName": "INT_VEC_RETIRED.VNNI_256",
+ "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -1079,6 +1126,7 @@
"Deprecated": "1",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.4K_ALIAS",
+ "PublicDescription": "This event is deprecated. Refer to new event LD_BLOCKS.ADDRESS_ALIAS Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_atom"
@@ -1088,6 +1136,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.ADDRESS_ALIAS",
+ "PublicDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_atom"
@@ -1097,7 +1146,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.ADDRESS_ALIAS",
- "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.",
+ "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -1107,6 +1156,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.DATA_UNKNOWN",
+ "PublicDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1116,7 +1166,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.NO_SR",
- "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+ "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x88",
"Unit": "cpu_core"
@@ -1126,7 +1176,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.STORE_FORWARD",
- "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.",
+ "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x82",
"Unit": "cpu_core"
@@ -1136,7 +1186,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x4c",
"EventName": "LOAD_HIT_PREFETCH.SWPF",
- "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.",
+ "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1147,7 +1197,7 @@
"CounterMask": "1",
"EventCode": "0xa8",
"EventName": "LSD.CYCLES_ACTIVE",
- "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
+ "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1158,7 +1208,7 @@
"CounterMask": "6",
"EventCode": "0xa8",
"EventName": "LSD.CYCLES_OK",
- "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).",
+ "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1168,7 +1218,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa8",
"EventName": "LSD.UOPS",
- "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
+ "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1180,7 +1230,7 @@
"EdgeDetect": "1",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.COUNT",
- "PublicDescription": "Counts the number of machine clears (nukes) of any type.",
+ "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1213,8 +1263,9 @@
"Unit": "cpu_atom"
},
{
- "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.",
+ "BriefDescription": "This event is deprecated.",
"Counter": "0,1,2,3,4,5",
+ "Deprecated": "1",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.SLOW",
"SampleAfterValue": "20003",
@@ -1235,7 +1286,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.SMC",
- "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
+ "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -1245,7 +1296,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe0",
"EventName": "MISC2_RETIRED.LFENCE",
- "PublicDescription": "number of LFENCE retired instructions",
+ "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0",
"SampleAfterValue": "400009",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -1255,7 +1306,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xe4",
"EventName": "MISC_RETIRED.LBR_INSERTS",
- "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY]",
+ "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY] Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1265,7 +1316,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xcc",
"EventName": "MISC_RETIRED.LBR_INSERTS",
- "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
+ "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -1275,7 +1326,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa2",
"EventName": "RESOURCE_STALLS.SB",
- "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+ "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -1285,10 +1336,78 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa2",
"EventName": "RESOURCE_STALLS.SCOREBOARD",
+ "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xa5",
+ "EventName": "RS.EMPTY",
+ "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x7",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "CounterMask": "1",
+ "EdgeDetect": "1",
+ "EventCode": "0xa5",
+ "EventName": "RS.EMPTY_COUNT",
+ "Invert": "1",
+ "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0",
+ "SampleAfterValue": "100003",
+ "UMask": "0x7",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xa5",
+ "EventName": "RS.EMPTY_RESOURCE",
+ "PublicDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end Available PDIST counters: 0",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "CounterMask": "1",
+ "Deprecated": "1",
+ "EdgeDetect": "1",
+ "EventCode": "0xa5",
+ "EventName": "RS_EMPTY.COUNT",
+ "Invert": "1",
+ "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT Available PDIST counters: 0",
+ "SampleAfterValue": "100003",
+ "UMask": "0x7",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "Deprecated": "1",
+ "EventCode": "0xa5",
+ "EventName": "RS_EMPTY.CYCLES",
+ "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY Available PDIST counters: 0",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x7",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0x75",
+ "EventName": "SERIALIZATION.C01_MS_SCB",
+ "SampleAfterValue": "200003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.",
"Counter": "0,1,2,3,4,5",
@@ -1304,7 +1423,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa4",
"EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
- "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.",
+ "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources. Available PDIST counters: 0",
"SampleAfterValue": "10000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -1314,7 +1433,7 @@
"Counter": "0",
"EventCode": "0xa4",
"EventName": "TOPDOWN.BAD_SPEC_SLOTS",
- "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.",
+ "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0",
"SampleAfterValue": "10000003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -1324,7 +1443,7 @@
"Counter": "0",
"EventCode": "0xa4",
"EventName": "TOPDOWN.BR_MISPREDICT_SLOTS",
- "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.",
+ "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0",
"SampleAfterValue": "10000003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -1334,6 +1453,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa4",
"EventName": "TOPDOWN.MEMORY_BOUND_SLOTS",
+ "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0",
"SampleAfterValue": "10000003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -1352,7 +1472,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa4",
"EventName": "TOPDOWN.SLOTS_P",
- "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.",
+ "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0",
"SampleAfterValue": "10000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1561,6 +1681,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc2",
"EventName": "TOPDOWN_RETIRING.ALL",
+ "PublicDescription": "Counts the total number of consumed retirement slots. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"Unit": "cpu_atom"
},
@@ -1569,6 +1690,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x76",
"EventName": "UOPS_DECODED.DEC0_UOPS",
+ "PublicDescription": "UOPS_DECODED.DEC0_UOPS Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1578,7 +1700,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb2",
"EventName": "UOPS_DISPATCHED.PORT_0",
- "PublicDescription": "Number of uops dispatch to execution port 0.",
+ "PublicDescription": "Number of uops dispatch to execution port 0. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1588,7 +1710,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb2",
"EventName": "UOPS_DISPATCHED.PORT_1",
- "PublicDescription": "Number of uops dispatch to execution port 1.",
+ "PublicDescription": "Number of uops dispatch to execution port 1. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -1598,7 +1720,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb2",
"EventName": "UOPS_DISPATCHED.PORT_2_3_10",
- "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10",
+ "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -1608,7 +1730,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb2",
"EventName": "UOPS_DISPATCHED.PORT_4_9",
- "PublicDescription": "Number of uops dispatch to execution ports 4 and 9",
+ "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -1618,7 +1740,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb2",
"EventName": "UOPS_DISPATCHED.PORT_5_11",
- "PublicDescription": "Number of uops dispatch to execution ports 5 and 11",
+ "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -1628,7 +1750,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb2",
"EventName": "UOPS_DISPATCHED.PORT_6",
- "PublicDescription": "Number of uops dispatch to execution port 6.",
+ "PublicDescription": "Number of uops dispatch to execution port 6. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x40",
"Unit": "cpu_core"
@@ -1638,7 +1760,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb2",
"EventName": "UOPS_DISPATCHED.PORT_7_8",
- "PublicDescription": "Number of uops dispatch to execution ports 7 and 8.",
+ "PublicDescription": "Number of uops dispatch to execution ports 7 and 8. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x80",
"Unit": "cpu_core"
@@ -1649,7 +1771,7 @@
"CounterMask": "1",
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
- "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.",
+ "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -1660,7 +1782,7 @@
"CounterMask": "2",
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
- "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.",
+ "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -1671,7 +1793,7 @@
"CounterMask": "3",
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
- "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.",
+ "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -1682,7 +1804,7 @@
"CounterMask": "4",
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
- "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.",
+ "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -1693,7 +1815,7 @@
"CounterMask": "1",
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.CYCLES_GE_1",
- "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
+ "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1704,7 +1826,7 @@
"CounterMask": "2",
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.CYCLES_GE_2",
- "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
+ "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1715,7 +1837,7 @@
"CounterMask": "3",
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.CYCLES_GE_3",
- "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+ "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1726,7 +1848,7 @@
"CounterMask": "4",
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.CYCLES_GE_4",
- "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+ "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1738,7 +1860,7 @@
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.STALLS",
"Invert": "1",
- "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+ "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1751,6 +1873,7 @@
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.STALL_CYCLES",
"Invert": "1",
+ "PublicDescription": "This event is deprecated. Refer to new event UOPS_EXECUTED.STALLS Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1760,6 +1883,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.THREAD",
+ "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1769,7 +1893,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.X87",
- "PublicDescription": "Counts the number of x87 uops executed.",
+ "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -1788,7 +1912,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xae",
"EventName": "UOPS_ISSUED.ANY",
- "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+ "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1799,6 +1923,7 @@
"CounterMask": "1",
"EventCode": "0xae",
"EventName": "UOPS_ISSUED.CYCLES",
+ "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1808,6 +1933,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.ALL",
+ "PublicDescription": "Counts the total number of uops retired. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"Unit": "cpu_atom"
},
@@ -1817,7 +1943,7 @@
"CounterMask": "1",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.CYCLES",
- "PublicDescription": "Counts cycles where at least one uop has retired.",
+ "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -1827,7 +1953,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.HEAVY",
- "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.",
+ "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -1837,6 +1963,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.IDIV",
+ "PublicDescription": "Counts the number of integer divide uops retired. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x10",
"Unit": "cpu_atom"
@@ -1846,7 +1973,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.MS",
- "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.",
+ "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_atom"
@@ -1858,6 +1985,7 @@
"EventName": "UOPS_RETIRED.MS",
"MSRIndex": "0x3F7",
"MSRValue": "0x8",
+ "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -1867,7 +1995,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.SLOTS",
- "PublicDescription": "Counts the retirement slots used each cycle.",
+ "PublicDescription": "Counts the retirement slots used each cycle. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -1879,7 +2007,7 @@
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.STALLS",
"Invert": "1",
- "PublicDescription": "This event counts cycles without actually retired uops.",
+ "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -1892,6 +2020,7 @@
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.STALL_CYCLES",
"Invert": "1",
+ "PublicDescription": "This event is deprecated. Refer to new event UOPS_RETIRED.STALLS Available PDIST counters: 0",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -1901,6 +2030,7 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.X87",
+ "PublicDescription": "Counts the number of x87 uops retired, includes those in MS flows. Available PDIST counters: 0",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_atom"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json
index 132ce48af6d9..3d15275eca61 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json
@@ -4,7 +4,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
- "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
+ "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -15,7 +15,7 @@
"CounterMask": "1",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
- "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.",
+ "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -35,7 +35,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
- "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+ "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0xe",
"Unit": "cpu_core"
@@ -45,7 +45,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
- "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+ "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -55,7 +55,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
- "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+ "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -65,7 +65,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
- "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+ "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -75,7 +75,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
- "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.",
+ "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -85,7 +85,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
- "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
+ "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -96,7 +96,7 @@
"CounterMask": "1",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
- "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
+ "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -116,7 +116,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
- "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+ "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0xe",
"Unit": "cpu_core"
@@ -126,7 +126,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
- "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+ "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -136,7 +136,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
- "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+ "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -146,7 +146,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
- "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+ "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -156,7 +156,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_PENDING",
- "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.",
+ "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -184,7 +184,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.STLB_HIT",
- "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).",
+ "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
@@ -195,7 +195,7 @@
"CounterMask": "1",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_ACTIVE",
- "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.",
+ "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -215,7 +215,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
- "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+ "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0xe",
"Unit": "cpu_core"
@@ -225,7 +225,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
- "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+ "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
@@ -235,7 +235,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
- "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+ "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -245,7 +245,7 @@
"Counter": "0,1,2,3",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_PENDING",
- "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.",
+ "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
@@ -266,6 +266,7 @@
"Deprecated": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
+ "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x13",
"Unit": "cpu_atom"
@@ -277,6 +278,7 @@
"Deprecated": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
+ "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_LOADS Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x11",
"Unit": "cpu_atom"
@@ -288,6 +290,7 @@
"Deprecated": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
+ "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_STORES Available PDIST counters: 0",
"SampleAfterValue": "200003",
"UMask": "0x12",
"Unit": "cpu_atom"
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 56d5fc419acf..881f418137fd 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -1,5 +1,5 @@
Family-model,Version,Filename,EventType
-GenuineIntel-6-(97|9A|B7|BA|BF),v1.28,alderlake,core
+GenuineIntel-6-(97|9A|B7|BA|BF),v1.29,alderlake,core
GenuineIntel-6-BE,v1.28,alderlaken,core
GenuineIntel-6-C[56],v1.07,arrowlake,core
GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core
--
2.49.0.472.ge94155a9ec-goog