Add vcopy workloads for MI300A and MI300X

Signed-off-by: coleramos425 <colramos@amd.com>


[ROCm/rocprofiler-compute commit: c079f1330b]
Этот коммит содержится в:
coleramos425 authored and Cole Ramos committed 2024-05-31 16:09:58 -05:00
1 родитель 34b289e66d
Коммит 2bc71cc0d8
66 files changed
+712

No files matched your search

+4
Просмотреть файл
@@ -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
0,11995,1,239059,239059,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504048950,162067504056482,0,208371.0,208371.0,16384.0,65536.0,27933.0,2268960.0
1,11995,1,239059,239059,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504097624,162067504103513,0,200939.0,200939.0,16384.0,65536.0,13020.0,1048740.0
2,11995,1,239059,239059,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504075511,162067504081560,0,177122.0,177122.0,16384.0,65536.0,13215.0,1049244.0
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 239059 239059 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504048950 162067504056482 0 208371.0 208371.0 16384.0 65536.0 27933.0 2268960.0
3 1 11995 1 239059 239059 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504097624 162067504103513 0 200939.0 200939.0 16384.0 65536.0 13020.0 1048740.0
4 2 11995 1 239059 239059 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504075511 162067504081560 0 177122.0 177122.0 16384.0 65536.0 13215.0 1049244.0
+4
Просмотреть файл
@@ -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
0,11995,1,239070,239070,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504048950,162067504056482,0,0.0,0.0,0.0
1,11995,1,239070,239070,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504097624,162067504103513,0,0.0,0.0,0.0
2,11995,1,239070,239070,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504075511,162067504081560,0,0.0,0.0,0.0
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 239070 239070 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504048950 162067504056482 0 0.0 0.0 0.0
3 1 11995 1 239070 239070 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504097624 162067504103513 0 0.0 0.0 0.0
4 2 11995 1 239070 239070 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504075511 162067504081560 0 0.0 0.0 0.0
+4
Просмотреть файл
@@ -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
0,11995,1,239081,239081,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504048950,162067504056482,0,65536.0,282426.0,22607296.0
1,11995,1,239081,239081,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504097624,162067504103513,0,65536.0,262012.0,20878056.0
2,11995,1,239081,239081,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504075511,162067504081560,0,65536.0,221574.0,17737216.0
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 239081 239081 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504048950 162067504056482 0 65536.0 282426.0 22607296.0
3 1 11995 1 239081 239081 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504097624 162067504103513 0 65536.0 262012.0 20878056.0
4 2 11995 1 239081 239081 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504075511 162067504081560 0 65536.0 221574.0 17737216.0
+4
Просмотреть файл
@@ -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
0,11995,1,239092,239092,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504048950,162067504056482,0,32768.0,525409.0,42022704.0
1,11995,1,239092,239092,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504097624,162067504103513,0,32768.0,405541.0,32437816.0
2,11995,1,239092,239092,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504075511,162067504081560,0,32768.0,414783.0,33168224.0
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 239092 239092 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504048950 162067504056482 0 32768.0 525409.0 42022704.0
3 1 11995 1 239092 239092 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504097624 162067504103513 0 32768.0 405541.0 32437816.0
4 2 11995 1 239092 239092 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504075511 162067504081560 0 32768.0 414783.0 33168224.0
+4
Просмотреть файл
@@ -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
0,11995,1,239103,239103,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504048950,162067504056482,0,220553.0,220553.0,125881.0,882212.0,16384.0,13496981.0,243456.0,0.0,54413320.0
1,11995,1,239103,239103,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504097624,162067504103513,0,186745.0,186745.0,104964.0,746980.0,16384.0,10050383.0,189145.0,0.0,40592236.0
2,11995,1,239103,239103,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504075511,162067504081560,0,177319.0,177319.0,96370.0,709276.0,16384.0,9944060.0,186126.0,0.0,40164888.0
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 239103 239103 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504048950 162067504056482 0 220553.0 220553.0 125881.0 882212.0 16384.0 13496981.0 243456.0 0.0 54413320.0
3 1 11995 1 239103 239103 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504097624 162067504103513 0 186745.0 186745.0 104964.0 746980.0 16384.0 10050383.0 189145.0 0.0 40592236.0
4 2 11995 1 239103 239103 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504075511 162067504081560 0 177319.0 177319.0 96370.0 709276.0 16384.0 9944060.0 186126.0 0.0 40164888.0
+251
Просмотреть файл
@@ -0,0 +1,251 @@
Omniperf version: 2.0.0
Profiler choice: rocprofv2
Path: /home/colramos/omniperf/tests/workloads/vcopy/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/vcopy/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
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH_LEVEL
|-> [/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
[profiling] Current input file: tests/workloads/vcopy/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
|-> [/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/vcopy/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/vcopy/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
[profiling] Current input file: tests/workloads/vcopy/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
[profiling] Current input file: tests/workloads/vcopy/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
[profiling] Current input file: tests/workloads/vcopy/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
[profiling] Current input file: tests/workloads/vcopy/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
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_16
|-> [/opt/rocm/bin/rocprofv2] - SQC_ICACHE_REQ
|-> [/opt/rocm/bin/rocprofv2] - SQC_ICACHE_HITS
|-> [/opt/rocm/bin/rocprofv2] - SQC_ICACHE_MISSES
|-> [/opt/rocm/bin/rocprofv2] - SQC_ICACHE_MISSES_DUPLICATE
[profiling] Current input file: tests/workloads/vcopy/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/vcopy/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
|-> [/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
[profiling] Current input file: tests/workloads/vcopy/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]
[profiling] Current input file: tests/workloads/vcopy/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]
[profiling] Current input file: tests/workloads/vcopy/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]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[5]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[5]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[5]
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[5]
[profiling] Current input file: tests/workloads/vcopy/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]
[profiling] Current input file: tests/workloads/vcopy/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/vcopy/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
[profiling] Current input file: tests/workloads/vcopy/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
[profiling] Current input file: tests/workloads/vcopy/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
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_VALU
[profiling] Current input file: tests/workloads/vcopy/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
[profiling] Current input file: tests/workloads/vcopy/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
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_ADDR_CONFLICT
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_UNALIGNED_STALL
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_EQ_64
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_64
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_48
[profiling] Current input file: tests/workloads/vcopy/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
[profiling] Current input file: tests/workloads/vcopy/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
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_BF16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_F64
[profiling] Current input file: tests/workloads/vcopy/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
[profiling] Current input file: tests/workloads/vcopy/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
[roofline] Roofline temporarily disabled in MI300
+5
Просмотреть файл
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
+5
Просмотреть файл
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
+5
Просмотреть файл
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
+5
Просмотреть файл
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
gpu:
range:
kernel:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel:
+4
Просмотреть файл
@@ -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)",0,16384.0,16384.0,11824840.0,823177.0,278528.0,0.0,0.0,98304.0,347497.0,0.0,0.0,443208.0,114369.0,32768.0,131072.0,131072.0,131072.0,0.0,0.0,524288.0,452708.0,1820.0,64,0,0,1360.0,1360.0,556952.0,680.0,1360.0,1360.0,566488.0,680.0,1360.0,1360.0,568549.0,680.0,1360.0,1360.0,573041.0,680.0,1360.0,1360.0,561814.0,680.0,1360.0,1360.0,567061.0,680.0,1360.0,1360.0,574536.0,680.0,1360.0,1360.0,570425.0,738.0,1368.0,1368.0,548422.0,684.0,1368.0,1368.0,556019.0,684.0,1368.0,1368.0,566154.0,684.0,1368.0,1368.0,568870.0,703.0,1368.0,1368.0,558192.0,684.0,1368.0,1368.0,565321.0,684.0,1368.0,1368.0,579473.0,684.0,1368.0,1368.0,577458.0,684.0,1360.0,1360.0,551043.0,680.0,1360.0,1360.0,557839.0,680.0,1360.0,1360.0,566019.0,680.0,1360.0,1360.0,566210.0,699.0,1360.0,1360.0,558870.0,680.0,1360.0,1360.0,563880.0,680.0,1360.0,1360.0,576261.0,680.0,1360.0,1360.0,571927.0,680.0,1368.0,1368.0,550938.0,684.0,1368.0,1368.0,561496.0,684.0,1368.0,1368.0,561781.0,684.0,1368.0,1368.0,565303.0,684.0,1368.0,1368.0,557352.0,684.0,1368.0,1368.0,561957.0,684.0,1368.0,1368.0,571133.0,684.0,1368.0,1368.0,565023.0,742.0,1364.0,1364.0,533435.0,682.0,1364.0,1364.0,539359.0,682.0,1364.0,1364.0,547937.0,682.0,1364.0,1364.0,547083.0,701.0,1364.0,1364.0,540317.0,682.0,1364.0,1364.0,543391.0,682.0,1364.0,1364.0,554244.0,682.0,1364.0,1364.0,550362.0,682.0,1368.0,1368.0,535923.0,684.0,1368.0,1368.0,547831.0,684.0,1368.0,1368.0,557598.0,684.0,1368.0,1368.0,564674.0,684.0,1368.0,1368.0,544182.0,684.0,1368.0,1368.0,548139.0,684.0,1368.0,1368.0,557353.0,684.0,1368.0,1368.0,565284.0,742.0,1364.0,1364.0,532807.0,682.0,1364.0,1364.0,544188.0,682.0,1364.0,1364.0,540243.0,682.0,1364.0,1364.0,547213.0,682.0,1364.0,1364.0,543903.0,682.0,1364.0,1364.0,547957.0,682.0,1364.0,1364.0,551382.0,682.0,1364.0,1364.0,546760.0,740.0,1368.0,1368.0,527629.0,684.0,1368.0,1368.0,533714.0,684.0,1368.0,1368.0,543952.0,684.0,1368.0,1368.0,545669.0,703.0,1368.0,1368.0,541600.0,684.0,1368.0,1368.0,542647.0,684.0,1368.0,1368.0,554380.0,684.0,1368.0,1368.0,550594.0,684.0,1364.0,1364.0,544902.0,682.0,1364.0,1364.0,554762.0,682.0,1364.0,1364.0,554792.0,682.0,1364.0,1364.0,561290.0,701.0,1364.0,1364.0,548092.0,682.0,1364.0,1364.0,552335.0,682.0,1364.0,1364.0,560215.0,682.0,1364.0,1364.0,556568.0,682.0,1368.0,1368.0,539715.0,684.0,1368.0,1368.0,546001.0,684.0,1368.0,1368.0,556919.0,684.0,1368.0,1368.0,553720.0,684.0,1368.0,1368.0,547021.0,684.0,1368.0,1368.0,551716.0,684.0,1368.0,1368.0,564642.0,684.0,1368.0,1368.0,559099.0,742.0,1364.0,1364.0,541700.0,682.0,1364.0,1364.0,548235.0,682.0,1364.0,1364.0,559090.0,682.0,1364.0,1364.0,553976.0,682.0,1364.0,1364.0,554773.0,682.0,1364.0,1364.0,554251.0,682.0,1364.0,1364.0,567477.0,682.0,1364.0,1364.0,564180.0,740.0,1368.0,1368.0,538926.0,684.0,1368.0,1368.0,549141.0,684.0,1368.0,1368.0,545582.0,684.0,1368.0,1368.0,553155.0,703.0,1368.0,1368.0,544140.0,684.0,1368.0,1368.0,549359.0,684.0,1368.0,1368.0,553065.0,684.0,1368.0,1368.0,550423.0,684.0,64,0,6291456.0,65536.0,0.0,0.0,0.0,16384.0,0.0,0.0,0.0,0.0,16384.0,32768.0,49354.0,65579.0,16182.0,47176.0,0.0,0.0,0.0,0.0,64,0,0,869.0,0.0,1368.0,873.0,0.0,1368.0,933.0,0.0,1368.0,933.0,0.0,1368.0,1161.0,0.0,1368.0,1164.0,0.0,1368.0,1270.0,0.0,1368.0,1180.0,0.0,1368.0,1145.0,0.0,1364.0,1194.0,0.0,1364.0,1192.0,0.0,1364.0,786.0,0.0,1364.0,1207.0,0.0,1364.0,1036.0,0.0,1364.0,1228.0,0.0,1364.0,791.0,0.0,1364.0,1183.0,0.0,1368.0,1233.0,0.0,1368.0,1232.0,0.0,1368.0,935.0,0.0,1368.0,1227.0,0.0,1368.0,1143.0,0.0,1368.0,1291.0,0.0,1368.0,954.0,0.0,1368.0,796.0,0.0,1364.0,804.0,0.0,1364.0,810.0,0.0,1364.0,836.0,0.0,1364.0,1204.0,0.0,1364.0,1273.0,0.0,1364.0,1224.0,0.0,1364.0,1152.0,0.0,1364.0,1104.0,0.0,1368.0,1172.0,0.0,1368.0,1158.0,0.0,1368.0,760.0,0.0,1368.0,1253.0,0.0,1368.0,1013.0,0.0,1368.0,1212.0,0.0,1368.0,782.0,0.0,1368.0,880.0,0.0,1360.0,890.0,0.0,1360.0,831.0,0.0,1360.0,887.0,0.0,1360.0,1245.0,0.0,1360.0,1179.0,0.0,1360.0,1238.0,0.0,1360.0,1171.0,0.0,1360.0,765.0,0.0,1368.0,769.0,0.0,1368.0,760.0,0.0,1368.0,762.0,0.0,1368.0,1172.0,0.0,1368.0,1101.0,0.0,1368.0,1298.0,0.0,1368.0,1102.0,0.0,1368.0,1187.0,0.0,1360.0,1316.0,0.0,1360.0,1262.0,0.0,1360.0,840.0,0.0,1360.0,1253.0,0.0,1360.0,1055.0,0.0,1360.0,1251.0,0.0,1360.0,851.0,0.0,1360.0,1124.0,0.0,1364.0,1217.0,0.0,1364.0,1124.0,0.0,1364.0,892.0,0.0,1364.0,1189.0,0.0,1364.0,966.0,0.0,1364.0,1303.0,0.0,1364.0,887.0,0.0,1364.0,845.0,0.0,1368.0,856.0,0.0,1368.0,955.0,0.0,1368.0,976.0,0.0,1368.0,1373.0,0.0,1368.0,1389.0,0.0,1368.0,1272.0,0.0,1368.0,1177.0,0.0,1368.0,790.0,0.0,1364.0,790.0,0.0,1364.0,793.0,0.0,1364.0,795.0,0.0,1364.0,1212.0,0.0,1364.0,1135.0,0.0,1364.0,1210.0,0.0,1364.0,1124.0,0.0,1364.0,1175.0,0.0,1368.0,1255.0,0.0,1368.0,1176.0,0.0,1368.0,880.0,0.0,1368.0,1263.0,0.0,1368.0,1076.0,0.0,1368.0,1253.0,0.0,1368.0,878.0,0.0,1368.0,64,0,0.0,49152.0,32768.0,65536.0,32768.0,0.0,0.0,0.0,11126.0,0.0,510.0,597828.0,78.0,0.0,0.0,0.0,66034.0,65536.0,131072.0,0.0,0.0,5242Line truncated
1,11995,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,16384.0,16384.0,9817554.0,822050.0,278528.0,0.0,0.0,98304.0,240433.0,0.0,0.0,462659.0,108226.0,32768.0,131072.0,131072.0,131072.0,0.0,0.0,524288.0,453989.0,1824.0,64,0,0,1368.0,1368.0,573935.0,684.0,1368.0,1368.0,583961.0,684.0,1368.0,1368.0,579543.0,684.0,1368.0,1368.0,587456.0,684.0,1368.0,1368.0,574004.0,684.0,1368.0,1368.0,578920.0,684.0,1368.0,1368.0,586832.0,684.0,1368.0,1368.0,586504.0,684.0,1360.0,1360.0,556518.0,680.0,1360.0,1360.0,564989.0,680.0,1360.0,1360.0,574220.0,680.0,1360.0,1360.0,573061.0,699.0,1360.0,1360.0,573547.0,680.0,1360.0,1360.0,577232.0,680.0,1360.0,1360.0,585528.0,680.0,1360.0,1360.0,581335.0,680.0,1364.0,1364.0,552490.0,682.0,1364.0,1364.0,561209.0,682.0,1364.0,1364.0,569189.0,682.0,1364.0,1364.0,567807.0,701.0,1364.0,1364.0,570222.0,682.0,1364.0,1364.0,573824.0,682.0,1364.0,1364.0,582234.0,682.0,1364.0,1364.0,583786.0,682.0,1368.0,1368.0,595370.0,684.0,1368.0,1368.0,608716.0,684.0,1368.0,1368.0,603470.0,684.0,1368.0,1368.0,627357.0,684.0,1368.0,1368.0,611458.0,684.0,1368.0,1368.0,614896.0,684.0,1368.0,1368.0,615202.0,684.0,1368.0,1368.0,609450.0,684.0,1368.0,1368.0,583470.0,684.0,1368.0,1368.0,589714.0,684.0,1368.0,1368.0,601374.0,684.0,1368.0,1368.0,613387.0,703.0,1368.0,1368.0,598724.0,684.0,1368.0,1368.0,603544.0,684.0,1368.0,1368.0,610013.0,684.0,1368.0,1368.0,611475.0,684.0,1364.0,1364.0,560367.0,682.0,1364.0,1364.0,574963.0,682.0,1364.0,1364.0,570937.0,682.0,1364.0,1364.0,568268.0,682.0,1364.0,1364.0,562614.0,682.0,1364.0,1364.0,562777.0,682.0,1364.0,1364.0,574105.0,682.0,1364.0,1364.0,567409.0,682.0,1368.0,1368.0,559357.0,684.0,1368.0,1368.0,573874.0,684.0,1368.0,1368.0,567330.0,684.0,1368.0,1368.0,569390.0,684.0,1368.0,1368.0,559357.0,684.0,1368.0,1368.0,563469.0,684.0,1368.0,1368.0,578039.0,684.0,1368.0,1368.0,574219.0,684.0,1364.0,1364.0,564220.0,682.0,1364.0,1364.0,573089.0,682.0,1364.0,1364.0,582583.0,682.0,1364.0,1364.0,583187.0,701.0,1364.0,1364.0,581868.0,682.0,1364.0,1364.0,579849.0,682.0,1364.0,1364.0,596973.0,682.0,1364.0,1364.0,587378.0,682.0,1368.0,1368.0,557029.0,684.0,1368.0,1368.0,566761.0,684.0,1368.0,1368.0,561459.0,684.0,1368.0,1368.0,568654.0,703.0,1368.0,1368.0,560206.0,684.0,1368.0,1368.0,565456.0,684.0,1368.0,1368.0,575972.0,684.0,1368.0,1368.0,571433.0,684.0,1364.0,1364.0,557536.0,682.0,1364.0,1364.0,563711.0,682.0,1364.0,1364.0,571441.0,682.0,1364.0,1364.0,570274.0,682.0,1364.0,1364.0,561207.0,682.0,1364.0,1364.0,564560.0,682.0,1364.0,1364.0,581250.0,682.0,1364.0,1364.0,580100.0,682.0,1360.0,1360.0,555895.0,680.0,1360.0,1360.0,557898.0,680.0,1360.0,1360.0,563587.0,680.0,1360.0,1360.0,559642.0,680.0,1360.0,1360.0,555823.0,680.0,1360.0,1360.0,557425.0,680.0,1360.0,1360.0,574725.0,680.0,1360.0,1360.0,574143.0,680.0,1368.0,1368.0,564591.0,684.0,1368.0,1368.0,577162.0,684.0,1368.0,1368.0,584277.0,684.0,1368.0,1368.0,590521.0,703.0,1368.0,1368.0,575860.0,684.0,1368.0,1368.0,581175.0,684.0,1368.0,1368.0,587388.0,684.0,1368.0,1368.0,587897.0,684.0,64,0,6291456.0,65536.0,0.0,0.0,0.0,16384.0,0.0,0.0,0.0,0.0,16384.0,32768.0,48708.0,65586.0,16828.0,75041.0,0.0,0.0,0.0,0.0,64,0,0,1332.0,0.0,1364.0,1661.0,0.0,1364.0,1383.0,0.0,1364.0,1333.0,0.0,1364.0,1393.0,0.0,1364.0,1404.0,0.0,1364.0,1466.0,0.0,1364.0,1364.0,0.0,1364.0,912.0,0.0,1368.0,899.0,0.0,1368.0,932.0,0.0,1368.0,936.0,0.0,1368.0,938.0,0.0,1368.0,928.0,0.0,1368.0,933.0,0.0,1368.0,955.0,0.0,1368.0,1005.0,0.0,1368.0,1228.0,0.0,1368.0,946.0,0.0,1368.0,1195.0,0.0,1368.0,1264.0,0.0,1368.0,1149.0,0.0,1368.0,1161.0,0.0,1368.0,1218.0,0.0,1368.0,999.0,0.0,1360.0,948.0,0.0,1360.0,969.0,0.0,1360.0,909.0,0.0,1360.0,951.0,0.0,1360.0,947.0,0.0,1360.0,1017.0,0.0,1360.0,954.0,0.0,1360.0,908.0,0.0,1360.0,910.0,0.0,1360.0,927.0,0.0,1360.0,923.0,0.0,1360.0,975.0,0.0,1360.0,971.0,0.0,1360.0,924.0,0.0,1360.0,975.0,0.0,1360.0,953.0,0.0,1368.0,1055.0,0.0,1368.0,1020.0,0.0,1368.0,909.0,0.0,1368.0,1093.0,0.0,1368.0,1082.0,0.0,1368.0,1082.0,0.0,1368.0,978.0,0.0,1368.0,1122.0,0.0,1368.0,1054.0,0.0,1368.0,1159.0,0.0,1368.0,1133.0,0.0,1368.0,1144.0,0.0,1368.0,1126.0,0.0,1368.0,1119.0,0.0,1368.0,1068.0,0.0,1368.0,832.0,0.0,1364.0,838.0,0.0,1364.0,827.0,0.0,1364.0,836.0,0.0,1364.0,884.0,0.0,1364.0,867.0,0.0,1364.0,828.0,0.0,1364.0,852.0,0.0,1364.0,1107.0,0.0,1368.0,1109.0,0.0,1368.0,1104.0,0.0,1368.0,1104.0,0.0,1368.0,1154.0,0.0,1368.0,1199.0,0.0,1368.0,1217.0,0.0,1368.0,1057.0,0.0,1368.0,874.0,0.0,1364.0,846.0,0.0,1364.0,834.0,0.0,1364.0,803.0,0.0,1364.0,836.0,0.0,1364.0,832.0,0.0,1364.0,868.0,0.0,1364.0,767.0,0.0,1364.0,932.0,0.0,1368.0,923.0,0.0,1368.0,987.0,0.0,1368.0,949.0,0.0,1368.0,972.0,0.0,1368.0,983.0,0.0,1368.0,1054.0,0.0,1368.0,983.0,0.0,1368.0,1118.0,0.0,1364.0,1316.0,0.0,1364.0,1135.0,0.0,1364.0,1139.0,0.0,1364.0,1484.0,0.0,1364.0,1149.0,0.0,1364.0,1208.0,0.0,1364.0,1186.0,0.0,1364.0,64,0,0.0,49152.0,32768.0,65536.0,32768.0,0.0,0.0,0.0,7644.0,0.0,7818.0,576636.0,1032.0,0.0,0.0,0.0,65698.0,65536.0,131072.0,0.0,0.0,524288.0,228.0,0Line truncated
2,11995,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,16384.0,16384.0,9585105.0,660506.0,278528.0,0.0,0.0,98304.0,214531.0,0.0,0.0,442602.0,118686.0,32768.0,131072.0,131072.0,131072.0,0.0,0.0,524288.0,452397.0,1824.0,64,0,0,1368.0,1368.0,574864.0,684.0,1368.0,1368.0,586520.0,684.0,1368.0,1368.0,584616.0,684.0,1368.0,1368.0,591956.0,684.0,1368.0,1368.0,576329.0,684.0,1368.0,1368.0,581813.0,684.0,1368.0,1368.0,592101.0,684.0,1368.0,1368.0,591848.0,684.0,1364.0,1364.0,554903.0,682.0,1364.0,1364.0,562126.0,682.0,1364.0,1364.0,575283.0,682.0,1364.0,1364.0,573770.0,701.0,1364.0,1364.0,567098.0,682.0,1364.0,1364.0,569136.0,682.0,1364.0,1364.0,583966.0,682.0,1364.0,1364.0,581161.0,682.0,1368.0,1368.0,580341.0,684.0,1368.0,1368.0,589152.0,684.0,1368.0,1368.0,597745.0,684.0,1368.0,1368.0,594956.0,703.0,1368.0,1368.0,587432.0,684.0,1368.0,1368.0,590073.0,684.0,1368.0,1368.0,612468.0,684.0,1368.0,1368.0,609798.0,684.0,1364.0,1364.0,560432.0,682.0,1364.0,1364.0,574108.0,682.0,1364.0,1364.0,569375.0,682.0,1364.0,1364.0,577049.0,682.0,1364.0,1364.0,566477.0,682.0,1364.0,1364.0,568987.0,682.0,1364.0,1364.0,575061.0,682.0,1364.0,1364.0,568556.0,682.0,1364.0,1364.0,567069.0,682.0,1364.0,1364.0,577697.0,682.0,1364.0,1364.0,595343.0,682.0,1364.0,1364.0,592707.0,701.0,1364.0,1364.0,591615.0,682.0,1364.0,1364.0,594056.0,682.0,1364.0,1364.0,608916.0,682.0,1364.0,1364.0,592853.0,682.0,1368.0,1368.0,572327.0,684.0,1368.0,1368.0,584447.0,684.0,1368.0,1368.0,572445.0,684.0,1368.0,1368.0,590184.0,684.0,1368.0,1368.0,571652.0,684.0,1368.0,1368.0,577108.0,684.0,1368.0,1368.0,584640.0,684.0,1368.0,1368.0,580519.0,684.0,1364.0,1364.0,566496.0,682.0,1364.0,1364.0,577142.0,682.0,1364.0,1364.0,579309.0,682.0,1364.0,1364.0,589559.0,682.0,1364.0,1364.0,567750.0,682.0,1364.0,1364.0,576195.0,682.0,1364.0,1364.0,579666.0,682.0,1364.0,1364.0,575634.0,682.0,1368.0,1368.0,555867.0,684.0,1368.0,1368.0,566472.0,684.0,1368.0,1368.0,573386.0,684.0,1368.0,1368.0,570821.0,703.0,1368.0,1368.0,569607.0,684.0,1368.0,1368.0,573181.0,684.0,1368.0,1368.0,584944.0,684.0,1368.0,1368.0,579114.0,684.0,1368.0,1368.0,567494.0,684.0,1368.0,1368.0,582417.0,684.0,1368.0,1368.0,582390.0,684.0,1368.0,1368.0,589098.0,703.0,1368.0,1368.0,574784.0,684.0,1368.0,1368.0,579230.0,684.0,1368.0,1368.0,589300.0,684.0,1368.0,1368.0,590929.0,684.0,1360.0,1360.0,563459.0,680.0,1360.0,1360.0,568642.0,680.0,1360.0,1360.0,577686.0,680.0,1360.0,1360.0,577147.0,680.0,1360.0,1360.0,562911.0,680.0,1360.0,1360.0,566456.0,680.0,1360.0,1360.0,584597.0,680.0,1360.0,1360.0,580592.0,680.0,1368.0,1368.0,568578.0,684.0,1368.0,1368.0,578242.0,684.0,1368.0,1368.0,583106.0,684.0,1368.0,1368.0,584567.0,684.0,1368.0,1368.0,568013.0,684.0,1368.0,1368.0,576998.0,684.0,1368.0,1368.0,589533.0,684.0,1368.0,1368.0,585383.0,684.0,1360.0,1360.0,553986.0,680.0,1360.0,1360.0,564602.0,680.0,1360.0,1360.0,562739.0,680.0,1360.0,1360.0,571731.0,699.0,1360.0,1360.0,554918.0,680.0,1360.0,1360.0,560029.0,680.0,1360.0,1360.0,570798.0,680.0,1360.0,1360.0,563941.0,680.0,64,0,6291456.0,65536.0,0.0,0.0,0.0,16384.0,0.0,0.0,0.0,0.0,16384.0,32768.0,48656.0,65584.0,16880.0,77124.0,0.0,0.0,0.0,0.0,64,0,0,973.0,0.0,1360.0,971.0,0.0,1360.0,959.0,0.0,1360.0,928.0,0.0,1360.0,915.0,0.0,1360.0,908.0,0.0,1360.0,929.0,0.0,1360.0,923.0,0.0,1360.0,1094.0,0.0,1368.0,1253.0,0.0,1368.0,1115.0,0.0,1368.0,1258.0,0.0,1368.0,1306.0,0.0,1368.0,1195.0,0.0,1368.0,1352.0,0.0,1368.0,1218.0,0.0,1368.0,960.0,0.0,1360.0,960.0,0.0,1360.0,975.0,0.0,1360.0,977.0,0.0,1360.0,1023.0,0.0,1360.0,1019.0,0.0,1360.0,972.0,0.0,1360.0,930.0,0.0,1360.0,1128.0,0.0,1368.0,1138.0,0.0,1368.0,1142.0,0.0,1368.0,1022.0,0.0,1368.0,1164.0,0.0,1368.0,959.0,0.0,1368.0,1016.0,0.0,1368.0,940.0,0.0,1368.0,906.0,0.0,1364.0,913.0,0.0,1364.0,833.0,0.0,1364.0,818.0,0.0,1364.0,946.0,0.0,1364.0,941.0,0.0,1364.0,978.0,0.0,1364.0,906.0,0.0,1364.0,1144.0,0.0,1368.0,1155.0,0.0,1368.0,1027.0,0.0,1368.0,1139.0,0.0,1368.0,1071.0,0.0,1368.0,1089.0,0.0,1368.0,1211.0,0.0,1368.0,1110.0,0.0,1368.0,924.0,0.0,1364.0,1005.0,0.0,1364.0,890.0,0.0,1364.0,842.0,0.0,1364.0,840.0,0.0,1364.0,991.0,0.0,1364.0,911.0,0.0,1364.0,873.0,0.0,1364.0,1057.0,0.0,1368.0,1051.0,0.0,1368.0,1037.0,0.0,1368.0,1062.0,0.0,1368.0,1052.0,0.0,1368.0,1055.0,0.0,1368.0,1041.0,0.0,1368.0,1020.0,0.0,1368.0,1306.0,0.0,1364.0,1314.0,0.0,1364.0,1156.0,0.0,1364.0,1136.0,0.0,1364.0,1539.0,0.0,1364.0,1533.0,0.0,1364.0,1317.0,0.0,1364.0,1249.0,0.0,1364.0,1104.0,0.0,1368.0,1113.0,0.0,1368.0,1110.0,0.0,1368.0,1085.0,0.0,1368.0,1084.0,0.0,1368.0,1050.0,0.0,1368.0,1117.0,0.0,1368.0,1044.0,0.0,1368.0,1266.0,0.0,1364.0,1263.0,0.0,1364.0,1210.0,0.0,1364.0,1161.0,0.0,1364.0,1286.0,0.0,1364.0,1262.0,0.0,1364.0,1381.0,0.0,1364.0,1308.0,0.0,1364.0,992.0,0.0,1368.0,963.0,0.0,1368.0,1021.0,0.0,1368.0,1012.0,0.0,1368.0,1073.0,0.0,1368.0,1001.0,0.0,1368.0,1010.0,0.0,1368.0,901.0,0.0,1368.0,64,0,0.0,49152.0,32768.0,65536.0,32768.0,0.0,0.0,0.0,7983.0,0.0,7879.0,587816.0,0.0,0.0,0.0,0.0,65728.0,65536.0,131072.0,0.0,0.0,524Line truncated
+2
Просмотреть файл
@@ -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
vcopy,tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 30 May 2024 02:09:51 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 vcopy tests/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF Thu 30 May 2024 02:09:51 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
+4
Просмотреть файл
@@ -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
1,11995,1,239313,239313,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504048950,162067504056482,0
3,11995,1,239313,239313,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504097624,162067504103513,0
2,11995,1,239313,239313,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",162067504075511,162067504081560,0
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 239313 239313 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504048950 162067504056482 0
3 3 11995 1 239313 239313 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504097624 162067504103513 0
4 2 11995 1 239313 239313 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 162067504075511 162067504081560 0
+4
Просмотреть файл
@@ -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
0,60633,1,1102641,1102641,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676802805,810969676816525,0,449213.0,449213.0,16384.0,65536.0,40694.0,3249356.0
1,60633,1,1102641,1102641,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676837363,810969676849123,0,421528.0,421528.0,16384.0,65536.0,13164.0,1048588.0
2,60633,1,1102641,1102641,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676868522,810969676880402,0,431238.0,431238.0,16384.0,65536.0,13128.0,1048576.0
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 1102641 1102641 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676802805 810969676816525 0 449213.0 449213.0 16384.0 65536.0 40694.0 3249356.0
3 1 60633 1 1102641 1102641 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676837363 810969676849123 0 421528.0 421528.0 16384.0 65536.0 13164.0 1048588.0
4 2 60633 1 1102641 1102641 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676868522 810969676880402 0 431238.0 431238.0 16384.0 65536.0 13128.0 1048576.0
+4
Просмотреть файл
@@ -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
0,60633,1,1102667,1102667,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676802805,810969676816525,0,0.0,0.0,0.0
1,60633,1,1102667,1102667,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676837363,810969676849123,0,0.0,0.0,0.0
2,60633,1,1102667,1102667,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676868522,810969676880402,0,0.0,0.0,0.0
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 1102667 1102667 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676802805 810969676816525 0 0.0 0.0 0.0
3 1 60633 1 1102667 1102667 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676837363 810969676849123 0 0.0 0.0 0.0
4 2 60633 1 1102667 1102667 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676868522 810969676880402 0 0.0 0.0 0.0
+4
Просмотреть файл
@@ -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
0,60633,1,1102685,1102685,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676802805,810969676816525,0,65536.0,3692420.0,295366648.0
1,60633,1,1102685,1102685,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676837363,810969676849123,0,65536.0,3741276.0,299325624.0
2,60633,1,1102685,1102685,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676868522,810969676880402,0,65536.0,3495126.0,279581920.0
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 1102685 1102685 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676802805 810969676816525 0 65536.0 3692420.0 295366648.0
3 1 60633 1 1102685 1102685 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676837363 810969676849123 0 65536.0 3741276.0 299325624.0
4 2 60633 1 1102685 1102685 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676868522 810969676880402 0 65536.0 3495126.0 279581920.0
+4
Просмотреть файл
@@ -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
0,60633,1,1102722,1102722,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676802805,810969676816525,0,32768.0,504073.0,40323912.0
1,60633,1,1102722,1102722,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676837363,810969676849123,0,32768.0,369531.0,29558556.0
2,60633,1,1102722,1102722,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676868522,810969676880402,0,32768.0,402918.0,32234036.0
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 1102722 1102722 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676802805 810969676816525 0 32768.0 504073.0 40323912.0
3 1 60633 1 1102722 1102722 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676837363 810969676849123 0 32768.0 369531.0 29558556.0
4 2 60633 1 1102722 1102722 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676868522 810969676880402 0 32768.0 402918.0 32234036.0
+4
Просмотреть файл
@@ -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
0,60633,1,1102733,1102733,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676802805,810969676816525,0,486977.0,486977.0,287597.0,1947908.0,16384.0,38712781.0,643368.0,0.0,155189876.0
1,60633,1,1102733,1102733,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676837363,810969676849123,0,453307.0,453307.0,266894.0,1813228.0,16384.0,34185086.0,537047.0,0.0,137095332.0
2,60633,1,1102733,1102733,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676868522,810969676880402,0,417367.0,417367.0,227048.0,1669468.0,16384.0,35398046.0,555090.0,0.0,141949588.0
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 1102733 1102733 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676802805 810969676816525 0 486977.0 486977.0 287597.0 1947908.0 16384.0 38712781.0 643368.0 0.0 155189876.0
3 1 60633 1 1102733 1102733 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676837363 810969676849123 0 453307.0 453307.0 266894.0 1813228.0 16384.0 34185086.0 537047.0 0.0 137095332.0
4 2 60633 1 1102733 1102733 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676868522 810969676880402 0 417367.0 417367.0 227048.0 1669468.0 16384.0 35398046.0 555090.0 0.0 141949588.0
+161
Просмотреть файл
@@ -0,0 +1,161 @@
Omniperf version: 2.0.0
Profiler choice: rocprofv2
Path: /home/colramos/omniperf/tests/workloads/vcopy/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/vcopy/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
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH_LEVEL
[profiling] Current input file: tests/workloads/vcopy/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
[profiling] Current input file: tests/workloads/vcopy/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/vcopy/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/vcopy/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
|-> [/opt/rocm/bin/rocprofv2] - SQ_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
[profiling] Current input file: tests/workloads/vcopy/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
[profiling] Current input file: tests/workloads/vcopy/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
[profiling] Current input file: tests/workloads/vcopy/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
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_REQ
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_16
|-> [/opt/rocm/bin/rocprofv2] - SQC_ICACHE_REQ
[profiling] Current input file: tests/workloads/vcopy/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
[profiling] Current input file: tests/workloads/vcopy/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
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
[profiling] Current input file: tests/workloads/vcopy/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]
|-> [/opt/rocm/bin/rocprofv2] - TCC_ATOMIC[1]
[profiling] Current input file: tests/workloads/vcopy/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]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[1]
[profiling] Current input file: tests/workloads/vcopy/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]
[profiling] Current input file: tests/workloads/vcopy/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]
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[1]
[profiling] Current input file: tests/workloads/vcopy/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]
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[1]
[profiling] Current input file: tests/workloads/vcopy/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
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F32
[profiling] Current input file: tests/workloads/vcopy/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
[profiling] Current input file: tests/workloads/vcopy/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
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAIT_INST_ANY
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_ANY
[profiling] Current input file: tests/workloads/vcopy/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
|-> [/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
[profiling] Current input file: tests/workloads/vcopy/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
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_BANK_CONFLICT
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_ADDR_CONFLICT
[profiling] Current input file: tests/workloads/vcopy/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
[profiling] Current input file: tests/workloads/vcopy/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
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_F16
[profiling] Current input file: tests/workloads/vcopy/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
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_BF16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F32
[profiling] Current input file: tests/workloads/vcopy/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
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
[roofline] Roofline temporarily disabled in MI300
+5
Просмотреть файл
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
+5
Просмотреть файл
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
+5
Просмотреть файл
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
+5
Просмотреть файл
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
gpu:
range:
kernel:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -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:
+5
Просмотреть файл
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel:
+4
Просмотреть файл
@@ -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)",0,2630734.0,0.0,0.0,65536.0,60576.0,160.0,4800.0,32768.0,64,0,0,0.0,512.0,50979.0,0.0,0.0,512.0,50979.0,0.0,0.0,512.0,50979.0,0.0,0.0,512.0,50979.0,0.0,0.0,512.0,50979.0,0.0,0.0,512.0,50979.0,0.0,0.0,512.0,50979.0,0.0,0.0,512.0,50979.0,0.0,0.0,512.0,50979.0,0.0,0.0,512.0,50979.0,0.0,0.0,512.0,50979.0,0.0,0.0,512.0,50979.0,0.0,0.0,512.0,50979.0,0.0,0.0,512.0,50979.0,0.0,0.0,512.0,50979.0,0.0,0.0,512.0,50979.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,47060.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,60880.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,70496.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,92468.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,102852.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,104775.0,0.0,0.0,512.0,113099.0,0.0,0.0,512.0,113099.0,0.0,0.0,512.0,113099.0,0.0,0.0,512.0,113099.0,0.0,0.0,512.0,113099.0,0.0,0.0,512.0,113099.0,0.0,0.0,512.0,113099.0,0.0,0.0,512.0,113099.0,0.0,0.0,512.0,113099.0,0.0,0.0,512.0,113099.0,0.0,0.0,512.0,113099.0,0.0,0.0,512.0,113099.0,0.0,0.0,512.0,113099.0,0.0,0.0,512.0,113099.0,0.0,0.0,512.0,113099.0,0.0,0.0,512.0,113099.0,0.0,64,0,0.0,0.0,1048576.0,0.0,0.0,0.0,0.0,0.0,0.0,32768.0,0.0,16384.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,64,0,131072.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,16384.0,0.0,0.0,115127013.0,71374843.0,232408.0,0.0,0.0,65536.0,131072.0,64,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,119405.0,31411.0,2401586.0,696.0,0.0,446729.0,0.0,0.0,66160.0,131311.0,197471.0,0.0,2097152.0,1048576.0,1048576.0,2097152.0,0.0,16384.0,64,0,0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1049.0,537.0,1561.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,593.0,1617.0,1616.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,593.0,1617.0,1616.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1049.0,537.0,1561.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1047.0,535.0,1559.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,593.0,1617.0,1616.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,593.0,1617.0,1616.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536Line truncated
1,60633,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,2808832.0,0.0,0.0,65536.0,60576.0,160.0,4800.0,32768.0,64,0,0,0.0,512.0,44522.0,0.0,0.0,512.0,44522.0,0.0,0.0,512.0,44522.0,0.0,0.0,512.0,44522.0,0.0,0.0,512.0,44522.0,0.0,0.0,512.0,44522.0,0.0,0.0,512.0,44522.0,0.0,0.0,512.0,44522.0,0.0,0.0,512.0,44522.0,0.0,0.0,512.0,44522.0,0.0,0.0,512.0,44522.0,0.0,0.0,512.0,44522.0,0.0,0.0,512.0,44522.0,0.0,0.0,512.0,44522.0,0.0,0.0,512.0,44522.0,0.0,0.0,512.0,44522.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,42816.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,61719.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,72756.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,86819.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,97264.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,95560.0,0.0,0.0,512.0,105665.0,0.0,0.0,512.0,105665.0,0.0,0.0,512.0,105665.0,0.0,0.0,512.0,105665.0,0.0,0.0,512.0,105665.0,0.0,0.0,512.0,105665.0,0.0,0.0,512.0,105665.0,0.0,0.0,512.0,105665.0,0.0,0.0,512.0,105665.0,0.0,0.0,512.0,105665.0,0.0,0.0,512.0,105665.0,0.0,0.0,512.0,105665.0,0.0,0.0,512.0,105665.0,0.0,0.0,512.0,105665.0,0.0,0.0,512.0,105665.0,0.0,0.0,512.0,105665.0,0.0,64,0,0.0,0.0,1048576.0,0.0,0.0,0.0,0.0,0.0,0.0,32768.0,0.0,16384.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,64,0,131072.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,16384.0,0.0,0.0,63402270.0,91577869.0,331064.0,0.0,0.0,65536.0,131072.0,64,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,50791.0,27989.0,2003598.0,9776.0,0.0,304771.0,0.0,0.0,65536.0,131325.0,196861.0,0.0,2097152.0,1048576.0,1048576.0,2097152.0,0.0,16384.0,64,0,0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1028.0,516.0,1540.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1048.0,536.0,1560.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1049.0,537.0,1561.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1048.0,536.0,1560.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1026.0,514.0,1538.0,1536.0,102Line truncated
2,60633,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,2769571.0,0.0,0.0,65536.0,60576.0,160.0,4800.0,32768.0,64,0,0,0.0,512.0,43005.0,0.0,0.0,512.0,43005.0,0.0,0.0,512.0,43005.0,0.0,0.0,512.0,43005.0,0.0,0.0,512.0,43005.0,0.0,0.0,512.0,43005.0,0.0,0.0,512.0,43005.0,0.0,0.0,512.0,43005.0,0.0,0.0,512.0,43005.0,0.0,0.0,512.0,43005.0,0.0,0.0,512.0,43005.0,0.0,0.0,512.0,43005.0,0.0,0.0,512.0,43005.0,0.0,0.0,512.0,43005.0,0.0,0.0,512.0,43005.0,0.0,0.0,512.0,43005.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,35886.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,54210.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,64399.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,79229.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,89913.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,91702.0,0.0,0.0,512.0,98763.0,0.0,0.0,512.0,98763.0,0.0,0.0,512.0,98763.0,0.0,0.0,512.0,98763.0,0.0,0.0,512.0,98763.0,0.0,0.0,512.0,98763.0,0.0,0.0,512.0,98763.0,0.0,0.0,512.0,98763.0,0.0,0.0,512.0,98763.0,0.0,0.0,512.0,98763.0,0.0,0.0,512.0,98763.0,0.0,0.0,512.0,98763.0,0.0,0.0,512.0,98763.0,0.0,0.0,512.0,98763.0,0.0,0.0,512.0,98763.0,0.0,0.0,512.0,98763.0,0.0,64,0,0.0,0.0,1048576.0,0.0,0.0,0.0,0.0,0.0,0.0,32768.0,0.0,16384.0,0.0,0.0,24.0,0.0,0.0,0.0,0.0,0.0,64,0,131072.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,16384.0,0.0,0.0,41118152.0,51993106.0,123499.0,0.0,0.0,65536.0,131072.0,64,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,45832.0,27319.0,2007684.0,9755.0,0.0,291971.0,0.0,0.0,65536.0,131323.0,196859.0,0.0,2097152.0,1048576.0,1048576.0,2097152.0,0.0,16384.0,64,0,0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1051.0,539.0,1563.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1048.0,536.0,1560.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1049.0,537.0,1561.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.Line truncated
+2
Просмотреть файл
@@ -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
vcopy,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 30 May 2024 02:19:39 PM (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 vcopy ./tests/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF Thu 30 May 2024 02:19:39 PM (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
+4
Просмотреть файл
@@ -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
1,60633,1,1103031,1103031,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676802805,810969676816525,0
2,60633,1,1103031,1103031,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676837363,810969676849123,0
3,60633,1,1103031,1103031,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",810969676868522,810969676880402,0
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 1103031 1103031 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676802805 810969676816525 0
3 2 60633 1 1103031 1103031 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676837363 810969676849123 0
4 3 60633 1 1103031 1103031 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 810969676868522 810969676880402 0