[PATCH v2 08/10] perf vendor events intel: Update pantherlake events from 1.02 to 1.04
Ian Rogers
irogers at google.com
Thu Feb 26 09:59:34 PST 2026
The updated events were published in:
https://github.com/intel/perfmon/commit/1f46fa264d202d57dade1d3fd5b58e79c4706147
https://github.com/intel/perfmon/commit/e49581aeb2903dde6fb1d187e9d412df58e01038
Signed-off-by: Ian Rogers <irogers at google.com>
---
tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +-
.../arch/x86/pantherlake/cache.json | 159 +++++++++++++-
.../arch/x86/pantherlake/floating-point.json | 28 +++
.../arch/x86/pantherlake/frontend.json | 36 ++++
.../arch/x86/pantherlake/memory.json | 27 +++
.../arch/x86/pantherlake/other.json | 10 +
.../arch/x86/pantherlake/pipeline.json | 200 +++++++++++++++++-
.../arch/x86/pantherlake/virtual-memory.json | 30 +++
8 files changed, 485 insertions(+), 7 deletions(-)
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 8d8fd8b08166..0839e21d4006 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -26,7 +26,7 @@ GenuineIntel-6-BD,v1.21,lunarlake,core
GenuineIntel-6-(AA|AC|B5),v1.20,meteorlake,core
GenuineIntel-6-1[AEF],v4,nehalemep,core
GenuineIntel-6-2E,v4,nehalemex,core
-GenuineIntel-6-CC,v1.02,pantherlake,core
+GenuineIntel-6-CC,v1.04,pantherlake,core
GenuineIntel-6-A7,v1.04,rocketlake,core
GenuineIntel-6-2A,v19,sandybridge,core
GenuineIntel-6-8F,v1.35,sapphirerapids,core
diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/cache.json b/tools/perf/pmu-events/arch/x86/pantherlake/cache.json
index 91f5ab908926..e5323093eec0 100644
--- a/tools/perf/pmu-events/arch/x86/pantherlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/pantherlake/cache.json
@@ -149,6 +149,60 @@
"UMask": "0xff",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the number of L2 cache accesses from front door Demand Code Read requests. Does not include rejects or recycles, per core event.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.DEMAND_CODE_RD",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xc4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 cache accesses from front door Demand Code Read requests that resulted in a Miss. Does not include rejects or recycles, per core event.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.DEMAND_CODE_RD_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x44",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 cache accesses from front door Demand Data Read requests. Does not include rejects or recycles, per core event.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.DEMAND_DATA_RD",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xc1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 cache accesses from front door Demand Data Read requests that resulted in a Miss. Does not include rejects or recycles, per core event.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.DEMAND_DATA_RD_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x41",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 cache accesses from front door Demand RFO requests. Does not include rejects or recycles, per core event.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.DEMAND_RFO",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xc2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 cache accesses from front door Demand RFO requests that resulted in a Miss. Does not include rejects or recycles, per core event.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.DEMAND_RFO_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x42",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of L2 cache accesses from front door requests that resulted in a Hit. Does not include rejects or recycles, per core event.",
"Counter": "0,1,2,3,4,5,6,7",
@@ -158,6 +212,24 @@
"UMask": "0x1bf",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number of L2 cache accesses from front door Hardware Prefetch requests. Does not include rejects or recycles, per core event.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.HWPF",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xc8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 cache accesses from front door requests that resulted in a Miss. Does not include rejects or recycles, per core event.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x17f",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_RQSTS.MISS]",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -365,6 +437,24 @@
"UMask": "0x6",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC, no snoop was required. LLC provided data.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x34",
+ "EventName": "MEM_BOUND_STALLS_LOAD.LLC_HIT_NOSNOOP",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC, a snoop was required, the snoop misses or the snoop hits but no fwd. LLC provides the data.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x34",
+ "EventName": "MEM_BOUND_STALLS_LOAD.LLC_HIT_SNOOP",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches.",
"Counter": "0,1,2,3,4,5,6,7",
@@ -716,6 +806,16 @@
"UMask": "0x20",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the total number of load ops retired that miss the L3 cache.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xd3",
+ "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.ALL",
+ "PublicDescription": "Counts the total number of load ops retired that miss the L3 cache. Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xff",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of load ops retired that miss the L3 cache and hit in DRAM",
"Counter": "0,1,2,3,4,5,6,7",
@@ -746,6 +846,26 @@
"UMask": "0x8",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number of load ops retired that hit in the L3 cache in which a snoop was required and no data was forwarded.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xd4",
+ "EventName": "MEM_LOAD_UOPS_MISC_RETIRED.L3_HIT_SNOOP_NO_FWD",
+ "PublicDescription": "Counts the number of load ops retired that hit in the L3 cache in which a snoop was required and no data was forwarded. Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of load ops retired that hit in the L3 cache in which a snoop was required and non-modified data was forwarded.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xd4",
+ "EventName": "MEM_LOAD_UOPS_MISC_RETIRED.L3_HIT_SNOOP_WITH_FWD",
+ "PublicDescription": "Counts the number of load ops retired that hit in the L3 cache in which a snoop was required and non-modified data was forwarded. Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of load ops retired that hit the L1 data cache.",
"Counter": "0,1,2,3,4,5,6,7",
@@ -796,6 +916,26 @@
"UMask": "0x1c",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number of load ops retired that hit in the L3 cache in which no snoop was required.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT_NO_SNOOP",
+ "PublicDescription": "Counts the number of load ops retired that hit in the L3 cache in which no snoop was required. Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of load ops retired that hit in the L3 cache in which a snoop was required and it hit and forwarded data, it hit and did not forward data, or it hit and the forwarded data was modified.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT_SNOOP_HIT",
+ "PublicDescription": "Counts the number of load ops retired that hit in the L3 cache in which a snoop was required and it hit and forwarded data, it hit and did not forward data, or it hit and the forwarded data was modified. Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of cycles that uops are blocked for any of the following reasons: load buffer, store buffer or RSV full.",
"Counter": "0,1,2,3,4,5,6,7",
@@ -880,13 +1020,14 @@
"Unit": "cpu_atom"
},
{
- "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+ "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 1024.",
"Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024",
"MSRIndex": "0x3F6",
"MSRValue": "0x400",
- "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
+ "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 1024. Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -894,6 +1035,7 @@
{
"BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
"Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
@@ -906,6 +1048,7 @@
{
"BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
"Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
@@ -916,13 +1059,14 @@
"Unit": "cpu_atom"
},
{
- "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+ "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 2048.",
"Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048",
"MSRIndex": "0x3F6",
"MSRValue": "0x800",
- "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
+ "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 2048. Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -930,6 +1074,7 @@
{
"BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
"Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
@@ -942,6 +1087,7 @@
{
"BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
"Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
@@ -954,6 +1100,7 @@
{
"BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
"Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
@@ -966,6 +1113,7 @@
{
"BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
"Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
@@ -978,6 +1126,7 @@
{
"BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
"Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
@@ -990,6 +1139,7 @@
{
"BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
"Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
@@ -1072,6 +1222,7 @@
{
"BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES",
"Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.STORE_LATENCY",
"PublicDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES Available PDIST counters: 0,1",
diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/floating-point.json b/tools/perf/pmu-events/arch/x86/pantherlake/floating-point.json
index e306a45b22ee..77f6c9028d93 100644
--- a/tools/perf/pmu-events/arch/x86/pantherlake/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/pantherlake/floating-point.json
@@ -1,4 +1,14 @@
[
+ {
+ "BriefDescription": "Counts the number of cycles when any of the floating point dividers are active.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "CounterMask": "1",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.FPDIV_ACTIVE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Cycles when floating-point divide unit is busy executing divide or square root operations.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -10,6 +20,24 @@
"UMask": "0x1",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the number of floating point dividers per cycle in the loop stage.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.FPDIV_OCCUPANCY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of floating point divider uops executed per cycle.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.FPDIV_UOPS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts all microcode FP assists.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/frontend.json b/tools/perf/pmu-events/arch/x86/pantherlake/frontend.json
index d36faa683d3f..5e69b81742f5 100644
--- a/tools/perf/pmu-events/arch/x86/pantherlake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/pantherlake/frontend.json
@@ -422,6 +422,24 @@
"UMask": "0x4",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache In use-full",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x83",
+ "EventName": "ICACHE_TAG.STALLS_INUSE",
+ "SampleAfterValue": "200003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache ISB-full",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x83",
+ "EventName": "ICACHE_TAG.STALLS_ISB",
+ "SampleAfterValue": "200003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -561,5 +579,23 @@
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the micro-sequencer is busy.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe7",
+ "EventName": "MS_DECODED.MS_BUSY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of times entered into a ucode flow in the FEC. Includes inserted flows due to front-end detected faults or assists.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe7",
+ "EventName": "MS_DECODED.MS_ENTRY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
}
]
diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/memory.json b/tools/perf/pmu-events/arch/x86/pantherlake/memory.json
index 3d31e620383d..4248cc101391 100644
--- a/tools/perf/pmu-events/arch/x86/pantherlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/pantherlake/memory.json
@@ -8,6 +8,24 @@
"UMask": "0xf4",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a DL1 miss.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.L1_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DL1 miss.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.L1_MISS_AT_RET",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x81",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to request buffers full or lock in progress.",
"Counter": "0,1,2,3,4,5,6,7",
@@ -17,6 +35,15 @@
"UMask": "0x2",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to request buffers full or lock in progress.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.WCB_FULL_AT_RET",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x82",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of machine clears due to memory ordering caused by a snoop from an external agent. Does not count internally generated machine clears such as those due to memory disambiguation.",
"Counter": "0,1,2,3,4,5,6,7",
diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/other.json b/tools/perf/pmu-events/arch/x86/pantherlake/other.json
index d49651d4f112..915c52f5abd1 100644
--- a/tools/perf/pmu-events/arch/x86/pantherlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/pantherlake/other.json
@@ -30,6 +30,16 @@
"UMask": "0x1",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the total number of BTCLEARS.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe8",
+ "EventName": "PREDICTION.BTCLEAR",
+ "PublicDescription": "Counts the total number of BTCLEARS which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Cycles the uncore cannot take further requests",
"Counter": "0,1,2,3,4,5,6,7,8,9",
diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/pipeline.json b/tools/perf/pmu-events/arch/x86/pantherlake/pipeline.json
index fb87d30c403d..86009237df2f 100644
--- a/tools/perf/pmu-events/arch/x86/pantherlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/pantherlake/pipeline.json
@@ -1,4 +1,14 @@
[
+ {
+ "BriefDescription": "Counts the number of cycles when any of the floating point or integer dividers are active.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "CounterMask": "1",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.DIV_ACTIVE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x3",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Cycles when divide unit is busy executing divide or square root operations.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -10,6 +20,16 @@
"UMask": "0x9",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the number of cycles when any of the integer dividers are active.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "CounterMask": "1",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.IDIV_ACTIVE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Cycles when integer divide unit is busy executing divide or square root operations.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -21,6 +41,24 @@
"UMask": "0x8",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts number of active integer dividers per cycle.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.IDIV_OCCUPANCY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of integer divider uops executed per cycle.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.IDIV_UOPS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -58,6 +96,38 @@
"SampleAfterValue": "400009",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "This event is deprecated. [This event is alias to BR_INST_RETIRED.NEAR_INDIRECT]",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "Deprecated": "1",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.ALL_NEAR_IND",
+ "PublicDescription": "This event is deprecated. [This event is alias to BR_INST_RETIRED.NEAR_INDIRECT] Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x50",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This event is deprecated. [This event is alias to BR_INST_RETIRED.NEAR_INDIRECT_OR_RETURN]",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "Deprecated": "1",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.ALL_NEAR_IND_OR_RET",
+ "PublicDescription": "This event is deprecated. [This event is alias to BR_INST_RETIRED.NEAR_INDIRECT_OR_RETURN] Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x58",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of conditional branch instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.COND",
+ "PublicDescription": "Counts the number of conditional branch instructions retired. Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x7",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Conditional branch instructions retired.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -88,6 +158,16 @@
"UMask": "0x4",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the number of taken conditional branch instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.COND_TAKEN",
+ "PublicDescription": "Counts the number of taken conditional branch instructions retired. Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x3",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Taken conditional branch instructions retired.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -98,6 +178,16 @@
"UMask": "0x3",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the number of taken backward conditional branch instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.COND_TAKEN_BWD",
+ "PublicDescription": "Counts the number of taken backward conditional branch instructions retired. Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Taken backward conditional branch instructions retired.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -108,6 +198,16 @@
"UMask": "0x1",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the number of taken forward conditional branch instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.COND_TAKEN_FWD",
+ "PublicDescription": "Counts the number of taken forward conditional branch instructions retired. Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Taken forward conditional branch instructions retired.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -178,6 +278,16 @@
"UMask": "0x80",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired. [This event is alias to BR_INST_RETIRED.ALL_NEAR_IND]",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.NEAR_INDIRECT",
+ "PublicDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired. [This event is alias to BR_INST_RETIRED.ALL_NEAR_IND] Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x50",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Indirect near branch instructions retired (excluding returns) [This event is alias to BR_INST_RETIRED.INDIRECT]",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -208,6 +318,16 @@
"UMask": "0x40",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the number of near indirect JMP, near indirect CALL, and RET branch instructions retired. [This event is alias to BR_INST_RETIRED.ALL_NEAR_IND_OR_RET]",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.NEAR_INDIRECT_OR_RETURN",
+ "PublicDescription": "Counts the number of near indirect JMP, near indirect CALL, and RET branch instructions retired. [This event is alias to BR_INST_RETIRED.ALL_NEAR_IND_OR_RET] Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x58",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "This event is deprecated. [This event is alias to BR_INST_RETIRED.NEAR_INDIRECT_CALL]",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -283,7 +403,7 @@
"Unit": "cpu_atom"
},
{
- "BriefDescription": "Taken branch instructions retired.",
+ "BriefDescription": "Near Taken branch instructions retired.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_TAKEN",
@@ -755,7 +875,7 @@
"Unit": "cpu_core"
},
{
- "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles.",
+ "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles. [This event is alias to CPU_CLK_UNHALTED.THREAD]",
"Counter": "Fixed counter 1",
"EventName": "CPU_CLK_UNHALTED.CORE",
"SampleAfterValue": "2000003",
@@ -1549,6 +1669,16 @@
"UMask": "0x1",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the number of CLFLUSH, CLWB, and CLDEMOTE instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe0",
+ "EventName": "MISC_RETIRED1.CL_INST",
+ "PublicDescription": "Counts the number of CLFLUSH, CLWB, and CLDEMOTE instructions retired. Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xff",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of LFENCE instructions retired.",
"Counter": "0,1,2,3,4,5,6,7",
@@ -1620,6 +1750,15 @@
"UMask": "0x4",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number issue slots not consumed due to a color request for an FCW or MXCSR control register when all 4 colors (copies) are already in use.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x75",
+ "EventName": "SERIALIZATION.COLOR_STALLS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of issue slots where no uop could issue due to an IQ scoreboard that stalls allocation until a specified older uop retires or (in the case of jump scoreboard) executes. Commonly executed instructions with IQ scoreboards include LFENCE and MFENCE.",
"Counter": "0,1,2,3,4,5,6,7",
@@ -1732,6 +1871,15 @@
"UMask": "0x8",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x73",
+ "EventName": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x3",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to Branch Mispredict",
"Counter": "0,1,2,3,4,5,6,7",
@@ -1795,6 +1943,15 @@
"UMask": "0x2",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to ROB full",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x74",
+ "EventName": "TOPDOWN_BE_BOUND.REORDER_BUFFER",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x40",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to iq/jeu scoreboards or ms scb",
"Counter": "0,1,2,3,4,5,6,7",
@@ -2076,6 +2233,15 @@
"UMask": "0x10",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the number of uops issued by the front end every cycle.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x0e",
+ "EventName": "UOPS_ISSUED.ANY",
+ "PublicDescription": "Counts the number of uops issued by the front end every cycle. When 4-uops are requested and only 2-uops are delivered, the event counts 2. Uops_issued correlates to the number of ROB entries. If uop takes 2 ROB slots it counts as 2 uops_issued.",
+ "SampleAfterValue": "1000003",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Uops that RAT issues to RS",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -2107,6 +2273,16 @@
"UMask": "0x2",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the number of uops retired that are the last uop of a macro-instruction.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc2",
+ "EventName": "UOPS_RETIRED.EOM",
+ "PublicDescription": "Counts the number of uops retired that are the last uop of a macro-instruction. EOM uops indicate the 'end of a macro-instruction' and play a crucial role in the processor's control flow and recovery mechanisms.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Retired uops except the last uop of each instruction.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -2127,6 +2303,16 @@
"UMask": "0x80",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number of uops retired that originated from a loop stream detector.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc2",
+ "EventName": "UOPS_RETIRED.LSD",
+ "PublicDescription": "Counts the number of uops retired that originated from a loop stream detector. Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.",
"Counter": "0,1,2,3,4,5,6,7",
@@ -2161,6 +2347,16 @@
"UMask": "0x4",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "UOPS_RETIRED.NANO_CODE",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc2",
+ "EventName": "UOPS_RETIRED.NANO_CODE",
+ "PublicDescription": "UOPS_RETIRED.NANO_CODE Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
diff --git a/tools/perf/pmu-events/arch/x86/pantherlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/pantherlake/virtual-memory.json
index 8d56c16b2a39..8f3dd36707dc 100644
--- a/tools/perf/pmu-events/arch/x86/pantherlake/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/pantherlake/virtual-memory.json
@@ -78,6 +78,16 @@
"UMask": "0x4",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to a 4K page.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x08",
+ "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
+ "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Page walks completed due to a demand data load to a 4K page.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -178,6 +188,16 @@
"UMask": "0x4",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to a 4K page.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x49",
+ "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
+ "PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Page walks completed due to a demand data store to a 4K page.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
@@ -267,6 +287,16 @@
"UMask": "0x4",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to a 4K page.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x85",
+ "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
+ "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3,4,5,6,7,8,9",
--
2.53.0.414.gf7e9f6c205-goog
More information about the linux-arm-kernel
mailing list