[rocprofiler-sdk] Add derived metrics for Navi4 (#238)

* add more derived metrics for navi4.

* addr comments

* addr comments, and add more derived counters.

* EOF.

* misc.

* remove duplicate counter.

* misc.

* Remove gfx12 architecture definition for ldslatency

* remove extra architectures for gfx12.

* use wgp for normalization

* move these changes to another PR.

---------

Co-authored-by: Venkateshwar Reddy Kandula <venkateshwar.kandula1306@gmail.com>

projects/rocprofiler-sdk/source/share/rocprofiler-sdk/counter_defs.yaml

@@ -467,6 +467,9 @@ rocprofiler-sdk:
       - gfx941
       - gfx942
       - gfx950
+      - gfx12
+      - gfx1200
+      - gfx1201
       expression: simd_count
   - name: CpUtil
     description: 'Unit: percent'
@@ -627,6 +630,9 @@ rocprofiler-sdk:
       - gfx941
       - gfx942
       - gfx950
+      - gfx12
+      - gfx1200
+      - gfx1201
       expression: FETCH_SIZE
   - name: FlatLDSInsts
     description: The average number of FLAT instructions that read or write to LDS executed per work item (affected by flow
@@ -1037,6 +1043,12 @@ rocprofiler-sdk:
       - gfx1102
       block: GL2C
       event: 88
+    - architectures:
+      - gfx12
+      - gfx1200
+      - gfx1201
+      block: GL2C
+      event: 122
   - name: GL2C_MC_WRREQ_sum
     description: Number of transactions (either 32-byte or 64-byte) going over the GL2C_MC_wrreq interface. Sum over GL2C
       instances.
@@ -1107,6 +1119,9 @@ rocprofiler-sdk:
       - gfx1100
       - gfx1101
       - gfx1102
+      - gfx12
+      - gfx1200
+      - gfx1201
       expression: reduce(GL2C_MC_WRREQ_STALL,max)
   - name: GPUBusy
     description: The percentage of time GPU was busy.
@@ -1127,6 +1142,9 @@ rocprofiler-sdk:
       - gfx906
       - gfx908
       - gfx90a
+      - gfx12
+      - gfx1200
+      - gfx1201
       expression: 100*reduce(GRBM_GUI_ACTIVE,max)/reduce(GRBM_COUNT,max)
   - name: GPU_UTIL
     description: Percentage of the time that GUI is active
@@ -1498,7 +1516,16 @@ rocprofiler-sdk:
     definitions:
     - architectures:
       - gfx90a
+      - gfx940
+      - gfx941
+      - gfx942
+      - gfx950
       expression: 100*reduce(SQ_LDS_IDX_ACTIVE,sum)/(reduce(GRBM_GUI_ACTIVE,max)*CU_NUM)
+    - architectures:
+      - gfx12
+      - gfx1200
+      - gfx1201
+      expression: 100*reduce(SQC_LDS_IDX_ACTIVE,sum)/(reduce(GRBM_GUI_ACTIVE,max)*(SIMD_NUM/4))
   - name: MAX_WAVE_SIZE
     description: Max wave size constant
     properties: []
@@ -1532,6 +1559,9 @@ rocprofiler-sdk:
       - gfx1100
       - gfx1101
       - gfx1102
+      - gfx12
+      - gfx1200
+      - gfx1201
       expression: reduce(SQ_WAVE_CYCLES,sum)/reduce(SQ_BUSY_CYCLES,sum)
     - architectures:
       - gfx90a
@@ -1549,6 +1579,9 @@ rocprofiler-sdk:
       - gfx1100
       - gfx1101
       - gfx1102
+      - gfx12
+      - gfx1200
+      - gfx1201
       expression: reduce(SQ_WAVE_CYCLES,sum)/reduce(GRBM_GUI_ACTIVE,max)/CU_NUM
     - architectures:
       - gfx10
@@ -1576,6 +1609,9 @@ rocprofiler-sdk:
       - gfx1100
       - gfx1101
       - gfx1102
+      - gfx12
+      - gfx1200
+      - gfx1201
       expression: 100*reduce(SQ_WAVE_CYCLES,sum)/reduce(GRBM_GUI_ACTIVE,max)/CU_NUM/32
     - architectures:
       - gfx90a
@@ -1604,6 +1640,9 @@ rocprofiler-sdk:
       - gfx906
       - gfx908
       - gfx90a
+      - gfx12
+      - gfx1200
+      - gfx1201
       expression: 100*reduce(TA_TA_BUSY,max)/reduce(GRBM_GUI_ACTIVE,max)
   - name: MemUnitStalled
     description: 'The percentage of GPUTime the memory unit is stalled. Try reducing the number or size of fetches and writes
@@ -1742,6 +1781,9 @@ rocprofiler-sdk:
       - gfx906
       - gfx908
       - gfx90a
+      - gfx12
+      - gfx1200
+      - gfx1201
       expression: reduce(SQ_INSTS_SALU,sum)/reduce(SQ_WAVES,sum)
   - name: SE_NUM
     description: SE_NUM
@@ -1766,6 +1808,9 @@ rocprofiler-sdk:
       - gfx941
       - gfx942
       - gfx950
+      - gfx12
+      - gfx1200
+      - gfx1201
       expression: array_count/simd_arrays_per_engine
   - name: SFetchInsts
     description: The average number of scalar fetch instructions from the video memory executed per work-item (affected by
@@ -1786,6 +1831,9 @@ rocprofiler-sdk:
       - gfx906
       - gfx908
       - gfx90a
+      - gfx12
+      - gfx1200
+      - gfx1201
       expression: reduce(SQ_INSTS_SMEM,sum)/reduce(SQ_WAVES,sum)
   - name: SPI_CSN_BUSY
     description: Number of clocks with outstanding waves (SPI or SH). Requires SPI_DEBUG_CNTL.DEBUG_PIPE_SEL to select source,
@@ -2725,6 +2773,22 @@ rocprofiler-sdk:
       - gfx950
       block: SQ
       event: 271
+    - architectures:
+      - gfx12
+      - gfx1200
+      - gfx1201
+      block: SQ
+      event: 302
+  - name: SQC_ICACHE_MISSES
+    description: Number of cache misses, includes uncached requests. {per-Bank, nondeterministic, C2}
+    properties: []
+    definitions:
+    - architectures:
+      - gfx12
+      - gfx1200
+      - gfx1201
+      block: SQ
+      event: 303
   - name: SQC_ICACHE_INPUT_VALID_READYB
     description: ' Input stalled by SQC (per-SQ, nondeterministic, unwindowed)'
     properties: []
@@ -2775,6 +2839,12 @@ rocprofiler-sdk:
       - gfx950
       block: SQ
       event: 270
+    - architectures:
+      - gfx12
+      - gfx1200
+      - gfx1201
+      block: SQ
+      event: 301
   - name: SQC_LDS_BANK_CONFLICT
     description: Number of cycles LDS is stalled by bank conflicts. (emulated, C1)
     properties: []
@@ -5434,6 +5504,27 @@ rocprofiler-sdk:
       - gfx950
       block: SQ
       event: 16
+  - name: SQ_INST_CYCLES_VALU
+    description: Number of cycles needed to execute VALU operations (SIMD cycles), where there is overlapping V_OP32_1 
+     and V_OP32_T instruction, count them separately. 
+    properties: []
+    definitions:
+    - architectures:
+      - gfx1201
+      - gfx12
+      - gfx1200
+      block: SQ
+      event: 99
+  - name: SQ_INSTS_VEC32_LEVEL_LDS
+    description: Number of in-flight wave32 LDS (indexed, flat) instructions issued.{level, nondeterministic}
+    properties: []
+    definitions:
+    - architectures:
+      - gfx1201
+      - gfx12
+      - gfx1200
+      block: SQ
+      event: 250
   - name: ScaPipeIssueUtil
     description: 'Unit: percent'
     properties: []
@@ -9850,6 +9941,26 @@ rocprofiler-sdk:
     - architectures:
       - gfx950
       expression: reduce(TCP_UTCL1_STALL_UTCL2_REQ_OUT_OF_CREDITS,sum)
+  - name: TCP_REQ
+    description: Total cache line accesses
+    properties: []
+    definitions:
+    - architectures:
+      - gfx12
+      - gfx1200
+      - gfx1201
+      block: TCP
+      event: 9
+  - name: TCP_REQ_MISS
+    description: Total cache requests that missed
+    properties: []
+    definitions:
+    - architectures:
+      - gfx12
+      - gfx1200
+      - gfx1201
+      block: TCP
+      event: 17
   - name: TD_ATOMIC_WAVEFRONT
     description: Count the wavefronts with opcode = atomic.
     properties: []
@@ -10159,6 +10270,11 @@ rocprofiler-sdk:
       - gfx942
       - gfx950
       expression: 100*reduce(SQ_ACTIVE_INST_VALU,sum)/CU_NUM/reduce(GRBM_GUI_ACTIVE,max)
+    - architectures:
+      - gfx12
+      - gfx1200
+      - gfx1201
+      expression: 100*reduce(SQ_INST_CYCLES_VALU,sum)/(SIMD_NUM/4)/reduce(GRBM_GUI_ACTIVE,max)
   - name: VALUInsts
     description: The average number of vector ALU instructions executed per work-item (affected by flow control).
     properties: []
@@ -10177,6 +10293,9 @@ rocprofiler-sdk:
       - gfx906
       - gfx908
       - gfx90a
+      - gfx12
+      - gfx1200
+      - gfx1201
       expression: reduce(SQ_INSTS_VALU,sum)/reduce(SQ_WAVES,sum)
   - name: VALUUtilization
     description: 'The percentage of active vector ALU threads in a wave. A lower number can mean either more thread divergence
@@ -10255,6 +10374,11 @@ rocprofiler-sdk:
       - gfx941
       - gfx942
       expression: 100*reduce(SQ_ACTIVE_INST_VALU,sum)/(reduce(GRBM_GUI_ACTIVE,max)*CU_NUM)
+    - architectures:
+      - gfx12
+      - gfx1200
+      - gfx1201
+      expression: 100*reduce(SQ_INST_CYCLES_VALU,sum)/(reduce(GRBM_GUI_ACTIVE,max)*(SIMD_NUM/4))
   - name: VmemLatency
     description: 'Unit: cycles'
     properties: []
@@ -10412,6 +10536,9 @@ rocprofiler-sdk:
       - gfx906
       - gfx908
       - gfx90a
+      - gfx12
+      - gfx1200
+      - gfx1201
       expression: reduce(SQ_WAVES,sum)
   - name: WriteSize
     description: The total kilobytes written to the video memory. This is measured with all extra fetches and any cache or
@@ -10450,6 +10577,9 @@ rocprofiler-sdk:
       - gfx1100
       - gfx1101
       - gfx1102
+      - gfx12
+      - gfx1200
+      - gfx1201
       expression: 100*GL2C_WRREQ_STALL_max/reduce(GRBM_GUI_ACTIVE,max)
   - name: sL1dCacheHitRate
     description: 'Unit: percent'
@@ -10555,3 +10685,13 @@ rocprofiler-sdk:
       - gfx942
       - gfx950
       expression: TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum/TCP_GATE_EN1_sum
+  - name: L0CacheHit
+    description: The percentage of read requests that hit the data in the L0 cache. The L0 cache contains vector data, which
+      is data that may vary in each thread across the wavefront. Value range 0% (no hit) to 100% (optimal).
+    properties: []
+    definitions:
+    - architectures:
+      - gfx12
+      - gfx1200
+      - gfx1201
+      expression: (1-(reduce(TCP_REQ_MISS,sum)/reduce(TCP_REQ,sum)))*100