| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20241209222800.296000-3-irogers@google.com>
Date: Mon, 9 Dec 2024 14:27:39 -0800
From: Ian Rogers <irogers@...gle.com>
To: Peter Zijlstra <peterz@...radead.org>, Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>, Namhyung Kim <namhyung@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>, Jiri Olsa <jolsa@...nel.org>,
Ian Rogers <irogers@...gle.com>, Adrian Hunter <adrian.hunter@...el.com>,
Kan Liang <kan.liang@...ux.intel.com>,
"Andreas Färber" <afaerber@...e.de>, Manivannan Sadhasivam <manivannan.sadhasivam@...aro.org>,
Weilin Wang <weilin.wang@...el.com>, linux-kernel@...r.kernel.org,
linux-perf-users@...r.kernel.org, Perry Taylor <perry.taylor@...el.com>,
Samantha Alt <samantha.alt@...el.com>, Caleb Biggers <caleb.biggers@...el.com>,
Edward Baker <edward.baker@...el.com>, Michael Petlan <mpetlan@...hat.com>
Subject: [PATCH v1 02/22] perf vendor events: Update AlderlakeN events/metrics
Update events from v1.27 to v1.28.
Update TMA metrics from 4.8 to 5.01.
Bring in the event updates v1.28:
https://github.com/intel/perfmon/commit/801f43f22ec6bd23fbb5d18860f395d61e7f4081
The TMA 5.01 update is from (with subsequent fixes):
https://github.com/intel/perfmon/commit/1d72913b2d938781fb28f3cc3507aaec5c22d782
Co-authored-by: Caleb Biggers <caleb.biggers@...el.com>
Signed-off-by: Ian Rogers <irogers@...gle.com>
---
.../arch/x86/alderlaken/adln-metrics.json | 83 ++++---
.../pmu-events/arch/x86/alderlaken/cache.json | 227 ++++++++++++++++--
.../arch/x86/alderlaken/floating-point.json | 17 +-
.../arch/x86/alderlaken/memory.json | 20 ++
.../pmu-events/arch/x86/alderlaken/other.json | 81 ++++++-
.../arch/x86/alderlaken/pipeline.json | 97 +++++---
.../arch/x86/alderlaken/virtual-memory.json | 30 +++
tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +-
8 files changed, 458 insertions(+), 99 deletions(-)
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
index 447596f924ab..141562def5c4 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
@@ -48,13 +48,6 @@
"MetricName": "C7_Core_Residency",
"ScaleUnit": "100%"
},
- {
- "BriefDescription": "C7 residency percent per package",
- "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC",
- "MetricGroup": "Power",
- "MetricName": "C7_Pkg_Residency",
- "ScaleUnit": "100%"
- },
{
"BriefDescription": "C8 residency percent per package",
"MetricExpr": "cstate_pkg@c8\\-residency@ / TSC",
@@ -62,13 +55,6 @@
"MetricName": "C8_Pkg_Residency",
"ScaleUnit": "100%"
},
- {
- "BriefDescription": "C9 residency percent per package",
- "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC",
- "MetricGroup": "Power",
- "MetricName": "C9_Pkg_Residency",
- "ScaleUnit": "100%"
- },
{
"BriefDescription": "Percentage of cycles spent in System Management Interrupts.",
"MetricExpr": "((msr@...rf@ - cycles) / msr@...rf@ if msr@smi@ > 0 else 0)",
@@ -89,7 +75,7 @@
"MetricExpr": "tma_core_bound",
"MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
"MetricName": "tma_allocation_restriction",
- "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)",
+ "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))",
"ScaleUnit": "100%"
},
{
@@ -98,7 +84,7 @@
"MetricExpr": "TOPDOWN_BE_BOUND.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "Default;TopdownL1;tma_L1_group",
"MetricName": "tma_backend_bound",
- "MetricThreshold": "tma_backend_bound > 0.1",
+ "MetricThreshold": "(tma_backend_bound >0.10)",
"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%"
@@ -109,7 +95,7 @@
"MetricExpr": "(5 * CPU_CLK_UNHALTED.CORE - (TOPDOWN_FE_BOUND.ALL + TOPDOWN_BE_BOUND.ALL + TOPDOWN_RETIRING.ALL)) / (5 * 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%"
@@ -119,7 +105,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / (5 * 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 > 0.2)",
+ "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
"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%"
},
@@ -128,7 +114,7 @@
"MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / (5 * 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%"
},
@@ -137,7 +123,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / (5 * 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 > 0.2)",
+ "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
"ScaleUnit": "100%"
},
{
@@ -145,7 +131,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.CISC / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
"MetricName": "tma_cisc",
- "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
+ "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
"ScaleUnit": "100%"
},
{
@@ -153,7 +139,7 @@
"MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
"MetricName": "tma_core_bound",
- "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1",
+ "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%"
},
@@ -162,7 +148,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.DECODE / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
"MetricName": "tma_decode",
- "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
+ "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
"ScaleUnit": "100%"
},
{
@@ -170,7 +156,7 @@
"MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / (5 * 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%"
},
{
@@ -179,7 +165,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "Default;TopdownL1;tma_L1_group",
"MetricName": "tma_frontend_bound",
- "MetricThreshold": "tma_frontend_bound > 0.2",
+ "MetricThreshold": "(tma_frontend_bound >0.20)",
"MetricgroupNoGroup": "TopdownL1;Default",
"ScaleUnit": "100%"
},
@@ -188,7 +174,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / (5 * 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 > 0.2)",
+ "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
"ScaleUnit": "100%"
},
{
@@ -196,7 +182,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
"MetricName": "tma_ifetch_bandwidth",
- "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2",
+ "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%"
},
@@ -205,7 +191,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / (5 * 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 > 0.2",
+ "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%"
},
@@ -320,6 +306,11 @@
"MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_L2_HIT / MEM_BOUND_STALLS.IFETCH",
"MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2hit"
},
+ {
+ "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss doesn't hit in the L2",
+ "MetricExpr": "100 * (MEM_BOUND_STALLS.IFETCH_LLC_HIT + MEM_BOUND_STALLS.IFETCH_DRAM_HIT) / MEM_BOUND_STALLS.IFETCH",
+ "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2miss"
+ },
{
"BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L3",
"MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_LLC_HIT / MEM_BOUND_STALLS.IFETCH",
@@ -336,6 +327,12 @@
"MetricGroup": "load_store_bound",
"MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2hit"
},
+ {
+ "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses in the L2",
+ "MetricExpr": "100 * (MEM_BOUND_STALLS.LOAD_LLC_HIT + MEM_BOUND_STALLS.LOAD_DRAM_HIT) / MEM_BOUND_STALLS.LOAD",
+ "MetricGroup": "load_store_bound",
+ "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2miss"
+ },
{
"BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L3",
"MetricExpr": "100 * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD",
@@ -472,6 +469,12 @@
"MetricGroup": "Summary",
"MetricName": "tma_info_system_kernel_utilization"
},
+ {
+ "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
+ "MetricExpr": "CPU_CLK_UNHALTED.CORE_P / CPU_CLK_UNHALTED.CORE",
+ "MetricName": "tma_info_system_mux",
+ "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))"
+ },
{
"BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.CORE / CPU_CLK_UNHALTED.REF_TSC",
@@ -503,7 +506,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.ITLB / (5 * 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 > 0.2)",
+ "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
"ScaleUnit": "100%"
},
{
@@ -511,7 +514,7 @@
"MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / (5 * 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%"
},
@@ -520,7 +523,7 @@
"MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
"MetricName": "tma_mem_scheduler",
- "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
+ "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
"ScaleUnit": "100%"
},
{
@@ -528,7 +531,7 @@
"MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
"MetricName": "tma_non_mem_scheduler",
- "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
+ "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
"ScaleUnit": "100%"
},
{
@@ -536,7 +539,7 @@
"MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / (5 * 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%"
},
{
@@ -544,7 +547,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.OTHER / (5 * 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 > 0.1 & tma_frontend_bound > 0.2)",
+ "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
"ScaleUnit": "100%"
},
{
@@ -552,7 +555,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
"MetricName": "tma_predecode",
- "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
+ "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
"ScaleUnit": "100%"
},
{
@@ -560,7 +563,7 @@
"MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
"MetricName": "tma_register",
- "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
+ "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
"ScaleUnit": "100%"
},
{
@@ -568,7 +571,7 @@
"MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
"MetricName": "tma_reorder_buffer",
- "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
+ "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
"ScaleUnit": "100%"
},
{
@@ -576,7 +579,7 @@
"MetricExpr": "tma_backend_bound - tma_core_bound",
"MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
"MetricName": "tma_resource_bound",
- "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1",
+ "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%"
},
@@ -586,7 +589,7 @@
"MetricExpr": "TOPDOWN_RETIRING.ALL / (5 * 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%"
},
@@ -595,7 +598,7 @@
"MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
"MetricName": "tma_serialization",
- "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
+ "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
"ScaleUnit": "100%"
}
]
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/cache.json b/tools/perf/pmu-events/arch/x86/alderlaken/cache.json
index 1500033ee19f..fd9ed58c2f90 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/cache.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/cache.json
@@ -1,4 +1,30 @@
[
+ {
+ "BriefDescription": "Counts the total number of L2 Cache accesses. Counts on a per core basis.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.ALL",
+ "PublicDescription": "Counts the total number of L2 Cache Accesses, includes hits, misses, rejects front door requests for CRd/DRd/RFO/ItoM/L2 Prefetches only. Counts on a per core basis.",
+ "SampleAfterValue": "200003"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 Cache accesses that resulted in a hit. Counts on a per core basis.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.HIT",
+ "PublicDescription": "Counts the number of L2 Cache accesses that resulted in a hit from a front door request only (does not include rejects or recycles), Counts on a per core basis.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x2"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 Cache accesses that resulted in a miss. Counts on a per core basis.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.MISS",
+ "PublicDescription": "Counts the number of L2 Cache accesses that resulted in a miss from a front door request only (does not include rejects or recycles). Counts on a per core basis.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.",
"Counter": "0,1,2,3,4,5",
@@ -92,30 +118,81 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x80"
},
+ {
+ "BriefDescription": "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.",
+ "Counter": "0,1,2,3,4,5",
+ "Data_LA": "1",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
+ "SampleAfterValue": "200003",
+ "UMask": "0x20"
+ },
+ {
+ "BriefDescription": "Counts the number of load uops retired that hit in the L1 data cache.",
+ "Counter": "0,1,2,3,4,5",
+ "Data_LA": "1",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
+ "SampleAfterValue": "200003",
+ "UMask": "0x1"
+ },
+ {
+ "BriefDescription": "Counts the number of load uops retired that miss in the L1 data cache.",
+ "Counter": "0,1,2,3,4,5",
+ "Data_LA": "1",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
+ "SampleAfterValue": "200003",
+ "UMask": "0x8"
+ },
{
"BriefDescription": "Counts the number of load uops retired that hit in the L2 cache.",
"Counter": "0,1,2,3,4,5",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
+ {
+ "BriefDescription": "Counts the number of load uops retired that miss in the L2 cache.",
+ "Counter": "0,1,2,3,4,5",
+ "Data_LA": "1",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
+ "SampleAfterValue": "200003",
+ "UMask": "0x10"
+ },
{
"BriefDescription": "Counts the number of load uops retired that hit in the L3 cache.",
"Counter": "0,1,2,3,4,5",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
+ {
+ "BriefDescription": "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.",
+ "Counter": "0,1,2,3,4,5",
+ "Data_LA": "1",
+ "EventCode": "0xd2",
+ "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.HIT_E_F",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x40"
+ },
+ {
+ "BriefDescription": "Counts the number of load uops retired that miss in the L3 cache.",
+ "Counter": "0,1,2,3,4,5",
+ "Data_LA": "1",
+ "EventCode": "0xd2",
+ "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.L3_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x20"
+ },
{
"BriefDescription": "Counts the number of cycles that uops are blocked for any of the following reasons: load buffer, store buffer or RSV full.",
"Counter": "0,1,2,3,4,5",
@@ -154,7 +231,6 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
- "PEBS": "1",
"PublicDescription": "Counts the total number of load uops retired.",
"SampleAfterValue": "200003",
"UMask": "0x81"
@@ -165,7 +241,6 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.ALL_STORES",
- "PEBS": "1",
"PublicDescription": "Counts the total number of store uops retired.",
"SampleAfterValue": "200003",
"UMask": "0x82"
@@ -178,7 +253,6 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"MSRValue": "0x80",
- "PEBS": "2",
"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.",
"SampleAfterValue": "1000003",
"UMask": "0x5"
@@ -191,7 +265,6 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"MSRValue": "0x10",
- "PEBS": "2",
"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.",
"SampleAfterValue": "1000003",
"UMask": "0x5"
@@ -204,7 +277,6 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"MSRValue": "0x100",
- "PEBS": "2",
"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.",
"SampleAfterValue": "1000003",
"UMask": "0x5"
@@ -217,7 +289,6 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"MSRValue": "0x20",
- "PEBS": "2",
"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.",
"SampleAfterValue": "1000003",
"UMask": "0x5"
@@ -230,7 +301,6 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"MSRValue": "0x4",
- "PEBS": "2",
"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.",
"SampleAfterValue": "1000003",
"UMask": "0x5"
@@ -243,7 +313,6 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"MSRValue": "0x200",
- "PEBS": "2",
"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.",
"SampleAfterValue": "1000003",
"UMask": "0x5"
@@ -256,7 +325,6 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"MSRValue": "0x40",
- "PEBS": "2",
"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.",
"SampleAfterValue": "1000003",
"UMask": "0x5"
@@ -269,7 +337,6 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"MSRValue": "0x8",
- "PEBS": "2",
"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.",
"SampleAfterValue": "1000003",
"UMask": "0x5"
@@ -280,7 +347,6 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x21"
},
@@ -290,28 +356,93 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x41"
},
+ {
+ "BriefDescription": "Counts the total number of load and store uops retired that missed in the second level TLB.",
+ "Counter": "0,1,2,3,4,5",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_UOPS_RETIRED.STLB_MISS",
+ "SampleAfterValue": "200003",
+ "UMask": "0x13"
+ },
+ {
+ "BriefDescription": "Counts the number of load ops retired that miss in the second Level TLB.",
+ "Counter": "0,1,2,3,4,5",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
+ "SampleAfterValue": "200003",
+ "UMask": "0x11"
+ },
+ {
+ "BriefDescription": "Counts the number of store ops retired that miss in the second level TLB.",
+ "Counter": "0,1,2,3,4,5",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
+ "SampleAfterValue": "200003",
+ "UMask": "0x12"
+ },
{
"BriefDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled.",
"Counter": "0,1,2,3,4,5",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.STORE_LATENCY",
- "PEBS": "2",
"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.",
"SampleAfterValue": "1000003",
"UMask": "0x6"
},
+ {
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x1F803C0004",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
+ {
+ "BriefDescription": "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.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10003C0004",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
+ {
+ "BriefDescription": "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.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x4003C0004",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
+ {
+ "BriefDescription": "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.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x8003C0004",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Counts demand data reads that were supplied by the L3 cache.",
"Counter": "0,1,2,3,4,5",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
"MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x3F803C0001",
+ "MSRValue": "0x1F803C0001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
@@ -351,7 +482,7 @@
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_RFO.L3_HIT",
"MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x3F803C0002",
+ "MSRValue": "0x1F803C0002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
@@ -365,6 +496,66 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
+ {
+ "BriefDescription": "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.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x4003C0002",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
+ {
+ "BriefDescription": "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.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x8003C0002",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
+ {
+ "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.SWPF_RD.L3_HIT",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x1F803C4000",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
+ {
+ "BriefDescription": "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.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HITM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10003C4000",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
+ {
+ "BriefDescription": "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.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x4003C4000",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
+ {
+ "BriefDescription": "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.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x8003C4000",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to instruction cache misses.",
"Counter": "0,1,2,3,4,5",
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json b/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json
index 484d8b3167f0..ed963fcb6485 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json
@@ -1,4 +1,20 @@
[
+ {
+ "BriefDescription": "Counts the number of cycles the floating point divider is in the loop stage.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.FPDIV_ACTIVE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2"
+ },
+ {
+ "BriefDescription": "Counts the number of floating point divider uops executed per cycle.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.FPDIV_UOPS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8"
+ },
{
"BriefDescription": "Counts the number of floating point operations retired that required microcode assist.",
"Counter": "0,1,2,3,4,5",
@@ -13,7 +29,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.FPDIV",
- "PEBS": "1",
"SampleAfterValue": "2000003",
"UMask": "0x8"
}
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json
index 619488d42a4a..3b46b048dfb2 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json
@@ -56,6 +56,16 @@
"SampleAfterValue": "20003",
"UMask": "0x2"
},
+ {
+ "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",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x3F84400004",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
"Counter": "0,1,2,3,4,5",
@@ -95,5 +105,15 @@
"MSRValue": "0x3F84400002",
"SampleAfterValue": "100003",
"UMask": "0x1"
+ },
+ {
+ "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were not supplied by the L3 cache.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.SWPF_RD.L3_MISS",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x3F84404000",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
}
]
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/other.json b/tools/perf/pmu-events/arch/x86/alderlaken/other.json
index 54ddbe2b3b9b..f8c21b7f8f40 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/other.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/other.json
@@ -5,7 +5,6 @@
"Deprecated": "1",
"EventCode": "0xe4",
"EventName": "LBR_INSERTS.ANY",
- "PEBS": "1",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
@@ -19,6 +18,26 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
+ {
+ "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"
+ },
+ {
+ "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"
+ },
{
"BriefDescription": "Counts demand data reads that have any type of response.",
"Counter": "0,1,2,3,4,5",
@@ -29,6 +48,16 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
+ {
+ "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"
+ },
{
"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",
@@ -39,6 +68,36 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
+ {
+ "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"
+ },
+ {
+ "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x800000010000",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
+ {
+ "BriefDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x400000010000",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Counts streaming stores that have any type of response.",
"Counter": "0,1,2,3,4,5",
@@ -49,6 +108,26 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
+ {
+ "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"
+ },
+ {
+ "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"
+ },
{
"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",
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json
index f05db45578ff..713ebc21cec0 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json
@@ -1,10 +1,59 @@
[
+ {
+ "BriefDescription": "Counts the number of cycles when any of the floating point or integer dividers are active.",
+ "Counter": "0,1,2,3,4,5",
+ "CounterMask": "1",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.DIV_ACTIVE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x3"
+ },
+ {
+ "BriefDescription": "Counts the number of active floating point and integer dividers per cycle.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.DIV_OCCUPANCY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x3"
+ },
+ {
+ "BriefDescription": "Counts the number of floating point and integer divider uops executed per cycle.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.DIV_UOPS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xc"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles any of the two integer dividers are active.",
+ "Counter": "0,1,2,3,4,5",
+ "CounterMask": "1",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.IDIV_ACTIVE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1"
+ },
+ {
+ "BriefDescription": "Counts the number of active integer dividers per cycle.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.IDIV_OCCUPANCY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1"
+ },
+ {
+ "BriefDescription": "Counts the number of integer divider uops executed per cycle.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.IDIV_UOPS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4"
+ },
{
"BriefDescription": "Counts the total number of branch instructions retired for all branch types.",
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.ALL_BRANCHES",
- "PEBS": "1",
"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.",
"SampleAfterValue": "200003"
},
@@ -14,7 +63,6 @@
"Deprecated": "1",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.CALL",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xf9"
},
@@ -23,7 +71,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.COND",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x7e"
},
@@ -32,7 +79,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.COND_TAKEN",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xfe"
},
@@ -41,7 +87,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.FAR_BRANCH",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xbf"
},
@@ -50,7 +95,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.INDIRECT",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xeb"
},
@@ -59,7 +103,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.INDIRECT_CALL",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xfb"
},
@@ -69,7 +112,6 @@
"Deprecated": "1",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.IND_CALL",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xfb"
},
@@ -79,7 +121,6 @@
"Deprecated": "1",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.JCC",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x7e"
},
@@ -88,7 +129,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_CALL",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xf9"
},
@@ -97,7 +137,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_RETURN",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xf7"
},
@@ -106,7 +145,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_TAKEN",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xc0"
},
@@ -116,7 +154,6 @@
"Deprecated": "1",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NON_RETURN_IND",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xeb"
},
@@ -125,7 +162,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.REL_CALL",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xfd"
},
@@ -135,7 +171,6 @@
"Deprecated": "1",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.RETURN",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xf7"
},
@@ -145,7 +180,6 @@
"Deprecated": "1",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.TAKEN_JCC",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xfe"
},
@@ -154,7 +188,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
- "PEBS": "1",
"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.",
"SampleAfterValue": "200003"
},
@@ -163,7 +196,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x7e"
},
@@ -172,7 +204,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND_TAKEN",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xfe"
},
@@ -181,7 +212,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.INDIRECT",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xeb"
},
@@ -190,7 +220,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xfb"
},
@@ -200,7 +229,6 @@
"Deprecated": "1",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.IND_CALL",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xfb"
},
@@ -210,7 +238,6 @@
"Deprecated": "1",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.JCC",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x7e"
},
@@ -219,7 +246,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x80"
},
@@ -229,7 +255,6 @@
"Deprecated": "1",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xeb"
},
@@ -238,7 +263,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.RETURN",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xf7"
},
@@ -248,7 +272,6 @@
"Deprecated": "1",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.TAKEN_JCC",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0xfe"
},
@@ -268,6 +291,15 @@
"PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. The core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. This event uses a programmable general purpose performance counter.",
"SampleAfterValue": "2000003"
},
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event CPU_CLK_UNHALTED.REF_TSC_P",
+ "Counter": "0,1,2,3,4,5",
+ "Deprecated": "1",
+ "EventCode": "0x3c",
+ "EventName": "CPU_CLK_UNHALTED.REF",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Counts the number of unhalted reference clock cycles at TSC frequency. (Fixed event)",
"Counter": "Fixed counter 2",
@@ -305,7 +337,6 @@
"BriefDescription": "Counts the total number of instructions retired. (Fixed event)",
"Counter": "Fixed counter 0",
"EventName": "INST_RETIRED.ANY",
- "PEBS": "1",
"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.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
@@ -315,7 +346,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc0",
"EventName": "INST_RETIRED.ANY_P",
- "PEBS": "1",
"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.",
"SampleAfterValue": "2000003"
},
@@ -325,7 +355,6 @@
"Deprecated": "1",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.4K_ALIAS",
- "PEBS": "1",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
@@ -334,7 +363,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.ADDRESS_ALIAS",
- "PEBS": "1",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
@@ -343,7 +371,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.DATA_UNKNOWN",
- "PEBS": "1",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
@@ -392,7 +419,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xe4",
"EventName": "MISC_RETIRED.LBR_INSERTS",
- "PEBS": "1",
"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]",
"SampleAfterValue": "1000003",
"UMask": "0x1"
@@ -588,7 +614,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc2",
"EventName": "TOPDOWN_RETIRING.ALL",
- "PEBS": "1",
"SampleAfterValue": "1000003"
},
{
@@ -604,7 +629,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.ALL",
- "PEBS": "1",
"SampleAfterValue": "2000003"
},
{
@@ -612,7 +636,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.IDIV",
- "PEBS": "1",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
@@ -621,7 +644,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.MS",
- "PEBS": "1",
"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.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
@@ -631,7 +653,6 @@
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.X87",
- "PEBS": "1",
"SampleAfterValue": "2000003",
"UMask": "0x2"
}
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json b/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json
index ad2b1349bab4..d9c737a17df0 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json
@@ -49,5 +49,35 @@
"EventName": "LD_HEAD.DTLB_MISS_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0x90"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS",
+ "Counter": "0,1,2,3,4,5",
+ "Data_LA": "1",
+ "Deprecated": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
+ "SampleAfterValue": "200003",
+ "UMask": "0x13"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_LOADS",
+ "Counter": "0,1,2,3,4,5",
+ "Data_LA": "1",
+ "Deprecated": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
+ "SampleAfterValue": "200003",
+ "UMask": "0x11"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_STORES",
+ "Counter": "0,1,2,3,4,5",
+ "Data_LA": "1",
+ "Deprecated": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
+ "SampleAfterValue": "200003",
+ "UMask": "0x12"
}
]
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index d9538723927b..2fa5529ee585 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -1,6 +1,6 @@
Family-model,Version,Filename,EventType
GenuineIntel-6-(97|9A|B7|BA|BF),v1.28,alderlake,core
-GenuineIntel-6-BE,v1.27,alderlaken,core
+GenuineIntel-6-BE,v1.28,alderlaken,core
GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core
GenuineIntel-6-(3D|47),v29,broadwell,core
GenuineIntel-6-56,v11,broadwellde,core
--
2.47.1.545.g3c1d2e2a6a-goog
Powered by blists - more mailing lists