redonkable
/
alistair23-linux
1
0
Fork 0
Code Releases Activity

perf vendor events: Add JSON metrics for Cascadelake server 

Add JSON metrics (based on event list v1) for Cascadelake server

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/3ab97c73-c197-8555-1a35-b54636e667e6@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
hifive-unleashed-5.1
Kan Liang 2018-11-15 08:33:27 -05:00 committed by Arnaldo Carvalho de Melo
parent 3b54411a44
commit ecd94f1be3
11 changed files with 31347 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10172
tools/perf/pmu-events/arch/x86/cascadelakex/cache.json 100644
View File

File diff suppressed because it is too large Load Diff

164
tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json 100644
View File

@ -0,0 +1,164 @@
[
{
"BriefDescription": "Instructions Per Cycle (per logical thread)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "TopDownL1",
"MetricName": "IPC"
},
{
"BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
"MetricGroup": "Pipeline",
"MetricName": "UPI"
},
{
"BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
"MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )",
"MetricGroup": "Frontend",
"MetricName": "IFetch_Line_Utilization"
},
{
"BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
"MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
"MetricGroup": "DSB; Frontend_Bandwidth",
"MetricName": "DSB_Coverage"
},
{
"BriefDescription": "Cycles Per Instruction (threaded)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
"MetricGroup": "Pipeline;Summary",
"MetricName": "CPI"
},
{
"BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Summary",
"MetricName": "CLKS"
},
{
"BriefDescription": "Total issue-pipeline slots",
"MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "TopDownL1",
"MetricName": "SLOTS"
},
{
"BriefDescription": "Total number of retired Instructions",
"MetricExpr": "INST_RETIRED.ANY",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
"BriefDescription": "Instructions Per Cycle (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "SMT",
"MetricName": "CoreIPC"
},
{
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
"MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
"MetricGroup": "Pipeline;Ports_Utilization",
"MetricName": "ILP"
},
{
"BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
"MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)",
"MetricGroup": "Unknown_Branches",
"MetricName": "BAClear_Cost"
},
{
"BriefDescription": "Core actual clocks when any thread is active on the physical core",
"MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "SMT",
"MetricName": "CORE_CLKS"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS_PS + MEM_LOAD_RETIRED.FB_HIT_PS )",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
},
{
"BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
"MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
"MetricGroup": "Memory_Bound;Memory_BW",
"MetricName": "MLP"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )",
"MetricGroup": "TLB",
"MetricName": "Page_Walks_Utilization"
},
{
"BriefDescription": "Average CPU Utilization",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
"MetricGroup": "Summary",
"MetricName": "CPU_Utilization"
},
{
"BriefDescription": "Giga Floating Point Operations Per Second",
"MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
"MetricGroup": "FLOPS;Summary",
"MetricName": "GFLOPs"
},
{
"BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
"MetricGroup": "Power",
"MetricName": "Turbo_Utilization"
},
{
"BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
"MetricGroup": "SMT;Summary",
"MetricName": "SMT_2T_Utilization"
},
{
"BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
"MetricGroup": "Summary",
"MetricName": "Kernel_Utilization"
},
{
"BriefDescription": "C3 residency percent per core",
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C3_Core_Residency"
},
{
"BriefDescription": "C6 residency percent per core",
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C6_Core_Residency"
},
{
"BriefDescription": "C7 residency percent per core",
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C7_Core_Residency"
},
{
"BriefDescription": "C2 residency percent per package",
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C2_Pkg_Residency"
},
{
"BriefDescription": "C3 residency percent per package",
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C3_Pkg_Residency"
},
{
"BriefDescription": "C6 residency percent per package",
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C6_Pkg_Residency"
},
{
"BriefDescription": "C7 residency percent per package",
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C7_Pkg_Residency"
}
]

85
tools/perf/pmu-events/arch/x86/cascadelakex/floating-point.json 100644
View File

@ -0,0 +1,85 @@
[
{
"EventCode": "0xC7",
"UMask": "0x1",
"BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC7",
"UMask": "0x2",
"BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC7",
"UMask": "0x4",
"BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT14 RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC7",
"UMask": "0x8",
"BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 4 calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC7",
"UMask": "0x10",
"BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 4 calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC7",
"UMask": "0x20",
"BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 8 calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC7",
"UMask": "0x40",
"BriefDescription": "Number of SSE/AVX computational 512-bit packed double 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 double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 8 calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC7",
"UMask": "0x80",
"BriefDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 16 calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xCA",
"UMask": "0x1e",
"BriefDescription": "Cycles with any input/output SSE or FP assist",
"Counter": "0,1,2,3",
"EventName": "FP_ASSIST.ANY",
"CounterMask": "1",
"PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
}
]

482
tools/perf/pmu-events/arch/x86/cascadelakex/frontend.json 100644
View File

@ -0,0 +1,482 @@
[
{
"EventCode": "0x79",
"UMask": "0x4",
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"EventName": "IDQ.MITE_CYCLES",
"CounterMask": "1",
"PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x4",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"EventName": "IDQ.MITE_UOPS",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x8",
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
"Counter": "0,1,2,3",
"EventName": "IDQ.DSB_CYCLES",
"CounterMask": "1",
"PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x8",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"Counter": "0,1,2,3",
"EventName": "IDQ.DSB_UOPS",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x10",
"BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"EventName": "IDQ.MS_DSB_CYCLES",
"CounterMask": "1",
"PublicDescription": "Counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x18",
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"Counter": "0,1,2,3",
"EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
"CounterMask": "1",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x18",
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
"Counter": "0,1,2,3",
"EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
"CounterMask": "4",
"PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x20",
"BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"EventName": "IDQ.MS_MITE_UOPS",
"PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x24",
"BriefDescription": "Cycles MITE is delivering any Uop",
"Counter": "0,1,2,3",
"EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
"CounterMask": "1",
"PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x24",
"BriefDescription": "Cycles MITE is delivering 4 Uops",
"Counter": "0,1,2,3",
"EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
"CounterMask": "4",
"PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x30",
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"EventName": "IDQ.MS_CYCLES",
"CounterMask": "1",
"PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x30",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"EventName": "IDQ.MS_UOPS",
"PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EdgeDetect": "1",
"EventCode": "0x79",
"UMask": "0x30",
"BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
"Counter": "0,1,2,3",
"EventName": "IDQ.MS_SWITCHES",
"CounterMask": "1",
"PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x80",
"UMask": "0x4",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
"Counter": "0,1,2,3",
"EventName": "ICACHE_16B.IFDATA_STALL",
"PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x83",
"UMask": "0x1",
"BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
"Counter": "0,1,2,3",
"EventName": "ICACHE_64B.IFTAG_HIT",
"SampleAfterValue": "200003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x83",
"UMask": "0x2",
"BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
"Counter": "0,1,2,3",
"EventName": "ICACHE_64B.IFTAG_MISS",
"SampleAfterValue": "200003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x83",
"UMask": "0x4",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"Counter": "0,1,2,3",
"EventName": "ICACHE_64B.IFTAG_STALL",
"SampleAfterValue": "200003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"Invert": "1",
"EventCode": "0x9C",
"UMask": "0x1",
"BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
"Counter": "0,1,2,3",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"CounterMask": "1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x9C",
"UMask": "0x1",
"BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
"Counter": "0,1,2,3",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
"CounterMask": "1",
"PublicDescription": "Cycles with less than 3 uops delivered by the front-end.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x9C",
"UMask": "0x1",
"BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
"Counter": "0,1,2,3",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
"CounterMask": "2",
"PublicDescription": "Cycles with less than 2 uops delivered by the front-end.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x9C",
"UMask": "0x1",
"BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
"Counter": "0,1,2,3",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
"CounterMask": "3",
"PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x9C",
"UMask": "0x1",
"BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
"Counter": "0,1,2,3",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
"CounterMask": "4",
"PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x9C",
"UMask": "0x1",
"BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
"Counter": "0,1,2,3",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
"PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xAB",
"UMask": "0x2",
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
"Counter": "0,1,2,3",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "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.",
"PEBS": "1",
"MSRValue": "0x400406",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.",
"PEBS": "1",
"MSRValue": "0x200206",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall.",
"PEBS": "1",
"MSRValue": "0x400206",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
"PEBS": "1",
"MSRValue": "0x15",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.STLB_MISS",
"MSRIndex": "0x3F7",
"PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. ",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "Retired Instructions who experienced iTLB true miss.",
"PEBS": "1",
"MSRValue": "0x14",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.ITLB_MISS",
"MSRIndex": "0x3F7",
"PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.",
"PEBS": "1",
"MSRValue": "0x13",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.L2_MISS",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
"PEBS": "1",
"MSRValue": "0x12",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.L1I_MISS",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss.",
"PEBS": "1",
"MSRValue": "0x11",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.DSB_MISS",
"MSRIndex": "0x3F7",
"PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. ",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.",
"PEBS": "1",
"MSRValue": "0x300206",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.",
"PEBS": "1",
"MSRValue": "0x100206",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
"MSRIndex": "0x3F7",
"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.",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "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.",
"PEBS": "1",
"MSRValue": "0x420006",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "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.",
"PEBS": "1",
"MSRValue": "0x410006",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "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.",
"PEBS": "1",
"MSRValue": "0x408006",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "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.",
"PEBS": "1",
"MSRValue": "0x404006",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.",
"PEBS": "1",
"MSRValue": "0x402006",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
"MSRIndex": "0x3F7",
"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.",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.",
"PEBS": "1",
"MSRValue": "0x401006",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
"MSRIndex": "0x3F7",
"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.",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.",
"PEBS": "1",
"MSRValue": "0x400806",
"Counter": "0,1,2,3",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
"MSRIndex": "0x3F7",
"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.",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
}
]

9909
tools/perf/pmu-events/arch/x86/cascadelakex/memory.json 100644
View File

File diff suppressed because it is too large Load Diff

8908
tools/perf/pmu-events/arch/x86/cascadelakex/other.json 100644
View File

File diff suppressed because it is too large Load Diff

969
tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json 100644
View File

@ -0,0 +1,969 @@
[
{
"EventCode": "0x00",
"UMask": "0x1",
"BriefDescription": "Instructions retired from execution.",
"Counter": "Fixed counter 0",
"EventName": "INST_RETIRED.ANY",
"PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
"SampleAfterValue": "2000003",
"CounterHTOff": "Fixed counter 0"
},
{
"EventCode": "0x00",
"UMask": "0x2",
"BriefDescription": "Core cycles when the thread is not in halt state",
"Counter": "Fixed counter 1",
"EventName": "CPU_CLK_UNHALTED.THREAD",
"PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
"SampleAfterValue": "2000003",
"CounterHTOff": "Fixed counter 1"
},
{
"EventCode": "0x00",
"UMask": "0x2",
"BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
"Counter": "Fixed counter 1",
"EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
"AnyThread": "1",
"SampleAfterValue": "2000003",
"CounterHTOff": "Fixed counter 1"
},
{
"EventCode": "0x00",
"UMask": "0x3",
"BriefDescription": "Reference cycles when the core is not in halt state.",
"Counter": "Fixed counter 2",
"EventName": "CPU_CLK_UNHALTED.REF_TSC",
"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. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. 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.",
"SampleAfterValue": "2000003",
"CounterHTOff": "Fixed counter 2"
},
{
"EventCode": "0x03",
"UMask": "0x2",
"BriefDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded .",
"Counter": "0,1,2,3",
"EventName": "LD_BLOCKS.STORE_FORWARD",
"PublicDescription": "Counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:a. preceding store conflicts with the load (incomplete overlap),b. store forwarding is impossible due to u-arch limitations,c. preceding lock RMW operations are not forwarded,d. store has the no-forward bit set (uncacheable/page-split/masked stores),e. all-blocking stores are used (mostly, fences and port I/O), and others.The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x03",
"UMask": "0x8",
"BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use",
"Counter": "0,1,2,3",
"EventName": "LD_BLOCKS.NO_SR",
"PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x07",
"UMask": "0x1",
"BriefDescription": "False dependencies in MOB due to partial compare on address.",
"Counter": "0,1,2,3",
"EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS",
"PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x0D",
"UMask": "0x1",
"BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)",
"Counter": "0,1,2,3",
"EventName": "INT_MISC.RECOVERY_CYCLES",
"PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x0D",
"UMask": "0x1",
"BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
"Counter": "0,1,2,3",
"EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
"AnyThread": "1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x0D",
"UMask": "0x80",
"BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.",
"Counter": "0,1,2,3",
"EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"Invert": "1",
"EventCode": "0x0E",
"UMask": "0x1",
"BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
"Counter": "0,1,2,3",
"EventName": "UOPS_ISSUED.STALL_CYCLES",
"CounterMask": "1",
"PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x0E",
"UMask": "0x1",
"BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)",
"Counter": "0,1,2,3",
"EventName": "UOPS_ISSUED.ANY",
"PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x0E",
"UMask": "0x2",
"BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.",
"Counter": "0,1,2,3",
"EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH",
"PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x0E",
"UMask": "0x20",
"BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.",
"Counter": "0,1,2,3",
"EventName": "UOPS_ISSUED.SLOW_LEA",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x14",
"UMask": "0x1",
"BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
"Counter": "0,1,2,3",
"EventName": "ARITH.DIVIDER_ACTIVE",
"CounterMask": "1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x3C",
"UMask": "0x0",
"BriefDescription": "Thread cycles when thread is not in halt state",
"Counter": "0,1,2,3",
"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.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x3C",
"UMask": "0x0",
"BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
"Counter": "0,1,2,3",
"EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
"AnyThread": "1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EdgeDetect": "1",
"EventCode": "0x3C",
"UMask": "0x0",
"BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.",
"Counter": "0,1,2,3",
"EventName": "CPU_CLK_UNHALTED.RING0_TRANS",
"CounterMask": "1",
"PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x3C",
"UMask": "0x1",
"BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
"Counter": "0,1,2,3",
"EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK",
"SampleAfterValue": "25003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x3C",
"UMask": "0x1",
"BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
"Counter": "0,1,2,3",
"EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
"AnyThread": "1",
"SampleAfterValue": "25003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x3C",
"UMask": "0x1",
"BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
"Counter": "0,1,2,3",
"EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
"AnyThread": "1",
"SampleAfterValue": "25003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x3C",
"UMask": "0x1",
"BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
"Counter": "0,1,2,3",
"EventName": "CPU_CLK_UNHALTED.REF_XCLK",
"SampleAfterValue": "25003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x3C",
"UMask": "0x2",
"BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.",
"Counter": "0,1,2,3",
"EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE",
"SampleAfterValue": "25003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x3C",
"UMask": "0x2",
"BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.",
"Counter": "0,1,2,3",
"EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
"SampleAfterValue": "25003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x4C",
"UMask": "0x1",
"BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.",
"Counter": "0,1,2,3",
"EventName": "LOAD_HIT_PRE.SW_PF",
"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.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x59",
"UMask": "0x1",
"BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.",
"Counter": "0,1,2,3",
"EventName": "PARTIAL_RAT_STALLS.SCOREBOARD",
"PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EdgeDetect": "1",
"Invert": "1",
"EventCode": "0x5E",
"UMask": "0x1",
"BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
"Counter": "0,1,2,3",
"EventName": "RS_EVENTS.EMPTY_END",
"CounterMask": "1",
"PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x5E",
"UMask": "0x1",
"BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
"Counter": "0,1,2,3",
"EventName": "RS_EVENTS.EMPTY_CYCLES",
"PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x87",
"UMask": "0x1",
"BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"Counter": "0,1,2,3",
"EventName": "ILD_STALL.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.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA1",
"UMask": "0x1",
"BriefDescription": "Cycles per thread when uops are executed in port 0",
"Counter": "0,1,2,3",
"EventName": "UOPS_DISPATCHED_PORT.PORT_0",
"PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA1",
"UMask": "0x2",
"BriefDescription": "Cycles per thread when uops are executed in port 1",
"Counter": "0,1,2,3",
"EventName": "UOPS_DISPATCHED_PORT.PORT_1",
"PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA1",
"UMask": "0x4",
"BriefDescription": "Cycles per thread when uops are executed in port 2",
"Counter": "0,1,2,3",
"EventName": "UOPS_DISPATCHED_PORT.PORT_2",
"PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA1",
"UMask": "0x8",
"BriefDescription": "Cycles per thread when uops are executed in port 3",
"Counter": "0,1,2,3",
"EventName": "UOPS_DISPATCHED_PORT.PORT_3",
"PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA1",
"UMask": "0x10",
"BriefDescription": "Cycles per thread when uops are executed in port 4",
"Counter": "0,1,2,3",
"EventName": "UOPS_DISPATCHED_PORT.PORT_4",
"PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA1",
"UMask": "0x20",
"BriefDescription": "Cycles per thread when uops are executed in port 5",
"Counter": "0,1,2,3",
"EventName": "UOPS_DISPATCHED_PORT.PORT_5",
"PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA1",
"UMask": "0x40",
"BriefDescription": "Cycles per thread when uops are executed in port 6",
"Counter": "0,1,2,3",
"EventName": "UOPS_DISPATCHED_PORT.PORT_6",
"PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA1",
"UMask": "0x80",
"BriefDescription": "Cycles per thread when uops are executed in port 7",
"Counter": "0,1,2,3",
"EventName": "UOPS_DISPATCHED_PORT.PORT_7",
"PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xa2",
"UMask": "0x1",
"BriefDescription": "Resource-related stall cycles",
"Counter": "0,1,2,3",
"EventName": "RESOURCE_STALLS.ANY",
"PublicDescription": "Counts resource-related stall cycles.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA2",
"UMask": "0x8",
"BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).",
"Counter": "0,1,2,3",
"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.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA3",
"UMask": "0x1",
"BriefDescription": "Cycles while L2 cache miss demand load is outstanding.",
"Counter": "0,1,2,3",
"EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
"CounterMask": "1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA3",
"UMask": "0x4",
"BriefDescription": "Total execution stalls.",
"Counter": "0,1,2,3",
"EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
"CounterMask": "4",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA3",
"UMask": "0x5",
"BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
"Counter": "0,1,2,3",
"EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
"CounterMask": "5",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA3",
"UMask": "0x8",
"BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
"Counter": "0,1,2,3",
"EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
"CounterMask": "8",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA3",
"UMask": "0xc",
"BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
"Counter": "0,1,2,3",
"EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
"CounterMask": "12",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA3",
"UMask": "0x10",
"BriefDescription": "Cycles while memory subsystem has an outstanding load.",
"Counter": "0,1,2,3",
"EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
"CounterMask": "16",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA3",
"UMask": "0x14",
"BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
"Counter": "0,1,2,3",
"EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
"CounterMask": "20",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xA6",
"UMask": "0x1",
"BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.",
"Counter": "0,1,2,3",
"EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS",
"PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA6",
"UMask": "0x2",
"BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.",
"Counter": "0,1,2,3",
"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.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA6",
"UMask": "0x4",
"BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.",
"Counter": "0,1,2,3",
"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.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA6",
"UMask": "0x8",
"BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.",
"Counter": "0,1,2,3",
"EventName": "EXE_ACTIVITY.3_PORTS_UTIL",
"PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA6",
"UMask": "0x10",
"BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.",
"Counter": "0,1,2,3",
"EventName": "EXE_ACTIVITY.4_PORTS_UTIL",
"PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA6",
"UMask": "0x40",
"BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.",
"Counter": "0,1,2,3",
"EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA8",
"UMask": "0x1",
"BriefDescription": "Number of Uops delivered by the LSD.",
"Counter": "0,1,2,3",
"EventName": "LSD.UOPS",
"PublicDescription": "Number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA8",
"UMask": "0x1",
"BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
"MSRValue": "0x00",
"Counter": "0,1,2,3",
"EventName": "LSD.CYCLES_4_UOPS",
"CounterMask": "4",
"PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA8",
"UMask": "0x1",
"BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
"Counter": "0,1,2,3",
"EventName": "LSD.CYCLES_ACTIVE",
"CounterMask": "1",
"PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xB1",
"UMask": "0x1",
"BriefDescription": "Cycles where at least 4 uops were executed per-thread",
"Counter": "0,1,2,3",
"EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
"CounterMask": "4",
"PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xB1",
"UMask": "0x1",
"BriefDescription": "Cycles where at least 3 uops were executed per-thread",
"Counter": "0,1,2,3",
"EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
"CounterMask": "3",
"PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xB1",
"UMask": "0x1",
"BriefDescription": "Cycles where at least 2 uops were executed per-thread",
"Counter": "0,1,2,3",
"EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
"CounterMask": "2",
"PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xB1",
"UMask": "0x1",
"BriefDescription": "Cycles where at least 1 uop was executed per-thread",
"Counter": "0,1,2,3",
"EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
"CounterMask": "1",
"PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"Invert": "1",
"EventCode": "0xB1",
"UMask": "0x1",
"BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
"Counter": "0,1,2,3",
"EventName": "UOPS_EXECUTED.STALL_CYCLES",
"CounterMask": "1",
"PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xB1",
"UMask": "0x1",
"BriefDescription": "Counts the number of uops to be executed per-thread each cycle.",
"Counter": "0,1,2,3",
"EventName": "UOPS_EXECUTED.THREAD",
"PublicDescription": "Number of uops to be executed per-thread each cycle.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xB1",
"UMask": "0x2",
"BriefDescription": "Number of uops executed on the core.",
"Counter": "0,1,2,3",
"EventName": "UOPS_EXECUTED.CORE",
"PublicDescription": "Number of uops executed from any thread.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"Invert": "1",
"EventCode": "0xB1",
"UMask": "0x2",
"BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
"Counter": "0,1,2,3",
"EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
"CounterMask": "1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xB1",
"UMask": "0x2",
"BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
"Counter": "0,1,2,3",
"EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
"CounterMask": "4",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xB1",
"UMask": "0x2",
"BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
"Counter": "0,1,2,3",
"EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
"CounterMask": "3",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xB1",
"UMask": "0x2",
"BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
"Counter": "0,1,2,3",
"EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
"CounterMask": "2",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xB1",
"UMask": "0x2",
"BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
"Counter": "0,1,2,3",
"EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
"CounterMask": "1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xB1",
"UMask": "0x10",
"BriefDescription": "Counts the number of x87 uops dispatched.",
"Counter": "0,1,2,3",
"EventName": "UOPS_EXECUTED.X87",
"PublicDescription": "Counts the number of x87 uops executed.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC0",
"UMask": "0x0",
"BriefDescription": "Number of instructions retired. General Counter - architectural event",
"Counter": "0,1,2,3",
"EventName": "INST_RETIRED.ANY_P",
"Errata": "SKL091, SKL044",
"PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC0",
"UMask": "0x1",
"BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution",
"PEBS": "2",
"Counter": "1",
"EventName": "INST_RETIRED.PREC_DIST",
"Errata": "SKL091, SKL044",
"PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled.",
"SampleAfterValue": "2000003",
"CounterHTOff": "1"
},
{
"Invert": "1",
"EventCode": "0xC0",
"UMask": "0x1",
"BriefDescription": "Number of cycles using always true condition applied to PEBS instructions retired event.",
"PEBS": "2",
"Counter": "0,2,3",
"EventName": "INST_RETIRED.TOTAL_CYCLES_PS",
"CounterMask": "10",
"Errata": "SKL091, SKL044",
"PublicDescription": "Number of cycles using an always true condition applied to PEBS instructions retired event. (inst_ret< 16)",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,2,3"
},
{
"EventCode": "0xC1",
"UMask": "0x3f",
"BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.",
"Counter": "0,1,2,3",
"EventName": "OTHER_ASSISTS.ANY",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"Invert": "1",
"EventCode": "0xC2",
"UMask": "0x2",
"BriefDescription": "Cycles with less than 10 actually retired uops.",
"Counter": "0,1,2,3",
"EventName": "UOPS_RETIRED.TOTAL_CYCLES",
"CounterMask": "10",
"PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"Invert": "1",
"EventCode": "0xC2",
"UMask": "0x2",
"BriefDescription": "Cycles without actually retired uops.",
"Counter": "0,1,2,3",
"EventName": "UOPS_RETIRED.STALL_CYCLES",
"CounterMask": "1",
"PublicDescription": "This event counts cycles without actually retired uops.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC2",
"UMask": "0x2",
"BriefDescription": "Retirement slots used.",
"Counter": "0,1,2,3",
"EventName": "UOPS_RETIRED.RETIRE_SLOTS",
"PublicDescription": "Counts the retirement slots used.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EdgeDetect": "1",
"EventCode": "0xC3",
"UMask": "0x1",
"BriefDescription": "Number of machine clears (nukes) of any type.",
"Counter": "0,1,2,3",
"EventName": "MACHINE_CLEARS.COUNT",
"CounterMask": "1",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC3",
"UMask": "0x4",
"BriefDescription": "Self-modifying code (SMC) detected.",
"Counter": "0,1,2,3",
"EventName": "MACHINE_CLEARS.SMC",
"PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC4",
"UMask": "0x0",
"BriefDescription": "All (macro) branch instructions retired.",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.ALL_BRANCHES",
"Errata": "SKL091",
"PublicDescription": "Counts all (macro) branch instructions retired.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC4",
"UMask": "0x1",
"BriefDescription": "Conditional branch instructions retired.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.CONDITIONAL",
"Errata": "SKL091",
"PublicDescription": "This event counts conditional branch instructions retired.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC4",
"UMask": "0x2",
"BriefDescription": "Direct and indirect near call instructions retired.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.NEAR_CALL",
"Errata": "SKL091",
"PublicDescription": "This event counts both direct and indirect near call instructions retired.",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC4",
"UMask": "0x4",
"BriefDescription": "All (macro) branch instructions retired.",
"PEBS": "2",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
"Errata": "SKL091",
"PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC4",
"UMask": "0x8",
"BriefDescription": "Return instructions retired.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.NEAR_RETURN",
"Errata": "SKL091",
"PublicDescription": "This event counts return instructions retired.",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC4",
"UMask": "0x10",
"BriefDescription": "Not taken branch instructions retired.",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.NOT_TAKEN",
"Errata": "SKL091",
"PublicDescription": "This event counts not taken branch instructions retired.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC4",
"UMask": "0x20",
"BriefDescription": "Taken branch instructions retired.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.NEAR_TAKEN",
"Errata": "SKL091",
"PublicDescription": "This event counts taken branch instructions retired.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC4",
"UMask": "0x40",
"BriefDescription": "Far branch instructions retired.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.FAR_BRANCH",
"Errata": "SKL091",
"PublicDescription": "This event counts far branch instructions retired.",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC5",
"UMask": "0x0",
"BriefDescription": "All mispredicted macro branch instructions retired.",
"Counter": "0,1,2,3",
"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.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC5",
"UMask": "0x1",
"BriefDescription": "Mispredicted conditional branch instructions retired.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_MISP_RETIRED.CONDITIONAL",
"PublicDescription": "This event counts mispredicted conditional branch instructions retired.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC5",
"UMask": "0x2",
"BriefDescription": "Mispredicted direct and indirect near call instructions retired.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_MISP_RETIRED.NEAR_CALL",
"PublicDescription": "Counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC5",
"UMask": "0x4",
"BriefDescription": "Mispredicted macro branch instructions retired.",
"PEBS": "2",
"Counter": "0,1,2,3",
"EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
"PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC5",
"UMask": "0x20",
"BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xCC",
"UMask": "0x20",
"BriefDescription": "Increments whenever there is an update to the LBR array.",
"Counter": "0,1,2,3",
"EventName": "ROB_MISC_EVENTS.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.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xCC",
"UMask": "0x40",
"BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.",
"Counter": "0,1,2,3",
"EventName": "ROB_MISC_EVENTS.PAUSE_INST",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xE6",
"UMask": "0x1",
"BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
"Counter": "0,1,2,3",
"EventName": "BACLEARS.ANY",
"PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
}
]

117
tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json 100644
View File

@ -0,0 +1,117 @@
[
{
"BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "LLC_MISSES.MEM_READ",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"Unit": "iMC"
},
{
"BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "LLC_MISSES.MEM_WRITE",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0xC",
"Unit": "iMC"
},
{
"BriefDescription": "Memory controller clock ticks",
"Counter": "0,1,2,3",
"EventName": "UNC_M_CLOCKTICKS",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode+C37",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "UNC_M_POWER_CHANNEL_PPD",
"MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
"MetricName": "power_channel_ppd %",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Cycles Memory is in self refresh power mode",
"Counter": "0,1,2,3",
"EventCode": "0x43",
"EventName": "UNC_M_POWER_SELF_REFRESH",
"MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
"MetricName": "power_self_refresh %",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Pre-charges due to page misses",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "iMC"
},
{
"BriefDescription": "Pre-charge for reads",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.RD",
"PerPkg": "1",
"UMask": "0x4",
"Unit": "iMC"
},
{
"BriefDescription": "Pre-charge for writes",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.WR",
"PerPkg": "1",
"UMask": "0x8",
"Unit": "iMC"
},
{
"BriefDescription": "Intel Optane DC persistent memory bandwidth read (MB/sec). Derived from unc_m_pmm_rpq_inserts",
"Counter": "0,1,2,3",
"EventCode": "0xE3",
"EventName": "UNC_M_PMM_BANDWIDTH.READ",
"PerPkg": "1",
"ScaleUnit": "6.103515625E-5MB/sec",
"Unit": "iMC"
},
{
"BriefDescription": "Intel Optane DC persistent memory bandwidth write (MB/sec). Derived from unc_m_pmm_wpq_inserts",
"Counter": "0,1,2,3",
"EventCode": "0xE7",
"EventName": "UNC_M_PMM_BANDWIDTH.WRITE",
"PerPkg": "1",
"ScaleUnit": "6.103515625E-5MB/sec",
"Unit": "iMC"
},
{
"BriefDescription": "Intel Optane DC persistent memory bandwidth total (MB/sec). Derived from unc_m_pmm_rpq_inserts",
"Counter": "0,1,2,3",
"EventCode": "0xE3",
"EventName": "UNC_M_PMM_BANDWIDTH.TOTAL",
"MetricExpr": "UNC_M_PMM_RPQ_INSERTS + UNC_M_PMM_WPQ_INSERTS",
"MetricName": "UNC_M_PMM_BANDWIDTH.TOTAL",
"PerPkg": "1",
"ScaleUnit": "6.103515625E-5MB/sec",
"Unit": "iMC"
},
{
"BriefDescription": "Intel Optane DC persistent memory read latency (ns). Derived from unc_m_pmm_rpq_occupancy.all",
"Counter": "0,1,2,3",
"EventCode": "0xE0",
"EventName": "UNC_M_PMM_READ_LATENCY",
"MetricExpr": "UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS / UNC_M_CLOCKTICKS",
"MetricName": "UNC_M_PMM_READ_LATENCY",
"PerPkg": "1",
"ScaleUnit": "6000000000ns",
"UMask": "0x1",
"Unit": "iMC"
}
]

255
tools/perf/pmu-events/arch/x86/cascadelakex/uncore-other.json 100644
View File

@ -0,0 +1,255 @@
[
{
"BriefDescription": "Uncore cache clock ticks",
"Counter": "0,1,2,3",
"EventName": "UNC_CHA_CLOCKTICKS",
"PerPkg": "1",
"Unit": "CHA"
},
{
"BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_cha_tor_inserts.ia_miss",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.UNCACHEABLE",
"Filter": "config1=0x40e33",
"PerPkg": "1",
"UMask": "0x21",
"Unit": "CHA"
},
{
"BriefDescription": "MMIO reads. Derived from unc_cha_tor_inserts.ia_miss",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.MMIO_READ",
"Filter": "config1=0x40040e33",
"PerPkg": "1",
"UMask": "0x21",
"Unit": "CHA"
},
{
"BriefDescription": "MMIO writes. Derived from unc_cha_tor_inserts.ia_miss",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_MISSES.MMIO_WRITE",
"Filter": "config1=0x40041e33",
"PerPkg": "1",
"UMask": "0x21",
"Unit": "CHA"
},
{
"BriefDescription": "Streaming stores (full cache line). Derived from unc_cha_tor_inserts.ia_miss",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.STREAMING_FULL",
"Filter": "config1=0x41833",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x21",
"Unit": "CHA"
},
{
"BriefDescription": "Streaming stores (partial cache line). Derived from unc_cha_tor_inserts.ia_miss",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
"Filter": "config1=0x41a33",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x21",
"Unit": "CHA"
},
{
"BriefDescription": "read requests from home agent",
"Counter": "0,1,2,3",
"EventCode": "0x50",
"EventName": "UNC_CHA_REQUESTS.READS",
"PerPkg": "1",
"UMask": "0x03",
"Unit": "CHA"
},
{
"BriefDescription": "read requests from local home agent",
"Counter": "0,1,2,3",
"EventCode": "0x50",
"EventName": "UNC_CHA_REQUESTS.READS_LOCAL",
"PerPkg": "1",
"UMask": "0x01",
"Unit": "CHA"
},
{
"BriefDescription": "read requests from remote home agent",
"Counter": "0,1,2,3",
"EventCode": "0x50",
"EventName": "UNC_CHA_REQUESTS.READS_REMOTE",
"PerPkg": "1",
"UMask": "0x02",
"Unit": "CHA"
},
{
"BriefDescription": "write requests from home agent",
"Counter": "0,1,2,3",
"EventCode": "0x50",
"EventName": "UNC_CHA_REQUESTS.WRITES",
"PerPkg": "1",
"UMask": "0x0C",
"Unit": "CHA"
},
{
"BriefDescription": "write requests from local home agent",
"Counter": "0,1,2,3",
"EventCode": "0x50",
"EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL",
"PerPkg": "1",
"UMask": "0x04",
"Unit": "CHA"
},
{
"BriefDescription": "write requests from remote home agent",
"Counter": "0,1,2,3",
"EventCode": "0x50",
"EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE",
"PerPkg": "1",
"UMask": "0x08",
"Unit": "CHA"
},
{
"BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UPI_DATA_BANDWIDTH_TX",
"PerPkg": "1",
"ScaleUnit": "7.11E-06Bytes",
"UMask": "0x0F",
"Unit": "UPI LL"
},
{
"BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0",
"Counter": "0,1",
"EventCode": "0x83",
"EventName": "LLC_MISSES.PCIE_READ",
"FCMask": "0x07",
"Filter": "ch_mask=0x1f",
"MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3",
"MetricName": "LLC_MISSES.PCIE_READ",
"PerPkg": "1",
"PortMask": "0x01",
"ScaleUnit": "4Bytes",
"UMask": "0x04",
"Unit": "IIO"
},
{
"BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0",
"Counter": "0,1",
"EventCode": "0x83",
"EventName": "LLC_MISSES.PCIE_WRITE",
"FCMask": "0x07",
"Filter": "ch_mask=0x1f",
"MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3",
"MetricName": "LLC_MISSES.PCIE_WRITE",
"PerPkg": "1",
"PortMask": "0x01",
"ScaleUnit": "4Bytes",
"UMask": "0x01",
"Unit": "IIO"
},
{
"BriefDescription": "PCI Express bandwidth writing at IIO, part 0",
"Counter": "0,1",
"EventCode": "0x83",
"EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0",
"FCMask": "0x07",
"MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3",
"MetricName": "LLC_MISSES.PCIE_WRITE",
"PerPkg": "1",
"PortMask": "0x01",
"ScaleUnit": "4Bytes",
"UMask": "0x01",
"Unit": "IIO"
},
{
"BriefDescription": "PCI Express bandwidth writing at IIO, part 1",
"Counter": "0,1",
"EventCode": "0x83",
"EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1",
"FCMask": "0x07",
"PerPkg": "1",
"PortMask": "0x02",
"ScaleUnit": "4Bytes",
"UMask": "0x01",
"Unit": "IIO"
},
{
"BriefDescription": "PCI Express bandwidth writing at IIO, part 2",
"Counter": "0,1",
"EventCode": "0x83",
"EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2",
"FCMask": "0x07",
"PerPkg": "1",
"PortMask": "0x04",
"ScaleUnit": "4Bytes",
"UMask": "0x01",
"Unit": "IIO"
},
{
"BriefDescription": "PCI Express bandwidth writing at IIO, part 3",
"Counter": "0,1",
"EventCode": "0x83",
"EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3",
"FCMask": "0x07",
"PerPkg": "1",
"PortMask": "0x08",
"ScaleUnit": "4Bytes",
"UMask": "0x01",
"Unit": "IIO"
},
{
"BriefDescription": "PCI Express bandwidth reading at IIO, part 0",
"Counter": "0,1",
"EventCode": "0x83",
"EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0",
"FCMask": "0x07",
"MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3",
"MetricName": "LLC_MISSES.PCIE_READ",
"PerPkg": "1",
"PortMask": "0x01",
"ScaleUnit": "4Bytes",
"UMask": "0x04",
"Unit": "IIO"
},
{
"BriefDescription": "PCI Express bandwidth reading at IIO, part 1",
"Counter": "0,1",
"EventCode": "0x83",
"EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1",
"FCMask": "0x07",
"PerPkg": "1",
"PortMask": "0x02",
"ScaleUnit": "4Bytes",
"UMask": "0x04",
"Unit": "IIO"
},
{
"BriefDescription": "PCI Express bandwidth reading at IIO, part 2",
"Counter": "0,1",
"EventCode": "0x83",
"EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2",
"FCMask": "0x07",
"PerPkg": "1",
"PortMask": "0x04",
"ScaleUnit": "4Bytes",
"UMask": "0x04",
"Unit": "IIO"
},
{
"BriefDescription": "PCI Express bandwidth reading at IIO, part 3",
"Counter": "0,1",
"EventCode": "0x83",
"EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3",
"FCMask": "0x07",
"PerPkg": "1",
"PortMask": "0x08",
"ScaleUnit": "4Bytes",
"UMask": "0x04",
"Unit": "IIO"
}
]

285
tools/perf/pmu-events/arch/x86/cascadelakex/virtual-memory.json 100644
View File

@ -0,0 +1,285 @@
[
{
"EventCode": "0x08",
"UMask": "0x1",
"BriefDescription": "Load misses in all DTLB levels that cause page walks",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x2",
"BriefDescription": "Page walk completed due to a demand data load to a 4K page",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x4",
"BriefDescription": "Page walk completed due to a demand data load to a 2M/4M page",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x8",
"BriefDescription": "Page walk completed due to a demand data load to a 1G page",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0xe",
"BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"PublicDescription": "Counts demand data loads that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x10",
"BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
"PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x10",
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
"CounterMask": "1",
"PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x20",
"BriefDescription": "Loads that miss the DTLB and hit the STLB.",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0x1",
"BriefDescription": "Store misses in all DTLB levels that cause page walks",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0x2",
"BriefDescription": "Page walk completed due to a demand data store to a 4K page",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0x4",
"BriefDescription": "Page walk completed due to a demand data store to a 2M/4M page",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0x8",
"BriefDescription": "Page walk completed due to a demand data store to a 1G page",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1G pages. The page walks can end with or without a page fault.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0xe",
"BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
"PublicDescription": "Counts demand data stores that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0x10",
"BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_PENDING",
"PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0x10",
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
"CounterMask": "1",
"PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0x20",
"BriefDescription": "Stores that miss the DTLB and hit the STLB.",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x4F",
"UMask": "0x10",
"BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.",
"Counter": "0,1,2,3",
"EventName": "EPT.WALK_PENDING",
"PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x1",
"BriefDescription": "Misses at all ITLB levels that cause page walks",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x2",
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts completed page walks (4K page size) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x4",
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts code misses in all ITLB levels that caused a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x8",
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0xe",
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"PublicDescription": "Counts completed page walks (2M and 4M page sizes) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x10",
"BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_PENDING",
"PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x10",
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.",
"MSRValue": "0x00",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_ACTIVE",
"CounterMask": "1",
"PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x20",
"BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.STLB_HIT",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xAE",
"UMask": "0x1",
"BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
"Counter": "0,1,2,3",
"EventName": "ITLB.ITLB_FLUSH",
"PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xBD",
"UMask": "0x1",
"BriefDescription": "DTLB flush attempts of the thread-specific entries",
"Counter": "0,1,2,3",
"EventName": "TLB_FLUSH.DTLB_THREAD",
"PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xBD",
"UMask": "0x20",
"BriefDescription": "STLB flush attempts",
"Counter": "0,1,2,3",
"EventName": "TLB_FLUSH.STLB_ANY",
"PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
}
]

1
tools/perf/pmu-events/arch/x86/mapfile.csv
View File

@ -32,3 +32,4 @@ GenuineIntel-6-2C,v2,westmereep-dp,core
GenuineIntel-6-25,v2,westmereep-sp,core
GenuineIntel-6-2F,v2,westmereex,core
GenuineIntel-6-55-[01234],v1,skylakex,core
GenuineIntel-6-55-[56789ABCDEF],v1,cascadelakex,core

1 Family-model Version Filename EventType
32 GenuineIntel-6-25 v2 westmereep-sp core
33 GenuineIntel-6-2F v2 westmereex core
34 GenuineIntel-6-55-[01234] v1 skylakex core
35 GenuineIntel-6-55-[56789ABCDEF] v1 cascadelakex core