Add CI workloads for MI300A_A1 and MI300X_A1

Signed-off-by: coleramos425 <colramos@amd.com>
This commit is contained in:
coleramos425 authored and Cole Ramos committed 2024-05-31 16:09:58 -05:00
1 bovenliggende 7d79fcc276
commit b8af814467
1580 files changed
+17548

No files matched your search

@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES
0,11995,1,144666,144666,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673339483,73517673347095,0,205430.0,205430.0,16384.0,65536.0,26688.0,2149344.0
1,11995,1,144666,144666,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673385473,73517673391482,0,178672.0,178672.0,16384.0,65536.0,13299.0,1048656.0
2,11995,1,144666,144666,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673363600,73517673369970,0,165003.0,165003.0,16384.0,65536.0,13060.0,1049392.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
2 0 11995 1 144666 144666 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673339483 73517673347095 0 205430.0 205430.0 16384.0 65536.0 26688.0 2149344.0
3 1 11995 1 144666 144666 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673385473 73517673391482 0 178672.0 178672.0 16384.0 65536.0 13299.0 1048656.0
4 2 11995 1 144666 144666 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673363600 73517673369970 0 165003.0 165003.0 16384.0 65536.0 13060.0 1049392.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES
0,11995,1,144677,144677,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673339483,73517673347095,0,0.0,0.0,0.0
1,11995,1,144677,144677,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673385473,73517673391482,0,0.0,0.0,0.0
2,11995,1,144677,144677,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673363600,73517673369970,0,0.0,0.0,0.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
2 0 11995 1 144677 144677 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673339483 73517673347095 0 0.0 0.0 0.0
3 1 11995 1 144677 144677 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673385473 73517673391482 0 0.0 0.0 0.0
4 2 11995 1 144677 144677 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673363600 73517673369970 0 0.0 0.0 0.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES
0,11995,1,144688,144688,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673339483,73517673347095,0,65536.0,340786.0,27207344.0
1,11995,1,144688,144688,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673385473,73517673391482,0,65536.0,277970.0,22234008.0
2,11995,1,144688,144688,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673363600,73517673369970,0,65536.0,215822.0,17342904.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
2 0 11995 1 144688 144688 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673339483 73517673347095 0 65536.0 340786.0 27207344.0
3 1 11995 1 144688 144688 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673385473 73517673391482 0 65536.0 277970.0 22234008.0
4 2 11995 1 144688 144688 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673363600 73517673369970 0 65536.0 215822.0 17342904.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES
0,11995,1,144699,144699,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673339483,73517673347095,0,32768.0,534566.0,42752356.0
1,11995,1,144699,144699,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673385473,73517673391482,0,32768.0,415032.0,33195988.0
2,11995,1,144699,144699,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673363600,73517673369970,0,32768.0,408920.0,32710300.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
2 0 11995 1 144699 144699 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673339483 73517673347095 0 32768.0 534566.0 42752356.0
3 1 11995 1 144699 144699 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673385473 73517673391482 0 32768.0 415032.0 33195988.0
4 2 11995 1 144699 144699 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673363600 73517673369970 0 32768.0 408920.0 32710300.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES
0,11995,1,144710,144710,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673339483,73517673347095,0,203242.0,203242.0,108439.0,812968.0,16384.0,13784518.0,249142.0,0.0,55564396.0
1,11995,1,144710,144710,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673385473,73517673391482,0,169171.0,169171.0,90620.0,676684.0,16384.0,10365368.0,191706.0,0.0,41854316.0
2,11995,1,144710,144710,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673363600,73517673369970,0,171791.0,171791.0,90307.0,687164.0,16384.0,10363168.0,193033.0,0.0,41847616.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
2 0 11995 1 144710 144710 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673339483 73517673347095 0 203242.0 203242.0 108439.0 812968.0 16384.0 13784518.0 249142.0 0.0 55564396.0
3 1 11995 1 144710 144710 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673385473 73517673391482 0 169171.0 169171.0 90620.0 676684.0 16384.0 10365368.0 191706.0 0.0 41854316.0
4 2 11995 1 144710 144710 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673363600 73517673369970 0 171791.0 171791.0 90307.0 687164.0 16384.0 10363168.0 193033.0 0.0 41847616.0
@@ -0,0 +1,229 @@
Omniperf version: 2.0.0
Profiler choice: rocprofv2
Path: /home/colramos/omniperf/tests/workloads/path/MI300A_A1
Target: MI300A_A1
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
Kernel Selection: None
Dispatch Selection: None
Hardware Blocks: All
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Collecting Performance Counters
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/SQ_IFETCH_LEVEL.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - GRBM_COUNT
|-> [/opt/rocm/bin/rocprofv2] - GRBM_GUI_ACTIVE
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/SQ_INST_LEVEL_LDS.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_LDS
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/SQ_INST_LEVEL_SMEM.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/SQ_INST_LEVEL_VMEM.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/SQ_LEVEL_WAVES.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - GRBM_COUNT
|-> [/opt/rocm/bin/rocprofv2] - GRBM_GUI_ACTIVE
|-> [/opt/rocm/bin/rocprofv2] - CPC_ME1_BUSY_FOR_PACKET_DECODE
|-> [/opt/rocm/bin/rocprofv2] - SQ_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVE_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_LEVEL_WAVES
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_0.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CU_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVE_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_CVT
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM_WR
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM_RD
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_1.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SALU
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VSKIPPED
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F16
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_10.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_ATOMIC_REQ
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_STALL
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_REQ
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_11.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_INPUT_VALID_READYB
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_ATOMIC
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_8
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_HITS
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_MISSES
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_MISSES_DUPLICATE
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_1
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_12.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_2
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_4
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_13.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_ATOMIC[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_BUBBLE[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_CYCLE[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_ATOMIC[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_BUBBLE[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_CYCLE[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC[1]
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_14.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[3]
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_15.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[0]
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_16.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[2]
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_17.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_TOO_MANY_EA_WRREQS_STALL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_WRITE[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_TOO_MANY_EA_WRREQS_STALL[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_WRITE[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[2]
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_2.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F64
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_3.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_FLAT
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_GDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_EXP_GDS
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_4.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_BRANCH
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SENDMSG
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAIT_ANY
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAIT_INST_ANY
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_ANY
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_LDS
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_5.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_SCA
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_EXP_GDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_MISC
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_FLAT
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_VMEM_WR
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_VMEM_RD
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_SALU
|-> [/opt/rocm/bin/rocprofv2] - TCP_TCC_READ_REQ_sum
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_6.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_THREAD_CYCLES_VALU
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_BANK_CONFLICT
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_7.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_32
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_16
|-> [/opt/rocm/bin/rocprofv2] - SQ_ITEMS
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_MEM_VIOLATIONS
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_ATOMIC_RETURN
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_IDX_ACTIVE
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_RESTORED
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_8.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM_NORM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_MFMA
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_I8
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_9.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_I8
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_BF16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F64
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_INST_REQ
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_READ_REQ
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_WRITE_REQ
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/timestamps.txt
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
[roofline] Roofline temporarily disabled in MI300
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_ATOMIC[0] TCC_BUBBLE[0] TCC_CYCLE[0] TCC_EA0_ATOMIC[0] TCC_ATOMIC[1] TCC_BUBBLE[1] TCC_CYCLE[1] TCC_EA0_ATOMIC[1] TCC_ATOMIC[2] TCC_BUBBLE[2] TCC_CYCLE[2] TCC_EA0_ATOMIC[2] TCC_ATOMIC[3] TCC_BUBBLE[3] TCC_CYCLE[3] TCC_EA0_ATOMIC[3] TCC_ATOMIC[4] TCC_BUBBLE[4] TCC_CYCLE[4] TCC_EA0_ATOMIC[4] TCC_ATOMIC[5] TCC_BUBBLE[5] TCC_CYCLE[5] TCC_EA0_ATOMIC[5] TCC_ATOMIC[6] TCC_BUBBLE[6] TCC_CYCLE[6] TCC_EA0_ATOMIC[6] TCC_ATOMIC[7] TCC_BUBBLE[7] TCC_CYCLE[7] TCC_EA0_ATOMIC[7] TCC_ATOMIC[8] TCC_BUBBLE[8] TCC_CYCLE[8] TCC_EA0_ATOMIC[8] TCC_ATOMIC[9] TCC_BUBBLE[9] TCC_CYCLE[9] TCC_EA0_ATOMIC[9] TCC_ATOMIC[10] TCC_BUBBLE[10] TCC_CYCLE[10] TCC_EA0_ATOMIC[10] TCC_ATOMIC[11] TCC_BUBBLE[11] TCC_CYCLE[11] TCC_EA0_ATOMIC[11] TCC_ATOMIC[12] TCC_BUBBLE[12] TCC_CYCLE[12] TCC_EA0_ATOMIC[12] TCC_ATOMIC[13] TCC_BUBBLE[13] TCC_CYCLE[13] TCC_EA0_ATOMIC[13] TCC_ATOMIC[14] TCC_BUBBLE[14] TCC_CYCLE[14] TCC_EA0_ATOMIC[14] TCC_ATOMIC[15] TCC_BUBBLE[15] TCC_CYCLE[15] TCC_EA0_ATOMIC[15]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_EA0_ATOMIC_LEVEL[0] TCC_EA0_RDREQ[0] TCC_EA0_RDREQ_32B[0] TCC_EA0_RDREQ_LEVEL[0] TCC_EA0_ATOMIC_LEVEL[1] TCC_EA0_RDREQ[1] TCC_EA0_RDREQ_32B[1] TCC_EA0_RDREQ_LEVEL[1] TCC_EA0_ATOMIC_LEVEL[2] TCC_EA0_RDREQ[2] TCC_EA0_RDREQ_32B[2] TCC_EA0_RDREQ_LEVEL[2] TCC_EA0_ATOMIC_LEVEL[3] TCC_EA0_RDREQ[3] TCC_EA0_RDREQ_32B[3] TCC_EA0_RDREQ_LEVEL[3] TCC_EA0_ATOMIC_LEVEL[4] TCC_EA0_RDREQ[4] TCC_EA0_RDREQ_32B[4] TCC_EA0_RDREQ_LEVEL[4] TCC_EA0_ATOMIC_LEVEL[5] TCC_EA0_RDREQ[5] TCC_EA0_RDREQ_32B[5] TCC_EA0_RDREQ_LEVEL[5] TCC_EA0_ATOMIC_LEVEL[6] TCC_EA0_RDREQ[6] TCC_EA0_RDREQ_32B[6] TCC_EA0_RDREQ_LEVEL[6] TCC_EA0_ATOMIC_LEVEL[7] TCC_EA0_RDREQ[7] TCC_EA0_RDREQ_32B[7] TCC_EA0_RDREQ_LEVEL[7] TCC_EA0_ATOMIC_LEVEL[8] TCC_EA0_RDREQ[8] TCC_EA0_RDREQ_32B[8] TCC_EA0_RDREQ_LEVEL[8] TCC_EA0_ATOMIC_LEVEL[9] TCC_EA0_RDREQ[9] TCC_EA0_RDREQ_32B[9] TCC_EA0_RDREQ_LEVEL[9] TCC_EA0_ATOMIC_LEVEL[10] TCC_EA0_RDREQ[10] TCC_EA0_RDREQ_32B[10] TCC_EA0_RDREQ_LEVEL[10] TCC_EA0_ATOMIC_LEVEL[11] TCC_EA0_RDREQ[11] TCC_EA0_RDREQ_32B[11] TCC_EA0_RDREQ_LEVEL[11] TCC_EA0_ATOMIC_LEVEL[12] TCC_EA0_RDREQ[12] TCC_EA0_RDREQ_32B[12] TCC_EA0_RDREQ_LEVEL[12] TCC_EA0_ATOMIC_LEVEL[13] TCC_EA0_RDREQ[13] TCC_EA0_RDREQ_32B[13] TCC_EA0_RDREQ_LEVEL[13] TCC_EA0_ATOMIC_LEVEL[14] TCC_EA0_RDREQ[14] TCC_EA0_RDREQ_32B[14] TCC_EA0_RDREQ_LEVEL[14] TCC_EA0_ATOMIC_LEVEL[15] TCC_EA0_RDREQ[15] TCC_EA0_RDREQ_32B[15] TCC_EA0_RDREQ_LEVEL[15]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_EA0_WRREQ[0] TCC_EA0_WRREQ_64B[0] TCC_EA0_WRREQ_LEVEL[0] TCC_HIT[0] TCC_EA0_WRREQ[1] TCC_EA0_WRREQ_64B[1] TCC_EA0_WRREQ_LEVEL[1] TCC_HIT[1] TCC_EA0_WRREQ[2] TCC_EA0_WRREQ_64B[2] TCC_EA0_WRREQ_LEVEL[2] TCC_HIT[2] TCC_EA0_WRREQ[3] TCC_EA0_WRREQ_64B[3] TCC_EA0_WRREQ_LEVEL[3] TCC_HIT[3] TCC_EA0_WRREQ[4] TCC_EA0_WRREQ_64B[4] TCC_EA0_WRREQ_LEVEL[4] TCC_HIT[4] TCC_EA0_WRREQ[5] TCC_EA0_WRREQ_64B[5] TCC_EA0_WRREQ_LEVEL[5] TCC_HIT[5] TCC_EA0_WRREQ[6] TCC_EA0_WRREQ_64B[6] TCC_EA0_WRREQ_LEVEL[6] TCC_HIT[6] TCC_EA0_WRREQ[7] TCC_EA0_WRREQ_64B[7] TCC_EA0_WRREQ_LEVEL[7] TCC_HIT[7] TCC_EA0_WRREQ[8] TCC_EA0_WRREQ_64B[8] TCC_EA0_WRREQ_LEVEL[8] TCC_HIT[8] TCC_EA0_WRREQ[9] TCC_EA0_WRREQ_64B[9] TCC_EA0_WRREQ_LEVEL[9] TCC_HIT[9] TCC_EA0_WRREQ[10] TCC_EA0_WRREQ_64B[10] TCC_EA0_WRREQ_LEVEL[10] TCC_HIT[10] TCC_EA0_WRREQ[11] TCC_EA0_WRREQ_64B[11] TCC_EA0_WRREQ_LEVEL[11] TCC_HIT[11] TCC_EA0_WRREQ[12] TCC_EA0_WRREQ_64B[12] TCC_EA0_WRREQ_LEVEL[12] TCC_HIT[12] TCC_EA0_WRREQ[13] TCC_EA0_WRREQ_64B[13] TCC_EA0_WRREQ_LEVEL[13] TCC_HIT[13] TCC_EA0_WRREQ[14] TCC_EA0_WRREQ_64B[14] TCC_EA0_WRREQ_LEVEL[14] TCC_HIT[14] TCC_EA0_WRREQ[15] TCC_EA0_WRREQ_64B[15] TCC_EA0_WRREQ_LEVEL[15] TCC_HIT[15]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_RW_REQ[0] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_RW_REQ[1] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_RW_REQ[2] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_RW_REQ[3] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_RW_REQ[4] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_RW_REQ[5] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_RW_REQ[6] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_RW_REQ[7] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_RW_REQ[8] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_RW_REQ[9] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_RW_REQ[10] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_RW_REQ[11] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_RW_REQ[12] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_RW_REQ[13] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_RW_REQ[14] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_RW_REQ[15]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_TAG_STALL[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_TAG_STALL[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_TAG_STALL[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_TAG_STALL[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_TAG_STALL[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_TAG_STALL[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_TAG_STALL[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_TAG_STALL[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_TAG_STALL[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_TAG_STALL[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_TAG_STALL[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_TAG_STALL[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_TAG_STALL[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_TAG_STALL[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_TAG_STALL[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_TAG_STALL[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA0_WRREQ_sum TCC_EA0_WRREQ_64B_sum TCC_EA0_WR_UNCACHED_32B_sum TCC_EA0_WRREQ_DRAM_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCC_READ_REQ_sum TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA0_RDREQ_sum TCC_EA0_RDREQ_32B_sum TCC_BUBBLE_sum TCC_EA0_RD_UNCACHED_32B_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_NC_READ_REQ_sum TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA0_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_UC_WRITE_REQ_sum TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA0_ATOMIC_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_CC_ATOMIC_REQ_sum TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA0_RDREQ_LEVEL_sum TCC_EA0_WRREQ_LEVEL_sum TCC_EA0_ATOMIC_LEVEL_sum TCC_EA0_WRREQ_STALL_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ TCP_PENDING_STALL_CYCLES_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel:
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Correlation_ID,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,TCC_EA0_WRREQ_64B_sum,TCC_EA0_WRREQ_DRAM_sum,TCC_EA0_WRREQ_sum,TCC_EA0_WR_UNCACHED_32B_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_TRANSLATION_MISS_sum,Wave_Size_1,Correlation_ID_1,XCC_Index,TCC_EA0_WRREQ[0],TCC_EA0_WRREQ_64B[0],TCC_EA0_WRREQ_LEVEL[0],TCC_HIT[0],TCC_EA0_WRREQ[1],TCC_EA0_WRREQ_64B[1],TCC_EA0_WRREQ_LEVEL[1],TCC_HIT[1],TCC_EA0_WRREQ[2],TCC_EA0_WRREQ_64B[2],TCC_EA0_WRREQ_LEVEL[2],TCC_HIT[2],TCC_EA0_WRREQ[3],TCC_EA0_WRREQ_64B[3],TCC_EA0_WRREQ_LEVEL[3],TCC_HIT[3],TCC_EA0_WRREQ[4],TCC_EA0_WRREQ_64B[4],TCC_EA0_WRREQ_LEVEL[4],TCC_HIT[4],TCC_EA0_WRREQ[5],TCC_EA0_WRREQ_64B[5],TCC_EA0_WRREQ_LEVEL[5],TCC_HIT[5],TCC_EA0_WRREQ[6],TCC_EA0_WRREQ_64B[6],TCC_EA0_WRREQ_LEVEL[6],TCC_HIT[6],TCC_EA0_WRREQ[7],TCC_EA0_WRREQ_64B[7],TCC_EA0_WRREQ_LEVEL[7],TCC_HIT[7],TCC_EA0_WRREQ[8],TCC_EA0_WRREQ_64B[8],TCC_EA0_WRREQ_LEVEL[8],TCC_HIT[8],TCC_EA0_WRREQ[9],TCC_EA0_WRREQ_64B[9],TCC_EA0_WRREQ_LEVEL[9],TCC_HIT[9],TCC_EA0_WRREQ[10],TCC_EA0_WRREQ_64B[10],TCC_EA0_WRREQ_LEVEL[10],TCC_HIT[10],TCC_EA0_WRREQ[11],TCC_EA0_WRREQ_64B[11],TCC_EA0_WRREQ_LEVEL[11],TCC_HIT[11],TCC_EA0_WRREQ[12],TCC_EA0_WRREQ_64B[12],TCC_EA0_WRREQ_LEVEL[12],TCC_HIT[12],TCC_EA0_WRREQ[13],TCC_EA0_WRREQ_64B[13],TCC_EA0_WRREQ_LEVEL[13],TCC_HIT[13],TCC_EA0_WRREQ[14],TCC_EA0_WRREQ_64B[14],TCC_EA0_WRREQ_LEVEL[14],TCC_HIT[14],TCC_EA0_WRREQ[15],TCC_EA0_WRREQ_64B[15],TCC_EA0_WRREQ_LEVEL[15],TCC_HIT[15],TCC_EA0_WRREQ[16],TCC_EA0_WRREQ_64B[16],TCC_EA0_WRREQ_LEVEL[16],TCC_HIT[16],TCC_EA0_WRREQ[17],TCC_EA0_WRREQ_64B[17],TCC_EA0_WRREQ_LEVEL[17],TCC_HIT[17],TCC_EA0_WRREQ[18],TCC_EA0_WRREQ_64B[18],TCC_EA0_WRREQ_LEVEL[18],TCC_HIT[18],TCC_EA0_WRREQ[19],TCC_EA0_WRREQ_64B[19],TCC_EA0_WRREQ_LEVEL[19],TCC_HIT[19],TCC_EA0_WRREQ[20],TCC_EA0_WRREQ_64B[20],TCC_EA0_WRREQ_LEVEL[20],TCC_HIT[20],TCC_EA0_WRREQ[21],TCC_EA0_WRREQ_64B[21],TCC_EA0_WRREQ_LEVEL[21],TCC_HIT[21],TCC_EA0_WRREQ[22],TCC_EA0_WRREQ_64B[22],TCC_EA0_WRREQ_LEVEL[22],TCC_HIT[22],TCC_EA0_WRREQ[23],TCC_EA0_WRREQ_64B[23],TCC_EA0_WRREQ_LEVEL[23],TCC_HIT[23],TCC_EA0_WRREQ[24],TCC_EA0_WRREQ_64B[24],TCC_EA0_WRREQ_LEVEL[24],TCC_HIT[24],TCC_EA0_WRREQ[25],TCC_EA0_WRREQ_64B[25],TCC_EA0_WRREQ_LEVEL[25],TCC_HIT[25],TCC_EA0_WRREQ[26],TCC_EA0_WRREQ_64B[26],TCC_EA0_WRREQ_LEVEL[26],TCC_HIT[26],TCC_EA0_WRREQ[27],TCC_EA0_WRREQ_64B[27],TCC_EA0_WRREQ_LEVEL[27],TCC_HIT[27],TCC_EA0_WRREQ[28],TCC_EA0_WRREQ_64B[28],TCC_EA0_WRREQ_LEVEL[28],TCC_HIT[28],TCC_EA0_WRREQ[29],TCC_EA0_WRREQ_64B[29],TCC_EA0_WRREQ_LEVEL[29],TCC_HIT[29],TCC_EA0_WRREQ[30],TCC_EA0_WRREQ_64B[30],TCC_EA0_WRREQ_LEVEL[30],TCC_HIT[30],TCC_EA0_WRREQ[31],TCC_EA0_WRREQ_64B[31],TCC_EA0_WRREQ_LEVEL[31],TCC_HIT[31],TCC_EA0_WRREQ[32],TCC_EA0_WRREQ_64B[32],TCC_EA0_WRREQ_LEVEL[32],TCC_HIT[32],TCC_EA0_WRREQ[33],TCC_EA0_WRREQ_64B[33],TCC_EA0_WRREQ_LEVEL[33],TCC_HIT[33],TCC_EA0_WRREQ[34],TCC_EA0_WRREQ_64B[34],TCC_EA0_WRREQ_LEVEL[34],TCC_HIT[34],TCC_EA0_WRREQ[35],TCC_EA0_WRREQ_64B[35],TCC_EA0_WRREQ_LEVEL[35],TCC_HIT[35],TCC_EA0_WRREQ[36],TCC_EA0_WRREQ_64B[36],TCC_EA0_WRREQ_LEVEL[36],TCC_HIT[36],TCC_EA0_WRREQ[37],TCC_EA0_WRREQ_64B[37],TCC_EA0_WRREQ_LEVEL[37],TCC_HIT[37],TCC_EA0_WRREQ[38],TCC_EA0_WRREQ_64B[38],TCC_EA0_WRREQ_LEVEL[38],TCC_HIT[38],TCC_EA0_WRREQ[39],TCC_EA0_WRREQ_64B[39],TCC_EA0_WRREQ_LEVEL[39],TCC_HIT[39],TCC_EA0_WRREQ[40],TCC_EA0_WRREQ_64B[40],TCC_EA0_WRREQ_LEVEL[40],TCC_HIT[40],TCC_EA0_WRREQ[41],TCC_EA0_WRREQ_64B[41],TCC_EA0_WRREQ_LEVEL[41],TCC_HIT[41],TCC_EA0_WRREQ[42],TCC_EA0_WRREQ_64B[42],TCC_EA0_WRREQ_LEVEL[42],TCC_HIT[42],TCC_EA0_WRREQ[43],TCC_EA0_WRREQ_64B[43],TCC_EA0_WRREQ_LEVEL[43],TCC_HIT[43],TCC_EA0_WRREQ[44],TCC_EA0_WRREQ_64B[44],TCC_EA0_WRREQ_LEVEL[44],TCC_HIT[44],TCC_EA0_WRREQ[45],TCC_EA0_WRREQ_64B[45],TCC_EA0_WRREQ_LEVEL[45],TCC_HIT[45],TCC_EA0_WRREQ[46],TCC_EA0_WRREQ_64B[46],TCC_EA0_WRREQ_LEVEL[46],TCC_HIT[46],TCC_EA0_WRREQ[47],TCC_EA0_WRREQ_64B[47],TCC_EA0_WRREQ_LEVEL[47],TCC_HIT[47],TCC_EA0_WRREQ[48],TCC_EA0_WRREQ_64B[48],TCC_EA0_WRREQ_LEVEL[48],TCC_HIT[48],TCC_EA0_WRREQ[49],TCC_EA0_WRREQ_64B[49],TCC_EA0_WRREQ_LEVEL[49],TCC_HIT[49],TCC_EA0_WRREQ[50],TCC_EA0_WRREQ_64B[50],TCC_EA0_WRREQ_LEVEL[50],TCC_HIT[50],TCC_EA0_WRREQ[51],TCC_EA0_WRREQ_64B[51],TCC_EA0_WRREQ_LEVEL[51],TCC_HIT[51],TCC_EA0_WRREQ[52],TCC_EA0_WRREQ_64B[52],TCC_EA0_WRREQ_LEVEL[52],TCC_HIT[52],TCC_EA0_WRREQ[53],TCC_EA0_WRREQ_64B[53],TCC_EA0_WRREQ_LEVEL[53],TCC_HIT[53],TCC_EA0_WRREQ[54],TCC_EA0_WRREQ_64B[54],TCC_EA0_WRREQ_LEVEL[54],TCC_HIT[54],TCC_EA0_WRREQ[55],TCC_EA0_WRREQ_64B[55],TCC_EA0_WRREQ_LEVEL[55],TCC_HIT[55],TCC_EA0_WRREQ[56],TCC_EA0_WRREQ_64B[56],TCC_EA0_WRREQ_LEVEL[56],TCC_HIT[56],TCC_EA0_WRREQ[57Line truncated
0,11995,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,16384.0,16384.0,11595556.0,868135.0,278528.0,0.0,0.0,98304.0,346761.0,0.0,0.0,477342.0,157274.0,32768.0,131072.0,131072.0,131072.0,0.0,0.0,524288.0,454135.0,1820.0,64,0,0,1368.0,1368.0,552757.0,684.0,1368.0,1368.0,564990.0,684.0,1368.0,1368.0,570792.0,684.0,1368.0,1368.0,575316.0,684.0,1368.0,1368.0,565396.0,684.0,1368.0,1368.0,567084.0,684.0,1368.0,1368.0,572578.0,684.0,1368.0,1368.0,564000.0,684.0,1364.0,1364.0,539365.0,682.0,1364.0,1364.0,548098.0,682.0,1364.0,1364.0,557332.0,682.0,1364.0,1364.0,557702.0,701.0,1364.0,1364.0,550989.0,740.0,1364.0,1364.0,555943.0,682.0,1364.0,1364.0,564319.0,682.0,1364.0,1364.0,559676.0,682.0,1368.0,1368.0,549393.0,684.0,1368.0,1368.0,558283.0,684.0,1368.0,1368.0,562733.0,684.0,1368.0,1368.0,571512.0,703.0,1368.0,1368.0,561222.0,742.0,1368.0,1368.0,565618.0,684.0,1368.0,1368.0,584296.0,684.0,1368.0,1368.0,576016.0,684.0,1364.0,1364.0,546788.0,682.0,1364.0,1364.0,560781.0,682.0,1364.0,1364.0,558471.0,682.0,1364.0,1364.0,563366.0,682.0,1364.0,1364.0,554884.0,682.0,1364.0,1364.0,560398.0,682.0,1364.0,1364.0,567876.0,682.0,1364.0,1364.0,558648.0,682.0,1364.0,1364.0,548864.0,682.0,1364.0,1364.0,557481.0,682.0,1364.0,1364.0,564582.0,682.0,1364.0,1364.0,563126.0,701.0,1364.0,1364.0,556634.0,740.0,1364.0,1364.0,559938.0,682.0,1364.0,1364.0,574279.0,682.0,1364.0,1364.0,572159.0,682.0,1368.0,1368.0,537661.0,684.0,1368.0,1368.0,550441.0,684.0,1368.0,1368.0,548929.0,684.0,1368.0,1368.0,555413.0,684.0,1368.0,1368.0,541898.0,684.0,1368.0,1368.0,549199.0,684.0,1368.0,1368.0,555554.0,684.0,1368.0,1368.0,551329.0,684.0,1364.0,1364.0,539518.0,682.0,1364.0,1364.0,553119.0,682.0,1364.0,1364.0,553549.0,682.0,1364.0,1364.0,557710.0,682.0,1364.0,1364.0,552890.0,682.0,1364.0,1364.0,557477.0,682.0,1364.0,1364.0,561754.0,682.0,1364.0,1364.0,557668.0,682.0,1368.0,1368.0,542064.0,684.0,1368.0,1368.0,549114.0,684.0,1368.0,1368.0,559881.0,684.0,1368.0,1368.0,559009.0,703.0,1368.0,1368.0,549089.0,742.0,1368.0,1368.0,553609.0,684.0,1368.0,1368.0,568374.0,684.0,1368.0,1368.0,562492.0,684.0,1368.0,1368.0,552582.0,684.0,1368.0,1368.0,565350.0,684.0,1368.0,1368.0,562085.0,684.0,1368.0,1368.0,567690.0,703.0,1368.0,1368.0,555983.0,742.0,1368.0,1368.0,560931.0,684.0,1368.0,1368.0,569021.0,684.0,1368.0,1368.0,565743.0,684.0,1360.0,1360.0,543294.0,680.0,1360.0,1360.0,549700.0,680.0,1360.0,1360.0,559798.0,680.0,1360.0,1360.0,559360.0,680.0,1360.0,1360.0,552654.0,680.0,1360.0,1360.0,556433.0,680.0,1360.0,1360.0,569546.0,680.0,1360.0,1360.0,565875.0,680.0,1368.0,1368.0,546716.0,684.0,1368.0,1368.0,554065.0,684.0,1368.0,1368.0,564585.0,684.0,1368.0,1368.0,562724.0,684.0,1368.0,1368.0,554816.0,684.0,1368.0,1368.0,559398.0,684.0,1368.0,1368.0,574628.0,684.0,1368.0,1368.0,570521.0,684.0,1360.0,1360.0,540984.0,680.0,1360.0,1360.0,553132.0,680.0,1360.0,1360.0,550903.0,680.0,1360.0,1360.0,557915.0,699.0,1360.0,1360.0,539696.0,738.0,1360.0,1360.0,546255.0,680.0,1360.0,1360.0,559402.0,680.0,1360.0,1360.0,550720.0,680.0,64,0,6291456.0,65536.0,0.0,0.0,0.0,16384.0,0.0,0.0,0.0,0.0,16384.0,32768.0,49369.0,65602.0,16167.0,83983.0,0.0,0.0,0.0,0.0,64,0,0,924.0,0.0,1360.0,927.0,0.0,1360.0,850.0,0.0,1360.0,853.0,0.0,1360.0,1279.0,0.0,1360.0,1259.0,0.0,1360.0,1264.0,0.0,1360.0,1241.0,0.0,1360.0,1128.0,0.0,1368.0,772.0,0.0,1368.0,1113.0,0.0,1368.0,914.0,0.0,1368.0,1003.0,0.0,1368.0,1119.0,0.0,1368.0,836.0,0.0,1368.0,1174.0,0.0,1368.0,1291.0,0.0,1360.0,937.0,0.0,1360.0,1349.0,0.0,1360.0,1312.0,0.0,1360.0,1333.0,0.0,1360.0,1250.0,0.0,1360.0,1035.0,0.0,1360.0,1295.0,0.0,1360.0,897.0,0.0,1368.0,909.0,0.0,1368.0,949.0,0.0,1368.0,950.0,0.0,1368.0,1335.0,0.0,1368.0,1382.0,0.0,1368.0,1343.0,0.0,1368.0,1345.0,0.0,1368.0,1108.0,0.0,1364.0,780.0,0.0,1364.0,1121.0,0.0,1364.0,1003.0,0.0,1364.0,979.0,0.0,1364.0,1123.0,0.0,1364.0,778.0,0.0,1364.0,1166.0,0.0,1364.0,896.0,0.0,1368.0,915.0,0.0,1368.0,855.0,0.0,1368.0,837.0,0.0,1368.0,1278.0,0.0,1368.0,1258.0,0.0,1368.0,1263.0,0.0,1368.0,1235.0,0.0,1368.0,793.0,0.0,1364.0,795.0,0.0,1364.0,780.0,0.0,1364.0,778.0,0.0,1364.0,1186.0,0.0,1364.0,1203.0,0.0,1364.0,1207.0,0.0,1364.0,1172.0,0.0,1364.0,1168.0,0.0,1368.0,891.0,0.0,1368.0,1181.0,0.0,1368.0,1137.0,0.0,1368.0,1154.0,0.0,1368.0,1170.0,0.0,1368.0,915.0,0.0,1368.0,1227.0,0.0,1368.0,1202.0,0.0,1364.0,799.0,0.0,1364.0,1193.0,0.0,1364.0,1061.0,0.0,1364.0,1007.0,0.0,1364.0,1120.0,0.0,1364.0,855.0,0.0,1364.0,1291.0,0.0,1364.0,974.0,0.0,1368.0,1015.0,0.0,1368.0,969.0,0.0,1368.0,988.0,0.0,1368.0,1338.0,0.0,1368.0,1344.0,0.0,1368.0,1291.0,0.0,1368.0,1253.0,0.0,1368.0,813.0,0.0,1364.0,812.0,0.0,1364.0,803.0,0.0,1364.0,837.0,0.0,1364.0,1177.0,0.0,1364.0,1184.0,0.0,1364.0,1212.0,0.0,1364.0,1189.0,0.0,1364.0,1143.0,0.0,1368.0,879.0,0.0,1368.0,1191.0,0.0,1368.0,1117.0,0.0,1368.0,1041.0,0.0,1368.0,1142.0,0.0,1368.0,943.0,0.0,1368.0,1219.0,0.0,1368.0,64,0,0.0,49152.0,32768.0,65536.0,32768.0,0.0,0.0,0.0,10150.0,0.0,510.0,607768.0,78.0,0.0,0.0,0.0,66077.0,65536.0,131072.0,0.0,0.0,524Line truncated
1,11995,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,16384.0,16384.0,9606887.0,867649.0,278528.0,0.0,0.0,98304.0,240438.0,0.0,0.0,443185.0,163710.0,32768.0,131072.0,131072.0,131072.0,0.0,0.0,524288.0,455643.0,1824.0,64,0,0,1364.0,1364.0,558594.0,682.0,1364.0,1364.0,575401.0,682.0,1364.0,1364.0,573729.0,682.0,1364.0,1364.0,576657.0,682.0,1364.0,1364.0,563605.0,682.0,1364.0,1364.0,569893.0,682.0,1364.0,1364.0,579289.0,682.0,1364.0,1364.0,572563.0,682.0,1368.0,1368.0,588867.0,684.0,1368.0,1368.0,600399.0,684.0,1368.0,1368.0,607654.0,684.0,1368.0,1368.0,609826.0,703.0,1368.0,1368.0,614671.0,684.0,1368.0,1368.0,613564.0,684.0,1368.0,1368.0,629125.0,684.0,1368.0,1368.0,630078.0,684.0,1364.0,1364.0,565391.0,682.0,1364.0,1364.0,581322.0,682.0,1364.0,1364.0,590980.0,682.0,1364.0,1364.0,591700.0,701.0,1364.0,1364.0,581667.0,682.0,1364.0,1364.0,581320.0,682.0,1364.0,1364.0,592822.0,682.0,1364.0,1364.0,595612.0,682.0,1368.0,1368.0,554796.0,684.0,1368.0,1368.0,570054.0,684.0,1368.0,1368.0,572357.0,684.0,1368.0,1368.0,580221.0,684.0,1368.0,1368.0,561764.0,684.0,1368.0,1368.0,566938.0,684.0,1368.0,1368.0,588145.0,684.0,1368.0,1368.0,581231.0,684.0,1368.0,1368.0,563001.0,684.0,1368.0,1368.0,577224.0,684.0,1368.0,1368.0,581672.0,684.0,1368.0,1368.0,578638.0,703.0,1368.0,1368.0,571145.0,684.0,1368.0,1368.0,575459.0,684.0,1368.0,1368.0,582906.0,684.0,1368.0,1368.0,579014.0,684.0,1364.0,1364.0,556007.0,682.0,1364.0,1364.0,567973.0,682.0,1364.0,1364.0,581427.0,682.0,1364.0,1364.0,588239.0,682.0,1364.0,1364.0,571250.0,682.0,1364.0,1364.0,576285.0,682.0,1364.0,1364.0,586734.0,682.0,1364.0,1364.0,579833.0,682.0,1360.0,1360.0,559262.0,680.0,1360.0,1360.0,572216.0,680.0,1360.0,1360.0,570921.0,680.0,1360.0,1360.0,584007.0,680.0,1360.0,1360.0,566232.0,680.0,1360.0,1360.0,570143.0,680.0,1360.0,1360.0,584660.0,680.0,1360.0,1360.0,578618.0,680.0,1368.0,1368.0,565141.0,684.0,1368.0,1368.0,571214.0,684.0,1368.0,1368.0,582367.0,684.0,1368.0,1368.0,582752.0,703.0,1368.0,1368.0,573558.0,684.0,1368.0,1368.0,577758.0,684.0,1368.0,1368.0,587178.0,684.0,1368.0,1368.0,584840.0,684.0,1360.0,1360.0,553558.0,680.0,1360.0,1360.0,565508.0,680.0,1360.0,1360.0,564138.0,680.0,1360.0,1360.0,568723.0,699.0,1360.0,1360.0,558643.0,680.0,1360.0,1360.0,562490.0,680.0,1360.0,1360.0,569593.0,680.0,1360.0,1360.0,562977.0,680.0,1368.0,1368.0,567075.0,684.0,1368.0,1368.0,573591.0,684.0,1368.0,1368.0,578657.0,684.0,1368.0,1368.0,579212.0,684.0,1368.0,1368.0,573074.0,684.0,1368.0,1368.0,577221.0,684.0,1368.0,1368.0,588633.0,684.0,1368.0,1368.0,585226.0,684.0,1368.0,1368.0,580050.0,684.0,1368.0,1368.0,585630.0,684.0,1368.0,1368.0,596350.0,684.0,1368.0,1368.0,598366.0,684.0,1368.0,1368.0,590344.0,684.0,1368.0,1368.0,593583.0,684.0,1368.0,1368.0,616152.0,684.0,1368.0,1368.0,610566.0,684.0,1364.0,1364.0,549768.0,682.0,1364.0,1364.0,559842.0,682.0,1364.0,1364.0,555394.0,682.0,1364.0,1364.0,560695.0,701.0,1364.0,1364.0,557927.0,682.0,1364.0,1364.0,563726.0,682.0,1364.0,1364.0,569026.0,682.0,1364.0,1364.0,564111.0,682.0,64,0,6291456.0,65536.0,0.0,0.0,0.0,16384.0,0.0,0.0,0.0,0.0,16384.0,32768.0,48676.0,65584.0,16860.0,109056.0,0.0,0.0,0.0,0.0,64,0,0,1073.0,0.0,1368.0,952.0,0.0,1368.0,1075.0,0.0,1368.0,1056.0,0.0,1368.0,1105.0,0.0,1368.0,910.0,0.0,1368.0,868.0,0.0,1368.0,897.0,0.0,1368.0,914.0,0.0,1360.0,918.0,0.0,1360.0,938.0,0.0,1360.0,936.0,0.0,1360.0,1000.0,0.0,1360.0,919.0,0.0,1360.0,930.0,0.0,1360.0,924.0,0.0,1360.0,797.0,0.0,1364.0,837.0,0.0,1364.0,786.0,0.0,1364.0,791.0,0.0,1364.0,889.0,0.0,1364.0,841.0,0.0,1364.0,830.0,0.0,1364.0,825.0,0.0,1364.0,1035.0,0.0,1368.0,1118.0,0.0,1368.0,1058.0,0.0,1368.0,978.0,0.0,1368.0,1074.0,0.0,1368.0,1057.0,0.0,1368.0,1050.0,0.0,1368.0,1036.0,0.0,1368.0,1001.0,0.0,1368.0,1007.0,0.0,1368.0,906.0,0.0,1368.0,1033.0,0.0,1368.0,1175.0,0.0,1368.0,1080.0,0.0,1368.0,931.0,0.0,1368.0,1124.0,0.0,1368.0,883.0,0.0,1364.0,876.0,0.0,1364.0,994.0,0.0,1364.0,990.0,0.0,1364.0,770.0,0.0,1364.0,762.0,0.0,1364.0,891.0,0.0,1364.0,856.0,0.0,1364.0,990.0,0.0,1368.0,1047.0,0.0,1368.0,1067.0,0.0,1368.0,1090.0,0.0,1368.0,999.0,0.0,1368.0,987.0,0.0,1368.0,898.0,0.0,1368.0,884.0,0.0,1368.0,1227.0,0.0,1364.0,1186.0,0.0,1364.0,1344.0,0.0,1364.0,1326.0,0.0,1364.0,1400.0,0.0,1364.0,1347.0,0.0,1364.0,1411.0,0.0,1364.0,1399.0,0.0,1364.0,1068.0,0.0,1368.0,1073.0,0.0,1368.0,1034.0,0.0,1368.0,1043.0,0.0,1368.0,983.0,0.0,1368.0,972.0,0.0,1368.0,1062.0,0.0,1368.0,1044.0,0.0,1368.0,1340.0,0.0,1364.0,1408.0,0.0,1364.0,1390.0,0.0,1364.0,1373.0,0.0,1364.0,1334.0,0.0,1364.0,1320.0,0.0,1364.0,1352.0,0.0,1364.0,1331.0,0.0,1364.0,919.0,0.0,1360.0,972.0,0.0,1360.0,923.0,0.0,1360.0,909.0,0.0,1360.0,938.0,0.0,1360.0,935.0,0.0,1360.0,915.0,0.0,1360.0,904.0,0.0,1360.0,826.0,0.0,1368.0,864.0,0.0,1368.0,848.0,0.0,1368.0,883.0,0.0,1368.0,1001.0,0.0,1368.0,972.0,0.0,1368.0,988.0,0.0,1368.0,921.0,0.0,1368.0,64,0,0.0,49152.0,32768.0,65536.0,32768.0,0.0,0.0,0.0,7198.0,0.0,7678.0,583855.0,1147.0,0.0,0.0,0.0,65736.0,65536.0,131072.0,0.0,0.0,524288.0,228.0,0.Line truncated
2,11995,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,16384.0,16384.0,9459526.0,884278.0,278528.0,0.0,0.0,98304.0,232672.0,0.0,0.0,464348.0,203111.0,32768.0,131072.0,131072.0,131072.0,0.0,0.0,524288.0,454604.0,1824.0,64,0,0,1368.0,1368.0,561191.0,684.0,1368.0,1368.0,571454.0,684.0,1368.0,1368.0,558961.0,684.0,1368.0,1368.0,566840.0,684.0,1368.0,1368.0,563542.0,684.0,1368.0,1368.0,566986.0,684.0,1368.0,1368.0,578326.0,684.0,1368.0,1368.0,572403.0,684.0,1364.0,1364.0,580301.0,682.0,1364.0,1364.0,588042.0,682.0,1364.0,1364.0,585812.0,682.0,1364.0,1364.0,586480.0,701.0,1364.0,1364.0,578778.0,682.0,1364.0,1364.0,581489.0,682.0,1364.0,1364.0,595611.0,682.0,1364.0,1364.0,593314.0,682.0,1368.0,1368.0,557726.0,684.0,1368.0,1368.0,562457.0,684.0,1368.0,1368.0,577352.0,684.0,1368.0,1368.0,574350.0,703.0,1368.0,1368.0,572402.0,684.0,1368.0,1368.0,572072.0,684.0,1368.0,1368.0,587690.0,684.0,1368.0,1368.0,584551.0,684.0,1364.0,1364.0,568269.0,682.0,1364.0,1364.0,581091.0,682.0,1364.0,1364.0,575265.0,682.0,1364.0,1364.0,582792.0,682.0,1364.0,1364.0,576402.0,682.0,1364.0,1364.0,581223.0,682.0,1364.0,1364.0,582386.0,682.0,1364.0,1364.0,577447.0,682.0,1368.0,1368.0,580750.0,684.0,1368.0,1368.0,589243.0,684.0,1368.0,1368.0,595677.0,684.0,1368.0,1368.0,595798.0,703.0,1368.0,1368.0,580919.0,684.0,1368.0,1368.0,584392.0,684.0,1368.0,1368.0,603709.0,684.0,1368.0,1368.0,601100.0,684.0,1360.0,1360.0,564517.0,680.0,1360.0,1360.0,576694.0,680.0,1360.0,1360.0,573955.0,680.0,1360.0,1360.0,581084.0,680.0,1360.0,1360.0,572500.0,680.0,1360.0,1360.0,580478.0,680.0,1360.0,1360.0,585048.0,680.0,1360.0,1360.0,578032.0,680.0,1368.0,1368.0,573735.0,684.0,1368.0,1368.0,586565.0,684.0,1368.0,1368.0,582976.0,684.0,1368.0,1368.0,588826.0,684.0,1368.0,1368.0,575051.0,684.0,1368.0,1368.0,580169.0,684.0,1368.0,1368.0,585505.0,684.0,1368.0,1368.0,580408.0,684.0,1360.0,1360.0,575506.0,680.0,1360.0,1360.0,584765.0,680.0,1360.0,1360.0,595938.0,680.0,1360.0,1360.0,592565.0,699.0,1360.0,1360.0,572241.0,680.0,1360.0,1360.0,575509.0,680.0,1360.0,1360.0,598383.0,680.0,1360.0,1360.0,594931.0,680.0,1364.0,1364.0,547584.0,682.0,1364.0,1364.0,560349.0,682.0,1364.0,1364.0,564070.0,682.0,1364.0,1364.0,570552.0,701.0,1364.0,1364.0,561207.0,682.0,1364.0,1364.0,567732.0,682.0,1364.0,1364.0,574855.0,682.0,1364.0,1364.0,567553.0,682.0,1368.0,1368.0,599453.0,684.0,1368.0,1368.0,607084.0,684.0,1368.0,1368.0,609048.0,684.0,1368.0,1368.0,607684.0,684.0,1368.0,1368.0,602100.0,684.0,1368.0,1368.0,605004.0,684.0,1368.0,1368.0,627851.0,684.0,1368.0,1368.0,623135.0,684.0,1364.0,1364.0,552770.0,682.0,1364.0,1364.0,558498.0,682.0,1364.0,1364.0,564740.0,682.0,1364.0,1364.0,564460.0,682.0,1364.0,1364.0,556189.0,682.0,1364.0,1364.0,557830.0,682.0,1364.0,1364.0,574988.0,682.0,1364.0,1364.0,570530.0,682.0,1368.0,1368.0,587643.0,684.0,1368.0,1368.0,599762.0,684.0,1368.0,1368.0,592094.0,684.0,1368.0,1368.0,601949.0,703.0,1368.0,1368.0,590470.0,684.0,1368.0,1368.0,595114.0,684.0,1368.0,1368.0,604650.0,684.0,1368.0,1368.0,598529.0,684.0,64,0,6291456.0,65536.0,0.0,0.0,0.0,16384.0,0.0,0.0,0.0,0.0,16384.0,32768.0,48767.0,65606.0,16769.0,110701.0,0.0,0.0,0.0,0.0,64,0,0,929.0,0.0,1368.0,932.0,0.0,1368.0,994.0,0.0,1368.0,991.0,0.0,1368.0,932.0,0.0,1368.0,924.0,0.0,1368.0,949.0,0.0,1368.0,958.0,0.0,1368.0,816.0,0.0,1364.0,820.0,0.0,1364.0,800.0,0.0,1364.0,915.0,0.0,1364.0,879.0,0.0,1364.0,898.0,0.0,1364.0,1048.0,0.0,1364.0,807.0,0.0,1364.0,1089.0,0.0,1368.0,1078.0,0.0,1368.0,963.0,0.0,1368.0,1085.0,0.0,1368.0,1141.0,0.0,1368.0,1057.0,0.0,1368.0,1161.0,0.0,1368.0,1169.0,0.0,1368.0,884.0,0.0,1364.0,908.0,0.0,1364.0,948.0,0.0,1364.0,985.0,0.0,1364.0,793.0,0.0,1364.0,852.0,0.0,1364.0,1027.0,0.0,1364.0,928.0,0.0,1364.0,1300.0,0.0,1364.0,1279.0,0.0,1364.0,1209.0,0.0,1364.0,1291.0,0.0,1364.0,1350.0,0.0,1364.0,1241.0,0.0,1364.0,1296.0,0.0,1364.0,1279.0,0.0,1364.0,1035.0,0.0,1368.0,1071.0,0.0,1368.0,952.0,0.0,1368.0,956.0,0.0,1368.0,931.0,0.0,1368.0,924.0,0.0,1368.0,921.0,0.0,1368.0,909.0,0.0,1368.0,1342.0,0.0,1364.0,1364.0,0.0,1364.0,1338.0,0.0,1364.0,1350.0,0.0,1364.0,1369.0,0.0,1364.0,1367.0,0.0,1364.0,1390.0,0.0,1364.0,1306.0,0.0,1364.0,932.0,0.0,1368.0,936.0,0.0,1368.0,919.0,0.0,1368.0,935.0,0.0,1368.0,1069.0,0.0,1368.0,908.0,0.0,1368.0,964.0,0.0,1368.0,1002.0,0.0,1368.0,919.0,0.0,1368.0,926.0,0.0,1368.0,938.0,0.0,1368.0,948.0,0.0,1368.0,1080.0,0.0,1368.0,1036.0,0.0,1368.0,906.0,0.0,1368.0,955.0,0.0,1368.0,948.0,0.0,1360.0,987.0,0.0,1360.0,1001.0,0.0,1360.0,999.0,0.0,1360.0,954.0,0.0,1360.0,947.0,0.0,1360.0,940.0,0.0,1360.0,936.0,0.0,1360.0,990.0,0.0,1368.0,1051.0,0.0,1368.0,892.0,0.0,1368.0,881.0,0.0,1368.0,1020.0,0.0,1368.0,945.0,0.0,1368.0,876.0,0.0,1368.0,833.0,0.0,1368.0,945.0,0.0,1360.0,948.0,0.0,1360.0,937.0,0.0,1360.0,937.0,0.0,1360.0,902.0,0.0,1360.0,904.0,0.0,1360.0,903.0,0.0,1360.0,980.0,0.0,1360.0,64,0,0.0,49152.0,32768.0,65536.0,32768.0,0.0,0.0,0.0,6367.0,0.0,5477.0,515406.0,0.0,0.0,0.0,0.0,65733.0,65536.0,131072.0,0.0,0.0,524288.0,228.0,0.0,64,0,0.0,0.Line truncated
@@ -0,0 +1,2 @@
workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
path,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Wed 29 May 2024 01:33:59 PM (CDT),2,sh5-1w300-rg3-3,AMD Instinct MI300A Accelerator,"American Megatrends International, LLC.RMO1002DS",Ubuntu 22.04.2 LTS,5.18.2-mi300-build-140423-ubuntu-22.04+,,131174852,,6.1.2-110,N/A,SPX,NPS1,MI300A_A1,gfx942,32,24576,228,4,24,64,1024,32,2100,1300,2100,1300,96,32,120,4,5324.8,6
1 workload_name command ip_blocks timestamp version hostname cpu_model sbios linux_distro linux_kernel_version amd_gpu_kernel_version cpu_memory gpu_memory rocm_version vbios compute_partition memory_partition gpu_model gpu_arch gpu_l1 gpu_l2 cu_per_gpu simd_per_cu se_per_gpu wave_size workgroup_max_size max_waves_per_cu max_sclk max_mclk cur_sclk cur_mclk total_l2_chan lds_banks_per_cu sqc_per_gpu pipes_per_gpu hbm_bw num_xcd
2 path ./tests/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF Wed 29 May 2024 01:33:59 PM (CDT) 2 sh5-1w300-rg3-3 AMD Instinct MI300A Accelerator American Megatrends International, LLC.RMO1002DS Ubuntu 22.04.2 LTS 5.18.2-mi300-build-140423-ubuntu-22.04+ 131174852 6.1.2-110 N/A SPX NPS1 MI300A_A1 gfx942 32 24576 228 4 24 64 1024 32 2100 1300 2100 1300 96 32 120 4 5324.8 6
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID
1,11995,1,144921,144921,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673339483,73517673347095,0
3,11995,1,144921,144921,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673385473,73517673391482,0
2,11995,1,144921,144921,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673363600,73517673369970,0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID
2 1 11995 1 144921 144921 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673339483 73517673347095 0
3 3 11995 1 144921 144921 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673385473 73517673391482 0
4 2 11995 1 144921 144921 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73517673363600 73517673369970 0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES
0,60633,1,962922,962922,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268071613,716165268087773,0,435104.0,435104.0,16384.0,65536.0,35112.0,2815648.0
1,60633,1,962922,962922,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268110013,716165268124653,0,442929.0,442929.0,16384.0,65536.0,13009.0,1048576.0
2,60633,1,962922,962922,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268144733,716165268158533,0,359921.0,359921.0,16384.0,65536.0,13296.0,1048592.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
2 0 60633 1 962922 962922 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268071613 716165268087773 0 435104.0 435104.0 16384.0 65536.0 35112.0 2815648.0
3 1 60633 1 962922 962922 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268110013 716165268124653 0 442929.0 442929.0 16384.0 65536.0 13009.0 1048576.0
4 2 60633 1 962922 962922 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268144733 716165268158533 0 359921.0 359921.0 16384.0 65536.0 13296.0 1048592.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES
0,60633,1,962933,962933,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268071613,716165268087773,0,0.0,0.0,0.0
1,60633,1,962933,962933,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268110013,716165268124653,0,0.0,0.0,0.0
2,60633,1,962933,962933,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268144733,716165268158533,0,0.0,0.0,0.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
2 0 60633 1 962933 962933 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268071613 716165268087773 0 0.0 0.0 0.0
3 1 60633 1 962933 962933 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268110013 716165268124653 0 0.0 0.0 0.0
4 2 60633 1 962933 962933 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268144733 716165268158533 0 0.0 0.0 0.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES
0,60633,1,962944,962944,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268071613,716165268087773,0,65536.0,3398670.0,271803456.0
1,60633,1,962944,962944,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268110013,716165268124653,0,65536.0,3594916.0,287618528.0
2,60633,1,962944,962944,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268144733,716165268158533,0,65536.0,3509382.0,280756880.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
2 0 60633 1 962944 962944 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268071613 716165268087773 0 65536.0 3398670.0 271803456.0
3 1 60633 1 962944 962944 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268110013 716165268124653 0 65536.0 3594916.0 287618528.0
4 2 60633 1 962944 962944 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268144733 716165268158533 0 65536.0 3509382.0 280756880.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES
0,60633,1,962955,962955,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268071613,716165268087773,0,32768.0,437332.0,34974484.0
1,60633,1,962955,962955,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268110013,716165268124653,0,32768.0,278708.0,22287984.0
2,60633,1,962955,962955,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268144733,716165268158533,0,32768.0,272752.0,21819956.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
2 0 60633 1 962955 962955 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268071613 716165268087773 0 32768.0 437332.0 34974484.0
3 1 60633 1 962955 962955 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268110013 716165268124653 0 32768.0 278708.0 22287984.0
4 2 60633 1 962955 962955 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268144733 716165268158533 0 32768.0 272752.0 21819956.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES
0,60633,1,962966,962966,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268071613,716165268087773,0,461523.0,461523.0,272360.0,1846092.0,16384.0,35221159.0,571274.0,0.0,141225272.0
1,60633,1,962966,962966,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268110013,716165268124653,0,405351.0,405351.0,224988.0,1621404.0,16384.0,31015819.0,522599.0,0.0,124419904.0
2,60633,1,962966,962966,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268144733,716165268158533,0,414642.0,414642.0,238604.0,1658568.0,16384.0,30314115.0,516384.0,0.0,121612444.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
2 0 60633 1 962966 962966 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268071613 716165268087773 0 461523.0 461523.0 272360.0 1846092.0 16384.0 35221159.0 571274.0 0.0 141225272.0
3 1 60633 1 962966 962966 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268110013 716165268124653 0 405351.0 405351.0 224988.0 1621404.0 16384.0 31015819.0 522599.0 0.0 124419904.0
4 2 60633 1 962966 962966 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268144733 716165268158533 0 414642.0 414642.0 238604.0 1658568.0 16384.0 30314115.0 516384.0 0.0 121612444.0
@@ -0,0 +1,149 @@
Omniperf version: 2.0.0
Profiler choice: rocprofv2
Path: /home/colramos/omniperf/tests/workloads/path/MI300X_A1
Target: MI300X_A1
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
Kernel Selection: None
Dispatch Selection: None
Hardware Blocks: All
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Collecting Performance Counters
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/SQ_IFETCH_LEVEL.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - GRBM_COUNT
|-> [/opt/rocm/bin/rocprofv2] - GRBM_GUI_ACTIVE
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/SQ_INST_LEVEL_LDS.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_LDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/SQ_INST_LEVEL_SMEM.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/SQ_INST_LEVEL_VMEM.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/SQ_LEVEL_WAVES.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - GRBM_COUNT
|-> [/opt/rocm/bin/rocprofv2] - GRBM_GUI_ACTIVE
|-> [/opt/rocm/bin/rocprofv2] - CPC_ME1_BUSY_FOR_PACKET_DECODE
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_0.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CU_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVE_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_CVT
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM_WR
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_1.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SALU
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VSKIPPED
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_10.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_ATOMIC_REQ
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_STALL
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_11.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_INPUT_VALID_READYB
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_ATOMIC
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_8
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_12.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_2
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_4
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_13.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_ATOMIC[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_BUBBLE[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_CYCLE[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC[0]
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_14.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[1]
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_15.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[1]
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_16.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[0]
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_17.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_TOO_MANY_EA_WRREQS_STALL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_WRITE[0]
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_2.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F16
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_3.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_FLAT
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_4.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_BRANCH
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SENDMSG
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAIT_ANY
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_5.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_SCA
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_EXP_GDS
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_6.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_THREAD_CYCLES_VALU
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_7.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_32
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_16
|-> [/opt/rocm/bin/rocprofv2] - SQ_ITEMS
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_MEM_VIOLATIONS
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_ATOMIC_RETURN
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_IDX_ACTIVE
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_8.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM_NORM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_MFMA
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_I8
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/pmc_perf_9.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_I8
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F16
[profiling] Current input file: tests/workloads/path/MI300X_A1/perfmon/timestamps.txt
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
[roofline] Roofline temporarily disabled in MI300
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_ATOMIC[0] TCC_BUBBLE[0] TCC_CYCLE[0] TCC_EA0_ATOMIC[0] TCC_ATOMIC[1] TCC_BUBBLE[1] TCC_CYCLE[1] TCC_EA0_ATOMIC[1] TCC_ATOMIC[2] TCC_BUBBLE[2] TCC_CYCLE[2] TCC_EA0_ATOMIC[2] TCC_ATOMIC[3] TCC_BUBBLE[3] TCC_CYCLE[3] TCC_EA0_ATOMIC[3] TCC_ATOMIC[4] TCC_BUBBLE[4] TCC_CYCLE[4] TCC_EA0_ATOMIC[4] TCC_ATOMIC[5] TCC_BUBBLE[5] TCC_CYCLE[5] TCC_EA0_ATOMIC[5] TCC_ATOMIC[6] TCC_BUBBLE[6] TCC_CYCLE[6] TCC_EA0_ATOMIC[6] TCC_ATOMIC[7] TCC_BUBBLE[7] TCC_CYCLE[7] TCC_EA0_ATOMIC[7] TCC_ATOMIC[8] TCC_BUBBLE[8] TCC_CYCLE[8] TCC_EA0_ATOMIC[8] TCC_ATOMIC[9] TCC_BUBBLE[9] TCC_CYCLE[9] TCC_EA0_ATOMIC[9] TCC_ATOMIC[10] TCC_BUBBLE[10] TCC_CYCLE[10] TCC_EA0_ATOMIC[10] TCC_ATOMIC[11] TCC_BUBBLE[11] TCC_CYCLE[11] TCC_EA0_ATOMIC[11] TCC_ATOMIC[12] TCC_BUBBLE[12] TCC_CYCLE[12] TCC_EA0_ATOMIC[12] TCC_ATOMIC[13] TCC_BUBBLE[13] TCC_CYCLE[13] TCC_EA0_ATOMIC[13] TCC_ATOMIC[14] TCC_BUBBLE[14] TCC_CYCLE[14] TCC_EA0_ATOMIC[14] TCC_ATOMIC[15] TCC_BUBBLE[15] TCC_CYCLE[15] TCC_EA0_ATOMIC[15]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_EA0_ATOMIC_LEVEL[0] TCC_EA0_RDREQ[0] TCC_EA0_RDREQ_32B[0] TCC_EA0_RDREQ_LEVEL[0] TCC_EA0_ATOMIC_LEVEL[1] TCC_EA0_RDREQ[1] TCC_EA0_RDREQ_32B[1] TCC_EA0_RDREQ_LEVEL[1] TCC_EA0_ATOMIC_LEVEL[2] TCC_EA0_RDREQ[2] TCC_EA0_RDREQ_32B[2] TCC_EA0_RDREQ_LEVEL[2] TCC_EA0_ATOMIC_LEVEL[3] TCC_EA0_RDREQ[3] TCC_EA0_RDREQ_32B[3] TCC_EA0_RDREQ_LEVEL[3] TCC_EA0_ATOMIC_LEVEL[4] TCC_EA0_RDREQ[4] TCC_EA0_RDREQ_32B[4] TCC_EA0_RDREQ_LEVEL[4] TCC_EA0_ATOMIC_LEVEL[5] TCC_EA0_RDREQ[5] TCC_EA0_RDREQ_32B[5] TCC_EA0_RDREQ_LEVEL[5] TCC_EA0_ATOMIC_LEVEL[6] TCC_EA0_RDREQ[6] TCC_EA0_RDREQ_32B[6] TCC_EA0_RDREQ_LEVEL[6] TCC_EA0_ATOMIC_LEVEL[7] TCC_EA0_RDREQ[7] TCC_EA0_RDREQ_32B[7] TCC_EA0_RDREQ_LEVEL[7] TCC_EA0_ATOMIC_LEVEL[8] TCC_EA0_RDREQ[8] TCC_EA0_RDREQ_32B[8] TCC_EA0_RDREQ_LEVEL[8] TCC_EA0_ATOMIC_LEVEL[9] TCC_EA0_RDREQ[9] TCC_EA0_RDREQ_32B[9] TCC_EA0_RDREQ_LEVEL[9] TCC_EA0_ATOMIC_LEVEL[10] TCC_EA0_RDREQ[10] TCC_EA0_RDREQ_32B[10] TCC_EA0_RDREQ_LEVEL[10] TCC_EA0_ATOMIC_LEVEL[11] TCC_EA0_RDREQ[11] TCC_EA0_RDREQ_32B[11] TCC_EA0_RDREQ_LEVEL[11] TCC_EA0_ATOMIC_LEVEL[12] TCC_EA0_RDREQ[12] TCC_EA0_RDREQ_32B[12] TCC_EA0_RDREQ_LEVEL[12] TCC_EA0_ATOMIC_LEVEL[13] TCC_EA0_RDREQ[13] TCC_EA0_RDREQ_32B[13] TCC_EA0_RDREQ_LEVEL[13] TCC_EA0_ATOMIC_LEVEL[14] TCC_EA0_RDREQ[14] TCC_EA0_RDREQ_32B[14] TCC_EA0_RDREQ_LEVEL[14] TCC_EA0_ATOMIC_LEVEL[15] TCC_EA0_RDREQ[15] TCC_EA0_RDREQ_32B[15] TCC_EA0_RDREQ_LEVEL[15]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_EA0_WRREQ[0] TCC_EA0_WRREQ_64B[0] TCC_EA0_WRREQ_LEVEL[0] TCC_HIT[0] TCC_EA0_WRREQ[1] TCC_EA0_WRREQ_64B[1] TCC_EA0_WRREQ_LEVEL[1] TCC_HIT[1] TCC_EA0_WRREQ[2] TCC_EA0_WRREQ_64B[2] TCC_EA0_WRREQ_LEVEL[2] TCC_HIT[2] TCC_EA0_WRREQ[3] TCC_EA0_WRREQ_64B[3] TCC_EA0_WRREQ_LEVEL[3] TCC_HIT[3] TCC_EA0_WRREQ[4] TCC_EA0_WRREQ_64B[4] TCC_EA0_WRREQ_LEVEL[4] TCC_HIT[4] TCC_EA0_WRREQ[5] TCC_EA0_WRREQ_64B[5] TCC_EA0_WRREQ_LEVEL[5] TCC_HIT[5] TCC_EA0_WRREQ[6] TCC_EA0_WRREQ_64B[6] TCC_EA0_WRREQ_LEVEL[6] TCC_HIT[6] TCC_EA0_WRREQ[7] TCC_EA0_WRREQ_64B[7] TCC_EA0_WRREQ_LEVEL[7] TCC_HIT[7] TCC_EA0_WRREQ[8] TCC_EA0_WRREQ_64B[8] TCC_EA0_WRREQ_LEVEL[8] TCC_HIT[8] TCC_EA0_WRREQ[9] TCC_EA0_WRREQ_64B[9] TCC_EA0_WRREQ_LEVEL[9] TCC_HIT[9] TCC_EA0_WRREQ[10] TCC_EA0_WRREQ_64B[10] TCC_EA0_WRREQ_LEVEL[10] TCC_HIT[10] TCC_EA0_WRREQ[11] TCC_EA0_WRREQ_64B[11] TCC_EA0_WRREQ_LEVEL[11] TCC_HIT[11] TCC_EA0_WRREQ[12] TCC_EA0_WRREQ_64B[12] TCC_EA0_WRREQ_LEVEL[12] TCC_HIT[12] TCC_EA0_WRREQ[13] TCC_EA0_WRREQ_64B[13] TCC_EA0_WRREQ_LEVEL[13] TCC_HIT[13] TCC_EA0_WRREQ[14] TCC_EA0_WRREQ_64B[14] TCC_EA0_WRREQ_LEVEL[14] TCC_HIT[14] TCC_EA0_WRREQ[15] TCC_EA0_WRREQ_64B[15] TCC_EA0_WRREQ_LEVEL[15] TCC_HIT[15]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_RW_REQ[0] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_RW_REQ[1] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_RW_REQ[2] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_RW_REQ[3] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_RW_REQ[4] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_RW_REQ[5] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_RW_REQ[6] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_RW_REQ[7] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_RW_REQ[8] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_RW_REQ[9] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_RW_REQ[10] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_RW_REQ[11] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_RW_REQ[12] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_RW_REQ[13] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_RW_REQ[14] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_RW_REQ[15]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_TAG_STALL[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_TAG_STALL[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_TAG_STALL[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_TAG_STALL[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_TAG_STALL[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_TAG_STALL[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_TAG_STALL[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_TAG_STALL[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_TAG_STALL[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_TAG_STALL[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_TAG_STALL[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_TAG_STALL[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_TAG_STALL[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_TAG_STALL[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_TAG_STALL[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_TAG_STALL[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA0_WRREQ_sum TCC_EA0_WRREQ_64B_sum TCC_EA0_WR_UNCACHED_32B_sum TCC_EA0_WRREQ_DRAM_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCC_READ_REQ_sum TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA0_RDREQ_sum TCC_EA0_RDREQ_32B_sum TCC_BUBBLE_sum TCC_EA0_RD_UNCACHED_32B_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_NC_READ_REQ_sum TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA0_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_UC_WRITE_REQ_sum TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA0_ATOMIC_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_CC_ATOMIC_REQ_sum TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA0_RDREQ_LEVEL_sum TCC_EA0_WRREQ_LEVEL_sum TCC_EA0_ATOMIC_LEVEL_sum TCC_EA0_WRREQ_STALL_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ TCP_PENDING_STALL_CYCLES_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel:
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Correlation_ID,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,Wave_Size_1,Correlation_ID_1,XCC_Index,TCC_ATOMIC[0],TCC_BUBBLE[0],TCC_CYCLE[0],TCC_EA0_ATOMIC[0],TCC_ATOMIC[1],TCC_BUBBLE[1],TCC_CYCLE[1],TCC_EA0_ATOMIC[1],TCC_ATOMIC[2],TCC_BUBBLE[2],TCC_CYCLE[2],TCC_EA0_ATOMIC[2],TCC_ATOMIC[3],TCC_BUBBLE[3],TCC_CYCLE[3],TCC_EA0_ATOMIC[3],TCC_ATOMIC[4],TCC_BUBBLE[4],TCC_CYCLE[4],TCC_EA0_ATOMIC[4],TCC_ATOMIC[5],TCC_BUBBLE[5],TCC_CYCLE[5],TCC_EA0_ATOMIC[5],TCC_ATOMIC[6],TCC_BUBBLE[6],TCC_CYCLE[6],TCC_EA0_ATOMIC[6],TCC_ATOMIC[7],TCC_BUBBLE[7],TCC_CYCLE[7],TCC_EA0_ATOMIC[7],TCC_ATOMIC[8],TCC_BUBBLE[8],TCC_CYCLE[8],TCC_EA0_ATOMIC[8],TCC_ATOMIC[9],TCC_BUBBLE[9],TCC_CYCLE[9],TCC_EA0_ATOMIC[9],TCC_ATOMIC[10],TCC_BUBBLE[10],TCC_CYCLE[10],TCC_EA0_ATOMIC[10],TCC_ATOMIC[11],TCC_BUBBLE[11],TCC_CYCLE[11],TCC_EA0_ATOMIC[11],TCC_ATOMIC[12],TCC_BUBBLE[12],TCC_CYCLE[12],TCC_EA0_ATOMIC[12],TCC_ATOMIC[13],TCC_BUBBLE[13],TCC_CYCLE[13],TCC_EA0_ATOMIC[13],TCC_ATOMIC[14],TCC_BUBBLE[14],TCC_CYCLE[14],TCC_EA0_ATOMIC[14],TCC_ATOMIC[15],TCC_BUBBLE[15],TCC_CYCLE[15],TCC_EA0_ATOMIC[15],TCC_ATOMIC[16],TCC_BUBBLE[16],TCC_CYCLE[16],TCC_EA0_ATOMIC[16],TCC_ATOMIC[17],TCC_BUBBLE[17],TCC_CYCLE[17],TCC_EA0_ATOMIC[17],TCC_ATOMIC[18],TCC_BUBBLE[18],TCC_CYCLE[18],TCC_EA0_ATOMIC[18],TCC_ATOMIC[19],TCC_BUBBLE[19],TCC_CYCLE[19],TCC_EA0_ATOMIC[19],TCC_ATOMIC[20],TCC_BUBBLE[20],TCC_CYCLE[20],TCC_EA0_ATOMIC[20],TCC_ATOMIC[21],TCC_BUBBLE[21],TCC_CYCLE[21],TCC_EA0_ATOMIC[21],TCC_ATOMIC[22],TCC_BUBBLE[22],TCC_CYCLE[22],TCC_EA0_ATOMIC[22],TCC_ATOMIC[23],TCC_BUBBLE[23],TCC_CYCLE[23],TCC_EA0_ATOMIC[23],TCC_ATOMIC[24],TCC_BUBBLE[24],TCC_CYCLE[24],TCC_EA0_ATOMIC[24],TCC_ATOMIC[25],TCC_BUBBLE[25],TCC_CYCLE[25],TCC_EA0_ATOMIC[25],TCC_ATOMIC[26],TCC_BUBBLE[26],TCC_CYCLE[26],TCC_EA0_ATOMIC[26],TCC_ATOMIC[27],TCC_BUBBLE[27],TCC_CYCLE[27],TCC_EA0_ATOMIC[27],TCC_ATOMIC[28],TCC_BUBBLE[28],TCC_CYCLE[28],TCC_EA0_ATOMIC[28],TCC_ATOMIC[29],TCC_BUBBLE[29],TCC_CYCLE[29],TCC_EA0_ATOMIC[29],TCC_ATOMIC[30],TCC_BUBBLE[30],TCC_CYCLE[30],TCC_EA0_ATOMIC[30],TCC_ATOMIC[31],TCC_BUBBLE[31],TCC_CYCLE[31],TCC_EA0_ATOMIC[31],TCC_ATOMIC[32],TCC_BUBBLE[32],TCC_CYCLE[32],TCC_EA0_ATOMIC[32],TCC_ATOMIC[33],TCC_BUBBLE[33],TCC_CYCLE[33],TCC_EA0_ATOMIC[33],TCC_ATOMIC[34],TCC_BUBBLE[34],TCC_CYCLE[34],TCC_EA0_ATOMIC[34],TCC_ATOMIC[35],TCC_BUBBLE[35],TCC_CYCLE[35],TCC_EA0_ATOMIC[35],TCC_ATOMIC[36],TCC_BUBBLE[36],TCC_CYCLE[36],TCC_EA0_ATOMIC[36],TCC_ATOMIC[37],TCC_BUBBLE[37],TCC_CYCLE[37],TCC_EA0_ATOMIC[37],TCC_ATOMIC[38],TCC_BUBBLE[38],TCC_CYCLE[38],TCC_EA0_ATOMIC[38],TCC_ATOMIC[39],TCC_BUBBLE[39],TCC_CYCLE[39],TCC_EA0_ATOMIC[39],TCC_ATOMIC[40],TCC_BUBBLE[40],TCC_CYCLE[40],TCC_EA0_ATOMIC[40],TCC_ATOMIC[41],TCC_BUBBLE[41],TCC_CYCLE[41],TCC_EA0_ATOMIC[41],TCC_ATOMIC[42],TCC_BUBBLE[42],TCC_CYCLE[42],TCC_EA0_ATOMIC[42],TCC_ATOMIC[43],TCC_BUBBLE[43],TCC_CYCLE[43],TCC_EA0_ATOMIC[43],TCC_ATOMIC[44],TCC_BUBBLE[44],TCC_CYCLE[44],TCC_EA0_ATOMIC[44],TCC_ATOMIC[45],TCC_BUBBLE[45],TCC_CYCLE[45],TCC_EA0_ATOMIC[45],TCC_ATOMIC[46],TCC_BUBBLE[46],TCC_CYCLE[46],TCC_EA0_ATOMIC[46],TCC_ATOMIC[47],TCC_BUBBLE[47],TCC_CYCLE[47],TCC_EA0_ATOMIC[47],TCC_ATOMIC[48],TCC_BUBBLE[48],TCC_CYCLE[48],TCC_EA0_ATOMIC[48],TCC_ATOMIC[49],TCC_BUBBLE[49],TCC_CYCLE[49],TCC_EA0_ATOMIC[49],TCC_ATOMIC[50],TCC_BUBBLE[50],TCC_CYCLE[50],TCC_EA0_ATOMIC[50],TCC_ATOMIC[51],TCC_BUBBLE[51],TCC_CYCLE[51],TCC_EA0_ATOMIC[51],TCC_ATOMIC[52],TCC_BUBBLE[52],TCC_CYCLE[52],TCC_EA0_ATOMIC[52],TCC_ATOMIC[53],TCC_BUBBLE[53],TCC_CYCLE[53],TCC_EA0_ATOMIC[53],TCC_ATOMIC[54],TCC_BUBBLE[54],TCC_CYCLE[54],TCC_EA0_ATOMIC[54],TCC_ATOMIC[55],TCC_BUBBLE[55],TCC_CYCLE[55],TCC_EA0_ATOMIC[55],TCC_ATOMIC[56],TCC_BUBBLE[56],TCC_CYCLE[56],TCC_EA0_ATOMIC[56],TCC_ATOMIC[57],TCC_BUBBLE[57],TCC_CYCLE[57],TCC_EA0_ATOMIC[57],TCC_ATOMIC[58],TCC_BUBBLE[58],TCC_CYCLE[58],TCC_EA0_ATOMIC[58],TCC_ATOMIC[59],TCC_BUBBLE[59],TCC_CYCLE[59],TCC_EA0_ATOMIC[59],TCC_ATOMIC[60],TCC_BUBBLE[60],TCC_CYCLE[60],TCC_EA0_ATOMIC[60],TCC_ATOMIC[61],TCC_BUBBLE[61],TCC_CYCLE[61],TCC_EA0_ATOMIC[61],TCC_ATOMIC[62],TCC_BUBBLE[62],TCC_CYCLE[62],TCC_EA0_ATOMIC[62],TCC_ATOMIC[63],TCC_BUBBLE[63],TCC_CYCLE[63],TCC_EA0_ATOMIC[63],TCC_ATOMIC[64],TCC_BUBBLE[64],TCC_CYCLE[64],TCC_EA0_ATOMIC[64],TCC_ATOMIC[65],TCC_BUBBLE[65],TCC_CYCLE[65],TCC_EA0_ATOMIC[65],TCC_ATOMIC[66],TCC_BUBBLE[66],TCC_CYCLE[66],TCC_EA0_ATOMIC[66],TCC_ATOMIC[67],TCC_BUBBLE[67],TCC_CYCLE[67],TCC_EA0_ATOMIC[67],TCC_ATOMIC[68],TCC_BUBBLE[68],TCC_CYCLE[68],TCC_EA0_ATOMIC[68],TCC_ATOMIC[69],TCC_BUBBLE[69],TCC_CYCLE[69],TCC_EA0_ATOMIC[69],TCC_ATOMIC[70],TCC_BUBBLE[70],TCC_CYCLE[70],TCC_EA0_ATOMIC[70],TCC_ATOMIC[71],TCC_BUBBLE[71],TCC_CYCLE[71],TCC_EA0_ATOMIC[71],TCC_ATOMIC[72],TCC_BUBBLE[72],TCC_CYCLE[72],TCC_EA0_ATOMIC[72],TCC_ATOMIC[73],TCC_BUBBLE[73],TCC_CYCLE[73],TCC_EA0_ATOMIC[73],TCC_ATOMIC[74],TCC_BUBBLine truncated
0,60633,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,2806891.0,0.0,0.0,65536.0,60576.0,160.0,4800.0,32768.0,64,0,0,0.0,512.0,47816.0,0.0,0.0,512.0,47816.0,0.0,0.0,512.0,47816.0,0.0,0.0,512.0,47816.0,0.0,0.0,512.0,47816.0,0.0,0.0,512.0,47816.0,0.0,0.0,512.0,47816.0,0.0,0.0,512.0,47816.0,0.0,0.0,512.0,47816.0,0.0,0.0,512.0,47816.0,0.0,0.0,512.0,47816.0,0.0,0.0,512.0,47816.0,0.0,0.0,512.0,47816.0,0.0,0.0,512.0,47816.0,0.0,0.0,512.0,47816.0,0.0,0.0,512.0,47816.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,48612.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,60573.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,71121.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,89829.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,100241.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,102934.0,0.0,0.0,512.0,113148.0,0.0,0.0,512.0,113148.0,0.0,0.0,512.0,113148.0,0.0,0.0,512.0,113148.0,0.0,0.0,512.0,113148.0,0.0,0.0,512.0,113148.0,0.0,0.0,512.0,113148.0,0.0,0.0,512.0,113148.0,0.0,0.0,512.0,113148.0,0.0,0.0,512.0,113148.0,0.0,0.0,512.0,113148.0,0.0,0.0,512.0,113148.0,0.0,0.0,512.0,113148.0,0.0,0.0,512.0,113148.0,0.0,0.0,512.0,113148.0,0.0,0.0,512.0,113148.0,0.0,64,0,0.0,0.0,1048576.0,0.0,0.0,0.0,0.0,0.0,0.0,32768.0,0.0,16384.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,64,0,131072.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,16384.0,0.0,0.0,109988688.0,70351897.0,218030.0,0.0,0.0,65536.0,131072.0,64,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,56966.0,33553.0,2088347.0,696.0,0.0,298326.0,0.0,0.0,66160.0,131328.0,197488.0,0.0,2097152.0,1048576.0,1048576.0,2097152.0,0.0,16384.0,64,0,0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1031.0,597.0,1621.0,1616.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1029.0,595.0,1619.0,1616.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1029.0,595.0,1619.0,1616.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1028.0,594.0,1618.0,1616.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.Line truncated
1,60633,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,2809976.0,0.0,0.0,65536.0,60576.0,160.0,4800.0,32768.0,64,0,0,0.0,512.0,42796.0,0.0,0.0,512.0,42796.0,0.0,0.0,512.0,42796.0,0.0,0.0,512.0,42796.0,0.0,0.0,512.0,42796.0,0.0,0.0,512.0,42796.0,0.0,0.0,512.0,42796.0,0.0,0.0,512.0,42796.0,0.0,0.0,512.0,42796.0,0.0,0.0,512.0,42796.0,0.0,0.0,512.0,42796.0,0.0,0.0,512.0,42796.0,0.0,0.0,512.0,42796.0,0.0,0.0,512.0,42796.0,0.0,0.0,512.0,42796.0,0.0,0.0,512.0,42796.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,44613.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,63251.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,73365.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,85157.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,96097.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,95404.0,0.0,0.0,512.0,105664.0,0.0,0.0,512.0,105664.0,0.0,0.0,512.0,105664.0,0.0,0.0,512.0,105664.0,0.0,0.0,512.0,105664.0,0.0,0.0,512.0,105664.0,0.0,0.0,512.0,105664.0,0.0,0.0,512.0,105664.0,0.0,0.0,512.0,105664.0,0.0,0.0,512.0,105664.0,0.0,0.0,512.0,105664.0,0.0,0.0,512.0,105664.0,0.0,0.0,512.0,105664.0,0.0,0.0,512.0,105664.0,0.0,0.0,512.0,105664.0,0.0,0.0,512.0,105664.0,0.0,64,0,0.0,0.0,1048576.0,0.0,0.0,0.0,0.0,0.0,0.0,32768.0,0.0,16384.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,64,0,131072.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,16384.0,0.0,0.0,53951831.0,79878391.0,251624.0,0.0,0.0,65536.0,131072.0,64,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,45515.0,24736.0,2027585.0,9618.0,0.0,287163.0,0.0,0.0,65536.0,131336.0,196872.0,0.0,2097152.0,1048576.0,1048576.0,2097152.0,0.0,16384.0,64,0,0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1025.0,513.0,1537.0,1536.0,1031.0,519.0,1543.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1026.0,514.0,1538.0,1536.0,1025.0,513.0,1537.0,1536.0,1030.0,518.0,1542.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1026.0,514.0,1538.0,1536.0,1025.0,513.0,1537.0,1536.0,1029.0,517.0,1541.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1026.0,514.0,1538.0,1536.0,1025.0,513.0,1537.0,1536.0,1027.0,515.0,1539.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,102Line truncated
2,60633,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,2853812.0,0.0,0.0,65536.0,60576.0,160.0,4800.0,32768.0,64,0,0,0.0,512.0,42780.0,0.0,0.0,512.0,42780.0,0.0,0.0,512.0,42780.0,0.0,0.0,512.0,42780.0,0.0,0.0,512.0,42780.0,0.0,0.0,512.0,42780.0,0.0,0.0,512.0,42780.0,0.0,0.0,512.0,42780.0,0.0,0.0,512.0,42780.0,0.0,0.0,512.0,42780.0,0.0,0.0,512.0,42780.0,0.0,0.0,512.0,42780.0,0.0,0.0,512.0,42780.0,0.0,0.0,512.0,42780.0,0.0,0.0,512.0,42780.0,0.0,0.0,512.0,42780.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,36516.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,56360.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,63214.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,79700.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,89231.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,88504.0,0.0,0.0,512.0,99010.0,0.0,0.0,512.0,99010.0,0.0,0.0,512.0,99010.0,0.0,0.0,512.0,99010.0,0.0,0.0,512.0,99010.0,0.0,0.0,512.0,99010.0,0.0,0.0,512.0,99010.0,0.0,0.0,512.0,99010.0,0.0,0.0,512.0,99010.0,0.0,0.0,512.0,99010.0,0.0,0.0,512.0,99010.0,0.0,0.0,512.0,99010.0,0.0,0.0,512.0,99010.0,0.0,0.0,512.0,99010.0,0.0,0.0,512.0,99010.0,0.0,0.0,512.0,99010.0,0.0,64,0,0.0,0.0,1048576.0,0.0,0.0,0.0,0.0,0.0,0.0,32768.0,0.0,16384.0,0.0,0.0,29.0,0.0,0.0,0.0,0.0,0.0,64,0,131072.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,16384.0,0.0,0.0,40181609.0,57766160.0,168892.0,0.0,0.0,65536.0,131072.0,64,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,44178.0,25744.0,1994761.0,7336.0,0.0,279252.0,0.0,0.0,65536.0,131333.0,196869.0,0.0,2097152.0,1048576.0,1048576.0,2097152.0,0.0,16384.0,64,0,0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1029.0,517.0,1541.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1029.0,517.0,1541.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1028.0,516.0,1540.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1027.0,515.0,1539.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.Line truncated
@@ -0,0 +1,2 @@
workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
path,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Wed 29 May 2024 11:59:34 AM (CDT),2,splinter-126-wr-c6,AMD Ryzen 9 7950X 16-Core Processor,"American Megatrends International, LLC.VS2683299N.FD",Ubuntu 22.04.4 LTS,5.18.2-mi300-build-140423-ubuntu-22.04+,,114656528,,6.2.0-13611,113-MI3SRIOV-001,SPX,NPS1,MI300X_A1,gfx942,32,4096,304,4,32,64,1024,32,2100,1300,2100,1300,128,32,160,4,5324.8,8
1 workload_name command ip_blocks timestamp version hostname cpu_model sbios linux_distro linux_kernel_version amd_gpu_kernel_version cpu_memory gpu_memory rocm_version vbios compute_partition memory_partition gpu_model gpu_arch gpu_l1 gpu_l2 cu_per_gpu simd_per_cu se_per_gpu wave_size workgroup_max_size max_waves_per_cu max_sclk max_mclk cur_sclk cur_mclk total_l2_chan lds_banks_per_cu sqc_per_gpu pipes_per_gpu hbm_bw num_xcd
2 path ./tests/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF Wed 29 May 2024 11:59:34 AM (CDT) 2 splinter-126-wr-c6 AMD Ryzen 9 7950X 16-Core Processor American Megatrends International, LLC.VS2683299N.FD Ubuntu 22.04.4 LTS 5.18.2-mi300-build-140423-ubuntu-22.04+ 114656528 6.2.0-13611 113-MI3SRIOV-001 SPX NPS1 MI300X_A1 gfx942 32 4096 304 4 32 64 1024 32 2100 1300 2100 1300 128 32 160 4 5324.8 8
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID
1,60633,1,963595,963595,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268071613,716165268087773,0
2,60633,1,963595,963595,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268110013,716165268124653,0
3,60633,1,963595,963595,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716165268144733,716165268158533,0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID
2 1 60633 1 963595 963595 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268071613 716165268087773 0
3 2 60633 1 963595 963595 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268110013 716165268124653 0
4 3 60633 1 963595 963595 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716165268144733 716165268158533 0