perf vendor events intel: Add core event list for Tigerlake

Add JSON core events for Tigerlake to perf.

Based on JSON list v1.03:

https://download.01.org/perfmon/TGL/Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210719070058.4159-1-yao.jin@linux.intel.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/pmu-events/arch/x86/mapfile.csv

@@ -36,7 +36,7 @@ GenuineIntel-6-55-[01234],v1,skylakex,core
 GenuineIntel-6-55-[56789ABCDEF],v1,cascadelakex,core
 GenuineIntel-6-7D,v1,icelake,core
 GenuineIntel-6-7E,v1,icelake,core
-GenuineIntel-6-8[CD],v1,icelake,core
+GenuineIntel-6-8[CD],v1,tigerlake,core
 GenuineIntel-6-A7,v1,icelake,core
 GenuineIntel-6-6A,v1,icelakex,core
 GenuineIntel-6-6C,v1,icelakex,core

tools/perf/pmu-events/arch/x86/tigerlake/floating-point.json

+[
+    {
+        "BriefDescription": "Counts all microcode FP assists.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc1",
+        "EventName": "ASSISTS.FP",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "PublicDescription": "Counts all microcode Floating Point assists.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "SampleAfterValue": "100003",
+        "UMask": "0x4"
+    },
+    {
+        "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 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "PublicDescription": "Counts number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x8"
+    },
+    {
+        "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "SampleAfterValue": "100003",
+        "UMask": "0x10"
+    },
+    {
+        "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "SampleAfterValue": "100003",
+        "UMask": "0x20"
+    },
+    {
+        "BriefDescription": "Counts 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 SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "SampleAfterValue": "100003",
+        "UMask": "0x40"
+    },
+    {
+        "BriefDescription": "Counts 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 16 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "SampleAfterValue": "100003",
+        "UMask": "0x80"
+    },
+    {
+        "BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "SampleAfterValue": "100003",
+        "UMask": "0x2"
+    }
+]
\ No newline at end of file

tools/perf/pmu-events/arch/x86/tigerlake/other.json

+[
+    {
+        "BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc1",
+        "EventName": "ASSISTS.ANY",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware Examples include AD (page Access Dirty), FP and AVX related assists.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7"
+    },
+    {
+        "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the Non-AVX turbo schedule.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x28",
+        "EventName": "CORE_POWER.LVL0_TURBO_LICENSE",
+        "PEBScounters": "0,1,2,3",
+        "PublicDescription": "Counts Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes.",
+        "SampleAfterValue": "200003",
+        "UMask": "0x7"
+    },
+    {
+        "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX2 turbo schedule.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x28",
+        "EventName": "CORE_POWER.LVL1_TURBO_LICENSE",
+        "PEBScounters": "0,1,2,3",
+        "PublicDescription": "Counts Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions.",
+        "SampleAfterValue": "200003",
+        "UMask": "0x18"
+    },
+    {
+        "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x28",
+        "EventName": "CORE_POWER.LVL2_TURBO_LICENSE",
+        "PEBScounters": "0,1,2,3",
+        "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server microarchtecture).  This includes high current AVX 512-bit instructions.",
+        "SampleAfterValue": "200003",
+        "UMask": "0x20"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10003C0001",
+        "Offcore": "1",
+        "PEBScounters": "0,1,2,3",
+        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x8003C0001",
+        "Offcore": "1",
+        "PEBScounters": "0,1,2,3",
+        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10003C0002",
+        "Offcore": "1",
+        "PEBScounters": "0,1,2,3",
+        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts streaming stores that have any type of response.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10800",
+        "Offcore": "1",
+        "PEBScounters": "0,1,2,3",
+        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Number of PREFETCHNTA instructions executed.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x32",
+        "EventName": "SW_PREFETCH_ACCESS.NTA",
+        "PEBScounters": "0,1,2,3",
+        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Number of PREFETCHW instructions executed.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x32",
+        "EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
+        "PEBScounters": "0,1,2,3",
+        "PublicDescription": "Counts the number of PREFETCHW instructions executed.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x8"
+    },
+    {
+        "BriefDescription": "Number of PREFETCHT0 instructions executed.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x32",
+        "EventName": "SW_PREFETCH_ACCESS.T0",
+        "PEBScounters": "0,1,2,3",
+        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x32",
+        "EventName": "SW_PREFETCH_ACCESS.T1_T2",
+        "PEBScounters": "0,1,2,3",
+        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "TMA slots where no uops were being issued due to lack of back-end resources.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa4",
+        "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "PublicDescription": "Counts the number of Top-down Microarchitecture Analysis (TMA) method's  slots where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.",
+        "SampleAfterValue": "10000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "TMA slots wasted due to incorrect speculation by branch mispredictions",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa4",
+        "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by branch mispredictions. This event estimates number of operations that were issued but not retired from the specualtive path as well as the out-of-order engine recovery past a branch misprediction.",
+        "SampleAfterValue": "10000003",
+        "UMask": "0x8"
+    },
+    {
+        "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event",
+        "CollectPEBSRecord": "2",
+        "Counter": "Fixed counter 3",
+        "EventName": "TOPDOWN.SLOTS",
+        "PEBScounters": "35",
+        "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).",
+        "SampleAfterValue": "10000003",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "TMA slots available for an unhalted logical processor. General counter - architectural event",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa4",
+        "EventName": "TOPDOWN.SLOTS_P",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.",
+        "SampleAfterValue": "10000003",
+        "UMask": "0x1"
+    }
+]
\ No newline at end of file