Add 'projects/rocprofiler-compute/' from commit 'd2cec001161fc49761bd71a498474a447b1d6975'

git-subtree-dir: projects/rocprofiler-compute
git-subtree-mainline: 8a4d7262f8
git-subtree-split: d2cec00116
This commit is contained in:
systems-assistant[bot]
2025-07-17 18:13:42 +00:00
4484 changed files with 289584 additions and 0 deletions
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1233276,1233276,1048576,256,0,0,8,8,16,64,0x0,0x7efe2639cec0,47520,47520,16384,65536,13262,1711364,1410088190828131,1410100033478037,1410100033502197,1410088198583377
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1233276,1233276,1048576,256,0,0,8,8,16,64,0x0,0x7efe2639cec0,41636,41636,16384,65536,8455,1048580,1410088198612933,1410100033593877,1410100033612597,1410088198932796
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1233276,1233276,1048576,256,0,0,8,8,16,64,0x0,0x7efe2639cec0,41636,41636,16384,65536,8143,1048580,1410088198965097,1410100033638517,1410100033657077,1410088199142181
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 1233276 1233276 1048576 256 0 0 8 8 16 64 0x0 0x7efe2639cec0 47520 47520 16384 65536 13262 1711364 1410088190828131 1410100033478037 1410100033502197 1410088198583377
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 1233276 1233276 1048576 256 0 0 8 8 16 64 0x0 0x7efe2639cec0 41636 41636 16384 65536 8455 1048580 1410088198612933 1410100033593877 1410100033612597 1410088198932796
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 1233276 1233276 1048576 256 0 0 8 8 16 64 0x0 0x7efe2639cec0 41636 41636 16384 65536 8143 1048580 1410088198965097 1410100033638517 1410100033657077 1410088199142181
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1233465,1233465,1048576,256,0,0,8,8,16,64,0x0,0x7fcfea990ec0,0,0,0,1410088676805908,1410100033478037,1410100033502197,1410088684337091
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1233465,1233465,1048576,256,0,0,8,8,16,64,0x0,0x7fcfea990ec0,0,0,0,1410088684356949,1410100033593877,1410100033612597,1410088684680419
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1233465,1233465,1048576,256,0,0,8,8,16,64,0x0,0x7fcfea990ec0,0,0,0,1410088684708933,1410100033638517,1410100033657077,1410088684889954
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 1233465 1233465 1048576 256 0 0 8 8 16 64 0x0 0x7fcfea990ec0 0 0 0 1410088676805908 1410100033478037 1410100033502197 1410088684337091
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 1233465 1233465 1048576 256 0 0 8 8 16 64 0x0 0x7fcfea990ec0 0 0 0 1410088684356949 1410100033593877 1410100033612597 1410088684680419
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 1233465 1233465 1048576 256 0 0 8 8 16 64 0x0 0x7fcfea990ec0 0 0 0 1410088684708933 1410100033638517 1410100033657077 1410088684889954
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1233652,1233652,1048576,256,0,0,8,8,16,64,0x0,0x7f35fba6cec0,65536,215772,27659752,1410089161300999,1410100033478037,1410100033502197,1410089168886174
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1233652,1233652,1048576,256,0,0,8,8,16,64,0x0,0x7f35fba6cec0,65536,218704,27996088,1410089168906202,1410100033593877,1410100033612597,1410089169214454
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1233652,1233652,1048576,256,0,0,8,8,16,64,0x0,0x7f35fba6cec0,65536,216244,27719712,1410089169242256,1410100033638517,1410100033657077,1410089169412888
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 1233652 1233652 1048576 256 0 0 8 8 16 64 0x0 0x7f35fba6cec0 65536 215772 27659752 1410089161300999 1410100033478037 1410100033502197 1410089168886174
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 1233652 1233652 1048576 256 0 0 8 8 16 64 0x0 0x7f35fba6cec0 65536 218704 27996088 1410089168906202 1410100033593877 1410100033612597 1410089169214454
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 1233652 1233652 1048576 256 0 0 8 8 16 64 0x0 0x7f35fba6cec0 65536 216244 27719712 1410089169242256 1410100033638517 1410100033657077 1410089169412888
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1233840,1233840,1048576,256,0,0,8,8,16,64,0x0,0x7fc449ed8ec0,32768,655957,83965736,1410089647501356,1410100033478037,1410100033502197,1410089655200997
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1233840,1233840,1048576,256,0,0,8,8,16,64,0x0,0x7fc449ed8ec0,32768,665445,85174904,1410089655222728,1410100033593877,1410100033612597,1410089655499350
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1233840,1233840,1048576,256,0,0,8,8,16,64,0x0,0x7fc449ed8ec0,32768,657926,84218544,1410089655527864,1410100033638517,1410100033657077,1410089655705819
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 1233840 1233840 1048576 256 0 0 8 8 16 64 0x0 0x7fc449ed8ec0 32768 655957 83965736 1410089647501356 1410100033478037 1410100033502197 1410089655200997
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 1233840 1233840 1048576 256 0 0 8 8 16 64 0x0 0x7fc449ed8ec0 32768 665445 85174904 1410089655222728 1410100033593877 1410100033612597 1410089655499350
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 1233840 1233840 1048576 256 0 0 8 8 16 64 0x0 0x7fc449ed8ec0 32768 657926 84218544 1410089655527864 1410100033638517 1410100033657077 1410089655705819
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,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,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1234024,1234024,1048576,256,0,0,8,8,16,64,0x0,0x7f90cce04ec0,48770,48770,18412,390168,16384,24851481,236800,0,99947332,1410090131932426,1410100033478037,1410100033502197,1410090139651645
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1234024,1234024,1048576,256,0,0,8,8,16,64,0x0,0x7f90cce04ec0,42136,42136,13157,337096,16384,24727121,229507,0,99439364,1410090139682352,1410100033593877,1410100033612597,1410090139991095
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1234024,1234024,1048576,256,0,0,8,8,16,64,0x0,0x7f90cce04ec0,42472,42472,13191,339784,16384,23653826,229247,0,95156176,1410090140029487,1410100033638517,1410100033657077,1410090140209627
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj 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 DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 1234024 1234024 1048576 256 0 0 8 8 16 64 0x0 0x7f90cce04ec0 48770 48770 18412 390168 16384 24851481 236800 0 99947332 1410090131932426 1410100033478037 1410100033502197 1410090139651645
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 1234024 1234024 1048576 256 0 0 8 8 16 64 0x0 0x7f90cce04ec0 42136 42136 13157 337096 16384 24727121 229507 0 99439364 1410090139682352 1410100033593877 1410100033612597 1410090139991095
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 1234024 1234024 1048576 256 0 0 8 8 16 64 0x0 0x7f90cce04ec0 42472 42472 13191 339784 16384 23653826 229247 0 95156176 1410090140029487 1410100033638517 1410100033657077 1410090140209627
@@ -0,0 +1,702 @@
Omniperf version: 2.0.0-RC1
Profiler choice: rocprofv1
Path: /home1/josantos/omniperf/tests/workloads/kernel_substr/MI100
Target: MI100
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
Kernel Selection: ['vecCopy']
Dispatch Selection: None
IP Blocks: All
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Collecting Performance Counters
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/SQ_IFETCH_LEVEL.txt
|-> [rocprof] RPL: on '240321_155234' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/SQ_IFETCH_LEVEL.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155234_1233116'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155234_1233116/input0_results_240321_155234'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155234_1233116/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 6 metrics
|-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155234_1233116/input0_results_240321_155234
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/SQ_IFETCH_LEVEL.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/SQ_INST_LEVEL_LDS.txt
|-> [rocprof] RPL: on '240321_155234' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/SQ_INST_LEVEL_LDS.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155234_1233305'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155234_1233305/input0_results_240321_155234'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155234_1233305/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 3 metrics
|-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155234_1233305/input0_results_240321_155234
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_LDS.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt
|-> [rocprof] RPL: on '240321_155235' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155235_1233492'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155235_1233492/input0_results_240321_155235'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155235_1233492/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 3 metrics
|-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155235_1233492/input0_results_240321_155235
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_SMEM.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt
|-> [rocprof] RPL: on '240321_155235' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155235_1233680'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155235_1233680/input0_results_240321_155235'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155235_1233680/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 3 metrics
|-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155235_1233680/input0_results_240321_155235
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_VMEM.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/SQ_LEVEL_WAVES.txt
|-> [rocprof] RPL: on '240321_155236' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/SQ_LEVEL_WAVES.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155236_1233864'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155236_1233864/input0_results_240321_155236'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155236_1233864/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 9 metrics
|-> [rocprof] 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
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155236_1233864/input0_results_240321_155236
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/SQ_LEVEL_WAVES.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_0.txt
|-> [rocprof] RPL: on '240321_155236' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_0.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155236_1234050'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155236_1234050/input0_results_240321_155236'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155236_1234050/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 28 metrics
|-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, 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
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155236_1234050/input0_results_240321_155236
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_0.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_1.txt
|-> [rocprof] RPL: on '240321_155237' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_1.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155237_1234236'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155237_1234236/input0_results_240321_155237'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155237_1234236/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 27 metrics
|-> [rocprof] 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, 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_COALESCABLE_WAVEFRONT_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
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155237_1234236/input0_results_240321_155237
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_1.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_10.txt
|-> [rocprof] RPL: on '240321_155237' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_10.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155237_1234425'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155237_1234425/input0_results_240321_155237'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155237_1234425/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 1 metrics
|-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155237_1234425/input0_results_240321_155237
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_10.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_11.txt
|-> [rocprof] RPL: on '240321_155238' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_11.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155238_1234614'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155238_1234614/input0_results_240321_155238'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155238_1234614/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 128 metrics
|-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31]
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155238_1234614/input0_results_240321_155238
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_11.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_12.txt
|-> [rocprof] RPL: on '240321_155238' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_12.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155238_1234809'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155238_1234809/input0_results_240321_155238'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155238_1234809/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 128 metrics
|-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31]
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155238_1234809/input0_results_240321_155238
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_12.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_13.txt
|-> [rocprof] RPL: on '240321_155239' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_13.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155239_1234998'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155239_1234998/input0_results_240321_155239'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155239_1234998/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 128 metrics
|-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31]
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155239_1234998/input0_results_240321_155239
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_13.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_14.txt
|-> [rocprof] RPL: on '240321_155240' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_14.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155240_1235184'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155240_1235184/input0_results_240321_155240'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155240_1235184/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 128 metrics
|-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31]
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155240_1235184/input0_results_240321_155240
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_14.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_15.txt
|-> [rocprof] RPL: on '240321_155240' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_15.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155240_1235373'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155240_1235373/input0_results_240321_155240'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155240_1235373/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 128 metrics
|-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31]
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155240_1235373/input0_results_240321_155240
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_15.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_16.txt
|-> [rocprof] RPL: on '240321_155241' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_16.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155241_1235565'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155241_1235565/input0_results_240321_155241'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155241_1235565/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 96 metrics
|-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31]
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155241_1235565/input0_results_240321_155241
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_16.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_2.txt
|-> [rocprof] RPL: on '240321_155242' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_2.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155242_1235753'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155242_1235753/input0_results_240321_155242'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155242_1235753/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 26 metrics
|-> [rocprof] 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, 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
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155242_1235753/input0_results_240321_155242
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_2.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_3.txt
|-> [rocprof] RPL: on '240321_155242' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_3.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155242_1235942'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155242_1235942/input0_results_240321_155242'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155242_1235942/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 23 metrics
|-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, 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, 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
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155242_1235942/input0_results_240321_155242
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_3.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_4.txt
|-> [rocprof] RPL: on '240321_155243' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_4.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155243_1236130'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155243_1236130/input0_results_240321_155243'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155243_1236130/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 22 metrics
|-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, 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_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155243_1236130/input0_results_240321_155243
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_4.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_5.txt
|-> [rocprof] RPL: on '240321_155243' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_5.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155243_1236315'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155243_1236315/input0_results_240321_155243'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155243_1236315/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 21 metrics
|-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_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_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155243_1236315/input0_results_240321_155243
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_5.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_6.txt
|-> [rocprof] RPL: on '240321_155244' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_6.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155244_1236503'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155244_1236503/input0_results_240321_155244'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155244_1236503/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 20 metrics
|-> [rocprof] 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, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_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_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155244_1236503/input0_results_240321_155244
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_6.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_7.txt
|-> [rocprof] RPL: on '240321_155244' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_7.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155244_1236690'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155244_1236690/input0_results_240321_155244'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155244_1236690/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 20 metrics
|-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155244_1236690/input0_results_240321_155244
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_7.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_8.txt
|-> [rocprof] RPL: on '240321_155245' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_8.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155245_1236877'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155245_1236877/input0_results_240321_155245'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155245_1236877/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 17 metrics
|-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155245_1236877/input0_results_240321_155245
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_8.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_9.txt
|-> [rocprof] RPL: on '240321_155245' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_9.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155245_1237066'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155245_1237066/input0_results_240321_155245'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155245_1237066/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 8 metrics
|-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155245_1237066/input0_results_240321_155245
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_9.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/timestamps.txt
|-> [rocprof] RPL: on '240321_155246' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/timestamps.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155246_1237253'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155246_1237253/input0_results_240321_155246'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155246_1237253/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 0 metrics
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155246_1237253/input0_results_240321_155246
|-> [rocprof] File 'tests/workloads/kernel_substr/MI100/timestamps.csv' is generating
|-> [rocprof]
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -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: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ 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: vecCopy
@@ -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 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_COALESCABLE_WAVEFRONT_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: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_EA_ATOMIC_LEVEL_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31]
gpu:
range:
kernel: vecCopy
@@ -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 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: vecCopy
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS_SMEM 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 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: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS SQ_WAIT_ANY 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_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_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_EA_WRREQ_STALL_sum TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: 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 SQ_THREAD_CYCLES_VALU SQ_IFETCH TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_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_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2
1 Dispatch_ID Kernel_Name GPU_ID
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2
File diff suppressed because one or more lines are too long
@@ -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,num_hbm_channels
path,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:52:12 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1,32
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 num_hbm_channels
2 path ./tests/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF Thu 21 Mar 2024 03:52:12 PM (CDT) 2 t007-001.hpcfund AMD EPYC 7V13 64-Core Processor American Megatrends Inc.0602 Rocky Linux 9.1 (Blue Onyx) 5.14.0-162.18.1.el9_1.x86_64 527651008 6.0.2-115 113-D3431401-100 NA NA MI100 gfx908 16 8192 120 4 8 64 1024 40 1502 1200 1502 1200 32 32 64 4 1228.8 1 32
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1237413,1237413,1048576,256,0,0,8,8,16,64,0x0,0x7f91afc6cec0,1410100033451844,1410100033478037,1410100033502197,1410100033513600
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1237413,1237413,1048576,256,0,0,8,8,16,64,0x0,0x7f91afc6cec0,1410100033514522,1410100033593877,1410100033612597,1410100033617336
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1237413,1237413,1048576,256,0,0,8,8,16,64,0x0,0x7f91afc6cec0,1410100033624710,1410100033638517,1410100033657077,1410100033658564
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 1237413 1237413 1048576 256 0 0 8 8 16 64 0x0 0x7f91afc6cec0 1410100033451844 1410100033478037 1410100033502197 1410100033513600
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 1237413 1237413 1048576 256 0 0 8 8 16 64 0x0 0x7f91afc6cec0 1410100033514522 1410100033593877 1410100033612597 1410100033617336
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 1237413 1237413 1048576 256 0 0 8 8 16 64 0x0 0x7f91afc6cec0 1410100033624710 1410100033638517 1410100033657077 1410100033658564
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4114786,4114786,1048576,256,0,0,8,0,16,64,0x0,0x7f7efac7cec0,27808,27808,16384,65536,13399,1542552,1411747993352852,1411760919537410,1411760919557090,1411748009210180
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4114786,4114786,1048576,256,0,0,8,0,16,64,0x0,0x7f7efac7cec0,42345,42345,16384,65536,9466,1048672,1411748009231631,1411760919576130,1411760919591970,1411748009550113
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4114786,4114786,1048576,256,0,0,8,0,16,64,0x0,0x7f7efac7cec0,41809,41809,16384,65536,9261,1048648,1411748009579198,1411760919648450,1411760919664930,1411748009739572
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 4114786 4114786 1048576 256 0 0 8 0 16 64 0x0 0x7f7efac7cec0 27808 27808 16384 65536 13399 1542552 1411747993352852 1411760919537410 1411760919557090 1411748009210180
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 4114786 4114786 1048576 256 0 0 8 0 16 64 0x0 0x7f7efac7cec0 42345 42345 16384 65536 9466 1048672 1411748009231631 1411760919576130 1411760919591970 1411748009550113
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 4114786 4114786 1048576 256 0 0 8 0 16 64 0x0 0x7f7efac7cec0 41809 41809 16384 65536 9261 1048648 1411748009579198 1411760919648450 1411760919664930 1411748009739572
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4114972,4114972,1048576,256,0,0,8,0,16,64,0x0,0x7fe2c102cec0,0,0,0,1411748492261360,1411760919537410,1411760919557090,1411748508646486
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4114972,4114972,1048576,256,0,0,8,0,16,64,0x0,0x7fe2c102cec0,0,0,0,1411748508665692,1411760919576130,1411760919591970,1411748508945812
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4114972,4114972,1048576,256,0,0,8,0,16,64,0x0,0x7fe2c102cec0,0,0,0,1411748508971250,1411760919648450,1411760919664930,1411748509120252
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 4114972 4114972 1048576 256 0 0 8 0 16 64 0x0 0x7fe2c102cec0 0 0 0 1411748492261360 1411760919537410 1411760919557090 1411748508646486
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 4114972 4114972 1048576 256 0 0 8 0 16 64 0x0 0x7fe2c102cec0 0 0 0 1411748508665692 1411760919576130 1411760919591970 1411748508945812
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 4114972 4114972 1048576 256 0 0 8 0 16 64 0x0 0x7fe2c102cec0 0 0 0 1411748508971250 1411760919648450 1411760919664930 1411748509120252
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4115172,4115172,1048576,256,0,0,8,0,16,64,0x0,0x7f98c6ce0ec0,65536,191466,21343568,1411748975548556,1411760919537410,1411760919557090,1411748991614648
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4115172,4115172,1048576,256,0,0,8,0,16,64,0x0,0x7f98c6ce0ec0,65536,266474,29803832,1411748991632112,1411760919576130,1411760919591970,1411748991928322
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4115172,4115172,1048576,256,0,0,8,0,16,64,0x0,0x7f98c6ce0ec0,65536,269860,30194104,1411748991954391,1411760919648450,1411760919664930,1411748992109995
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 4115172 4115172 1048576 256 0 0 8 0 16 64 0x0 0x7f98c6ce0ec0 65536 191466 21343568 1411748975548556 1411760919537410 1411760919557090 1411748991614648
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 4115172 4115172 1048576 256 0 0 8 0 16 64 0x0 0x7f98c6ce0ec0 65536 266474 29803832 1411748991632112 1411760919576130 1411760919591970 1411748991928322
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 4115172 4115172 1048576 256 0 0 8 0 16 64 0x0 0x7f98c6ce0ec0 65536 269860 30194104 1411748991954391 1411760919648450 1411760919664930 1411748992109995
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4115370,4115370,1048576,256,0,0,8,0,16,64,0x0,0x7f400bee0ec0,32768,293469,32855948,1411749461257651,1411760919537410,1411760919557090,1411749477699425
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4115370,4115370,1048576,256,0,0,8,0,16,64,0x0,0x7f400bee0ec0,32768,562268,62950004,1411749477717519,1411760919576130,1411760919591970,1411749478030080
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4115370,4115370,1048576,256,0,0,8,0,16,64,0x0,0x7f400bee0ec0,32768,583160,65318136,1411749478056540,1411760919648450,1411760919664930,1411749478223946
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 4115370 4115370 1048576 256 0 0 8 0 16 64 0x0 0x7f400bee0ec0 32768 293469 32855948 1411749461257651 1411760919537410 1411760919557090 1411749477699425
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 4115370 4115370 1048576 256 0 0 8 0 16 64 0x0 0x7f400bee0ec0 32768 562268 62950004 1411749477717519 1411760919576130 1411760919591970 1411749478030080
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 4115370 4115370 1048576 256 0 0 8 0 16 64 0x0 0x7f400bee0ec0 32768 583160 65318136 1411749478056540 1411760919648450 1411760919664930 1411749478223946
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,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,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4115572,4115572,1048576,256,0,0,8,0,16,64,0x0,0x7f08ef3d8ec0,28866,28866,11064,230936,16384,11619166,137356,0,46984496,1411749950842366,1411760919537410,1411760919557090,1411749966997337
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4115572,4115572,1048576,256,0,0,8,0,16,64,0x0,0x7f08ef3d8ec0,41555,41555,13750,332448,16384,19544648,223581,0,78671448,1411749967023126,1411760919576130,1411760919591970,1411749967377907
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4115572,4115572,1048576,256,0,0,8,0,16,64,0x0,0x7f08ef3d8ec0,42294,42294,14213,338360,16384,19749746,227566,0,79473776,1411749967412673,1411760919648450,1411760919664930,1411749967581332
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj 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 DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 4115572 4115572 1048576 256 0 0 8 0 16 64 0x0 0x7f08ef3d8ec0 28866 28866 11064 230936 16384 11619166 137356 0 46984496 1411749950842366 1411760919537410 1411760919557090 1411749966997337
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 4115572 4115572 1048576 256 0 0 8 0 16 64 0x0 0x7f08ef3d8ec0 41555 41555 13750 332448 16384 19544648 223581 0 78671448 1411749967023126 1411760919576130 1411760919591970 1411749967377907
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 4115572 4115572 1048576 256 0 0 8 0 16 64 0x0 0x7f08ef3d8ec0 42294 42294 14213 338360 16384 19749746 227566 0 79473776 1411749967412673 1411760919648450 1411760919664930 1411749967581332
@@ -0,0 +1,764 @@
Omniperf version: 2.0.0-RC1
Profiler choice: rocprofv1
Path: /home1/josantos/omniperf/tests/workloads/kernel_substr/MI200
Target: MI200
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
Kernel Selection: ['vecCopy']
Dispatch Selection: None
IP Blocks: All
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Collecting Performance Counters
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/SQ_IFETCH_LEVEL.txt
|-> [rocprof] RPL: on '240321_162015' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/SQ_IFETCH_LEVEL.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162015_4114626'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162015_4114626/input0_results_240321_162015'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162015_4114626/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 6 metrics
|-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162015_4114626/input0_results_240321_162015
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/SQ_IFETCH_LEVEL.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_LDS.txt
|-> [rocprof] RPL: on '240321_162016' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_LDS.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162016_4114812'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162016_4114812/input0_results_240321_162016'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162016_4114812/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 3 metrics
|-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162016_4114812/input0_results_240321_162016
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_LDS.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt
|-> [rocprof] RPL: on '240321_162016' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162016_4115012'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162016_4115012/input0_results_240321_162016'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162016_4115012/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 3 metrics
|-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162016_4115012/input0_results_240321_162016
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_SMEM.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt
|-> [rocprof] RPL: on '240321_162017' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162017_4115210'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162017_4115210/input0_results_240321_162017'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162017_4115210/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 3 metrics
|-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162017_4115210/input0_results_240321_162017
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_VMEM.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/SQ_LEVEL_WAVES.txt
|-> [rocprof] RPL: on '240321_162017' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/SQ_LEVEL_WAVES.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162017_4115412'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162017_4115412/input0_results_240321_162017'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162017_4115412/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 9 metrics
|-> [rocprof] 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
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162017_4115412/input0_results_240321_162017
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/SQ_LEVEL_WAVES.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_0.txt
|-> [rocprof] RPL: on '240321_162018' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_0.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162018_4115614'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162018_4115614/input0_results_240321_162018'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162018_4115614/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 28 metrics
|-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, 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
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162018_4115614/input0_results_240321_162018
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_0.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_1.txt
|-> [rocprof] RPL: on '240321_162018' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_1.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162018_4115800'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162018_4115800/input0_results_240321_162018'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162018_4115800/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 27 metrics
|-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, 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
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162018_4115800/input0_results_240321_162018
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_1.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_10.txt
|-> [rocprof] RPL: on '240321_162019' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_10.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162019_4116004'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162019_4116004/input0_results_240321_162019'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162019_4116004/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 8 metrics
|-> [rocprof] SQC_TC_DATA_WRITE_REQ, 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
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162019_4116004/input0_results_240321_162019
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_10.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_11.txt
|-> [rocprof] RPL: on '240321_162019' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_11.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162019_4116192'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162019_4116192/input0_results_240321_162019'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162019_4116192/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 8 metrics
|-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, 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
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162019_4116192/input0_results_240321_162019
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_11.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_12.txt
|-> [rocprof] RPL: on '240321_162020' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_12.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162020_4116376'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162020_4116376/input0_results_240321_162020'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162020_4116376/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 3 metrics
|-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162020_4116376/input0_results_240321_162020
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_12.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_13.txt
|-> [rocprof] RPL: on '240321_162020' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_13.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162020_4116562'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162020_4116562/input0_results_240321_162020'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162020_4116562/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 128 metrics
|-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31]
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162020_4116562/input0_results_240321_162020
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_13.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_14.txt
|-> [rocprof] RPL: on '240321_162021' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_14.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162021_4116749'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162021_4116749/input0_results_240321_162021'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162021_4116749/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 128 metrics
|-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31]
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162021_4116749/input0_results_240321_162021
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_14.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_15.txt
|-> [rocprof] RPL: on '240321_162022' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_15.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162022_4116935'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162022_4116935/input0_results_240321_162022'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162022_4116935/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 128 metrics
|-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31]
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162022_4116935/input0_results_240321_162022
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_15.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_16.txt
|-> [rocprof] RPL: on '240321_162022' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_16.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162022_4117123'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162022_4117123/input0_results_240321_162022'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162022_4117123/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 128 metrics
|-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31]
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162022_4117123/input0_results_240321_162022
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_16.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_17.txt
|-> [rocprof] RPL: on '240321_162023' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_17.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162023_4117308'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162023_4117308/input0_results_240321_162023'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162023_4117308/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 128 metrics
|-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31]
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162023_4117308/input0_results_240321_162023
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_17.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_18.txt
|-> [rocprof] RPL: on '240321_162024' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_18.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162024_4117498'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162024_4117498/input0_results_240321_162024'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162024_4117498/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 96 metrics
|-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31]
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162024_4117498/input0_results_240321_162024
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_18.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_2.txt
|-> [rocprof] RPL: on '240321_162024' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_2.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162024_4117686'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162024_4117686/input0_results_240321_162024'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162024_4117686/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 26 metrics
|-> [rocprof] 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, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, 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
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162024_4117686/input0_results_240321_162024
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_2.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_3.txt
|-> [rocprof] RPL: on '240321_162025' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_3.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162025_4117888'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162025_4117888/input0_results_240321_162025'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162025_4117888/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 24 metrics
|-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, 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
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162025_4117888/input0_results_240321_162025
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_3.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_4.txt
|-> [rocprof] RPL: on '240321_162025' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_4.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162025_4118072'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162025_4118072/input0_results_240321_162025'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162025_4118072/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 22 metrics
|-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, 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_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162025_4118072/input0_results_240321_162025
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_4.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_5.txt
|-> [rocprof] RPL: on '240321_162026' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_5.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162026_4118275'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162026_4118275/input0_results_240321_162026'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162026_4118275/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 21 metrics
|-> [rocprof] 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_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_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_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162026_4118275/input0_results_240321_162026
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_5.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_6.txt
|-> [rocprof] RPL: on '240321_162026' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_6.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162026_4118477'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162026_4118477/input0_results_240321_162026'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162026_4118477/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 20 metrics
|-> [rocprof] 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_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_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_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162026_4118477/input0_results_240321_162026
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_6.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_7.txt
|-> [rocprof] RPL: on '240321_162027' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_7.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162027_4118664'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162027_4118664/input0_results_240321_162027'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162027_4118664/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 20 metrics
|-> [rocprof] 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_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_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_EA_ATOMIC_sum
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162027_4118664/input0_results_240321_162027
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_7.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_8.txt
|-> [rocprof] RPL: on '240321_162027' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_8.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162027_4118848'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162027_4118848/input0_results_240321_162027'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162027_4118848/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 17 metrics
|-> [rocprof] 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_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162027_4118848/input0_results_240321_162027
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_8.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_9.txt
|-> [rocprof] RPL: on '240321_162028' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_9.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162028_4119050'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162028_4119050/input0_results_240321_162028'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162028_4119050/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 12 metrics
|-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, 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, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162028_4119050/input0_results_240321_162028
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_9.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/timestamps.txt
|-> [rocprof] RPL: on '240321_162028' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/timestamps.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162028_4119234'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162028_4119234/input0_results_240321_162028'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162028_4119234/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel = vecCopy
|-> [rocprof] range =
|-> [rocprof] 0 metrics
|-> [rocprof] vcopy testing on GCD 0
|-> [rocprof] Finished allocating vectors on the CPU
|-> [rocprof] Finished allocating vectors on the GPU
|-> [rocprof] Finished copying vectors to the GPU
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [rocprof] Launching the kernel on the GPU
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished executing kernel
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|-> [rocprof] Releasing GPU memory
|-> [rocprof] Releasing CPU memory
|-> [rocprof]
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162028_4119234/input0_results_240321_162028
|-> [rocprof] File 'tests/workloads/kernel_substr/MI200/timestamps.csv' is generating
|-> [rocprof]
[roofline] Checking for roofline.csv in tests/workloads/kernel_substr/MI200
[roofline] No roofline data found. Generating...
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -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: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU 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: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 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: vecCopy
@@ -0,0 +1,5 @@
pmc: SQC_TC_DATA_WRITE_REQ 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
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQC_ICACHE_MISSES_DUPLICATE 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
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: 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 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 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: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG 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: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES 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_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum
gpu:
range:
kernel: vecCopy
@@ -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_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_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_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum
gpu:
range:
kernel: vecCopy
@@ -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_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_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_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum
gpu:
range:
kernel: vecCopy
@@ -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_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_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_EA_ATOMIC_sum
gpu:
range:
kernel: vecCopy
@@ -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_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_FLAT_LDS_ONLY 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 TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2
1 Dispatch_ID Kernel_Name GPU_ID
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2
File diff suppressed because one or more lines are too long
@@ -0,0 +1,5 @@
device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh
0,1388.9658,1388.3842,1389.5475,5015.9883,5012.938,5019.0386,9225.1172,9224.5098,9225.7246,17715.531,17712.326,17718.736,20938.605,20878.021,20999.189,20270.34,20269.768,20270.912,170471.98,170468.02,170475.95,164910.77,164906.02,164915.52,41434.18,41433.711,41434.648,41492.617,41491.949,41493.285,166394.14,165902.47,166885.81
1,1389.0469,1388.5142,1389.5796,5028.8301,5026.8472,5030.813,9236.9521,9236.207,9237.6973,18239.07,18236.047,18242.094,20985.062,20918.174,21051.951,20304.107,20303.527,20304.688,170946.45,170942.11,170950.8,165186.3,165182.33,165190.27,41504.238,41503.312,41505.164,41562.047,41561.035,41563.059,166949,166945.52,166952.48
2,1388.8693,1388.3575,1389.381,5035.5464,5033.2891,5037.8037,9260.1914,9259.3496,9261.0332,18218.021,18217.1,18218.943,21053.375,21052.932,21053.818,20353.885,20353.205,20354.564,171154.2,171149.33,171159.08,165526.98,165523.47,165530.5,41583.637,41582.98,41584.293,41644.199,41643.281,41645.117,166959.98,166367,167552.97
3,1389.0635,1388.4847,1389.6422,5033.917,5032.3442,5035.4897,9239.7314,9239.0586,9240.4043,18333.445,18332.5,18334.391,21036.664,21036.422,21036.906,20312.801,20312.271,20313.33,171053,171047.16,171058.84,165173.69,165169.31,165178.06,41435.715,41282.48,41588.949,41581.074,41579.879,41582.27,166969.88,166965.3,166974.45
1 device HBMBw HBMBwLow hbmBwHigh L2Bw L2BwLow L2BwHigh L1Bw L1BwLow L1BwHigh LDSBw LDSBwLow LDSBwHigh FP32Flops FP32FlopsLow FP32FlopsHigh FP64Flops FP64FlopsLow FP64FlopsHigh MFMABF16Flops MFMABF16FlopsLow MFMABF16FlopsHigh MFMAF16Flops MFMAF16FlopsLow MFMAF16FlopsHigh MFMAF32Flops MFMAF32FlopsLow MFMAF32FlopsHigh MFMAF64Flops MFMAF64FlopsLow MFMAF64FlopsHigh MFMAI8Ops MFMAFI8OpsLow MFMAI8OpsHigh
2 0 1388.9658 1388.3842 1389.5475 5015.9883 5012.938 5019.0386 9225.1172 9224.5098 9225.7246 17715.531 17712.326 17718.736 20938.605 20878.021 20999.189 20270.34 20269.768 20270.912 170471.98 170468.02 170475.95 164910.77 164906.02 164915.52 41434.18 41433.711 41434.648 41492.617 41491.949 41493.285 166394.14 165902.47 166885.81
3 1 1389.0469 1388.5142 1389.5796 5028.8301 5026.8472 5030.813 9236.9521 9236.207 9237.6973 18239.07 18236.047 18242.094 20985.062 20918.174 21051.951 20304.107 20303.527 20304.688 170946.45 170942.11 170950.8 165186.3 165182.33 165190.27 41504.238 41503.312 41505.164 41562.047 41561.035 41563.059 166949 166945.52 166952.48
4 2 1388.8693 1388.3575 1389.381 5035.5464 5033.2891 5037.8037 9260.1914 9259.3496 9261.0332 18218.021 18217.1 18218.943 21053.375 21052.932 21053.818 20353.885 20353.205 20354.564 171154.2 171149.33 171159.08 165526.98 165523.47 165530.5 41583.637 41582.98 41584.293 41644.199 41643.281 41645.117 166959.98 166367 167552.97
5 3 1389.0635 1388.4847 1389.6422 5033.917 5032.3442 5035.4897 9239.7314 9239.0586 9240.4043 18333.445 18332.5 18334.391 21036.664 21036.422 21036.906 20312.801 20312.271 20313.33 171053 171047.16 171058.84 165173.69 165169.31 165178.06 41435.715 41282.48 41588.949 41581.074 41579.879 41582.27 166969.88 166965.3 166974.45
@@ -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,num_hbm_channels
path,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:16:46 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1,32
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 num_hbm_channels
2 path ./tests/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline Thu 21 Mar 2024 04:16:46 PM (CDT) 2 t007-002.hpcfund AMD EPYC 7V13 64-Core Processor American Megatrends Inc.0602 Rocky Linux 9.1 (Blue Onyx) 5.14.0-162.18.1.el9_1.x86_64 527650760 6.0.2-115 113-D67301-059 NA NA MI200 gfx90a 16 8192 104 4 8 64 1024 32 1700 1600 1700 1600 32 32 56 4 1638.4 1 32
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4119394,4119394,1048576,256,0,0,8,0,16,64,0x0,0x7fac132a4ec0,1411760919510468,1411760919537410,1411760919557090,1411760919572024
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4119394,4119394,1048576,256,0,0,8,0,16,64,0x0,0x7fac132a4ec0,1411760919567997,1411760919576130,1411760919591970,1411760919645724
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4119394,4119394,1048576,256,0,0,8,0,16,64,0x0,0x7fac132a4ec0,1411760919602192,1411760919648450,1411760919664930,1411760919666122
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 4119394 4119394 1048576 256 0 0 8 0 16 64 0x0 0x7fac132a4ec0 1411760919510468 1411760919537410 1411760919557090 1411760919572024
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 4119394 4119394 1048576 256 0 0 8 0 16 64 0x0 0x7fac132a4ec0 1411760919567997 1411760919576130 1411760919591970 1411760919645724
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 4119394 4119394 1048576 256 0 0 8 0 16 64 0x0 0x7fac132a4ec0 1411760919602192 1411760919648450 1411760919664930 1411760919666122
@@ -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
0,11995,1,145295,145295,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152516542,73578152524434,0,206478.0,206478.0,16384.0,65536.0,27426.0,2197528.0
1,11995,1,145295,145295,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152563173,73578152568942,0,189728.0,189728.0,16384.0,65536.0,13109.0,1048768.0
2,11995,1,145295,145295,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152541099,73578152547068,0,166335.0,166335.0,16384.0,65536.0,13122.0,1049488.0
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 145295 145295 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152516542 73578152524434 0 206478.0 206478.0 16384.0 65536.0 27426.0 2197528.0
3 1 11995 1 145295 145295 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152563173 73578152568942 0 189728.0 189728.0 16384.0 65536.0 13109.0 1048768.0
4 2 11995 1 145295 145295 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152541099 73578152547068 0 166335.0 166335.0 16384.0 65536.0 13122.0 1049488.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES
0,11995,1,145307,145307,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152516542,73578152524434,0,0.0,0.0,0.0
1,11995,1,145307,145307,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152563173,73578152568942,0,0.0,0.0,0.0
2,11995,1,145307,145307,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152541099,73578152547068,0,0.0,0.0,0.0
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 145307 145307 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152516542 73578152524434 0 0.0 0.0 0.0
3 1 11995 1 145307 145307 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152563173 73578152568942 0 0.0 0.0 0.0
4 2 11995 1 145307 145307 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152541099 73578152547068 0 0.0 0.0 0.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES
0,11995,1,145319,145319,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152516542,73578152524434,0,65536.0,286850.0,23022216.0
1,11995,1,145319,145319,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152563173,73578152568942,0,65536.0,284112.0,22724824.0
2,11995,1,145319,145319,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152541099,73578152547068,0,65536.0,193332.0,15480240.0
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 145319 145319 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152516542 73578152524434 0 65536.0 286850.0 23022216.0
3 1 11995 1 145319 145319 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152563173 73578152568942 0 65536.0 284112.0 22724824.0
4 2 11995 1 145319 145319 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152541099 73578152547068 0 65536.0 193332.0 15480240.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES
0,11995,1,145331,145331,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152516542,73578152524434,0,32768.0,521655.0,41735128.0
1,11995,1,145331,145331,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152563173,73578152568942,0,32768.0,411382.0,32908148.0
2,11995,1,145331,145331,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152541099,73578152547068,0,32768.0,407969.0,32636212.0
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 145331 145331 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152516542 73578152524434 0 32768.0 521655.0 41735128.0
3 1 11995 1 145331 145331 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152563173 73578152568942 0 32768.0 411382.0 32908148.0
4 2 11995 1 145331 145331 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152541099 73578152547068 0 32768.0 407969.0 32636212.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES
0,11995,1,145343,145343,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152516542,73578152524434,0,216770.0,216770.0,124638.0,867080.0,16384.0,13528873.0,247296.0,0.0,54536480.0
1,11995,1,145343,145343,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152563173,73578152568942,0,192345.0,192345.0,108619.0,769380.0,16384.0,10930963.0,202980.0,0.0,44128348.0
2,11995,1,145343,145343,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152541099,73578152547068,0,176247.0,176247.0,95064.0,704988.0,16384.0,10384019.0,198974.0,0.0,41996144.0
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 145343 145343 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152516542 73578152524434 0 216770.0 216770.0 124638.0 867080.0 16384.0 13528873.0 247296.0 0.0 54536480.0
3 1 11995 1 145343 145343 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152563173 73578152568942 0 192345.0 192345.0 108619.0 769380.0 16384.0 10930963.0 202980.0 0.0 44128348.0
4 2 11995 1 145343 145343 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152541099 73578152547068 0 176247.0 176247.0 95064.0 704988.0 16384.0 10384019.0 198974.0 0.0 41996144.0
@@ -0,0 +1,329 @@
Omniperf version: 2.0.0
Profiler choice: rocprofv2
Path: /home/colramos/omniperf/tests/workloads/kernel_substr/MI300A_A1
Target: MI300A_A1
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
Kernel Selection: ['vecCopy']
Dispatch Selection: None
Hardware Blocks: All
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Collecting Performance Counters
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[profiling] Current input file: tests/workloads/kernel_substr/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
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
[profiling] Current input file: tests/workloads/kernel_substr/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
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
[profiling] Current input file: tests/workloads/kernel_substr/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
|-> [/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:
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/SQ_INST_LEVEL_VMEM.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished copying the output vector from the GPU to the CPU
|-> [/opt/rocm/bin/rocprofv2] Releasing GPU memory
|-> [/opt/rocm/bin/rocprofv2] Releasing CPU memory
|-> [/opt/rocm/bin/rocprofv2] Results File: "tests/workloads/kernel_substr/MI300A_A1/out/pmc_1/results_SQ_INST_LEVEL_VMEM.csv"
|-> [/opt/rocm/bin/rocprofv2]
|-> [/opt/rocm/bin/rocprofv2] The output path for the following counters: tests/workloads/kernel_substr/MI300A_A1/out/pmc_1
[profiling] Current input file: tests/workloads/kernel_substr/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
[profiling] Current input file: tests/workloads/kernel_substr/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/kernel_substr/MI300A_A1/perfmon/pmc_perf_1.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SALU
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VSKIPPED
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F16
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_10.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_ATOMIC_REQ
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_STALL
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_REQ
[profiling] Current input file: tests/workloads/kernel_substr/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
[profiling] Current input file: tests/workloads/kernel_substr/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
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_13.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_ATOMIC[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_BUBBLE[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_CYCLE[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_ATOMIC[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_BUBBLE[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_CYCLE[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC[1]
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_14.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[5]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[5]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[5]
[profiling] Current input file: tests/workloads/kernel_substr/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]
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_16.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[5]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[5]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[5]
[profiling] Current input file: tests/workloads/kernel_substr/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]
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_2.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F64
|-> [/opt/rocm/bin/rocprofv2] - TCP_VOLATILE_sum
|-> [/opt/rocm/bin/rocprofv2] - TCP_TOTAL_ACCESSES_sum
|-> [/opt/rocm/bin/rocprofv2] - TCP_TOTAL_READ_sum
|-> [/opt/rocm/bin/rocprofv2] - TCP_TOTAL_WRITE_sum
|-> [/opt/rocm/bin/rocprofv2] - TA_BUFFER_ATOMIC_WAVEFRONTS_sum
|-> [/opt/rocm/bin/rocprofv2] - TA_BUFFER_TOTAL_CYCLES_sum
|-> [/opt/rocm/bin/rocprofv2] - TD_ATOMIC_WAVEFRONT_sum
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_3.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_FLAT
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_GDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_EXP_GDS
|-> [/opt/rocm/bin/rocprofv2] - TCP_TOTAL_ATOMIC_WITH_RET_sum
|-> [/opt/rocm/bin/rocprofv2] - TCP_TOTAL_ATOMIC_WITHOUT_RET_sum
|-> [/opt/rocm/bin/rocprofv2] - TCP_TOTAL_WRITEBACK_INVALIDATES_sum
|-> [/opt/rocm/bin/rocprofv2] - TCP_TOTAL_CACHE_ACCESSES_sum
|-> [/opt/rocm/bin/rocprofv2] - TA_BUFFER_COALESCED_READ_CYCLES_sum
|-> [/opt/rocm/bin/rocprofv2] - TA_BUFFER_COALESCED_WRITE_CYCLES_sum
|-> [/opt/rocm/bin/rocprofv2] - TD_COALESCABLE_WAVEFRONT_sum
|-> [/opt/rocm/bin/rocprofv2] - SPI_RA_RES_STALL_CSN
|-> [/opt/rocm/bin/rocprofv2] - SPI_RA_TMP_STALL_CSN
[profiling] Current input file: tests/workloads/kernel_substr/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/kernel_substr/MI300A_A1/perfmon/pmc_perf_5.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_SCA
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_EXP_GDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_MISC
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_FLAT
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_VMEM_WR
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_VMEM_RD
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_SALU
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_6.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_THREAD_CYCLES_VALU
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_BANK_CONFLICT
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_7.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_32
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_16
|-> [/opt/rocm/bin/rocprofv2] - SQ_ITEMS
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_MEM_VIOLATIONS
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_ATOMIC_RETURN
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_IDX_ACTIVE
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_RESTORED
[profiling] Current input file: tests/workloads/kernel_substr/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
|-> [/opt/rocm/bin/rocprofv2] - SQ_VALU_MFMA_BUSY_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - TCP_TCC_CC_ATOMIC_REQ_sum
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_9.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_I8
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_BF16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F64
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_INST_REQ
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_READ_REQ
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_WRITE_REQ
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/timestamps.txt
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
[roofline] Roofline temporarily disabled in MI300
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
gpu:
range:
kernel: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID
0,"vecCopy(double*, double*, double*, int, int) (.kd)",11995
1,"vecCopy(double*, double*, double*, int, int) (.kd)",11995
2,"vecCopy(double*, double*, double*, int, int) (.kd)",11995
1 Dispatch_ID Kernel_Name GPU_ID
2 0 vecCopy(double*, double*, double*, int, int) (.kd) 11995
3 1 vecCopy(double*, double*, double*, int, int) (.kd) 11995
4 2 vecCopy(double*, double*, double*, int, int) (.kd) 11995

Some files were not shown because too many files have changed in this diff Show More