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 fájl változott, egészen pontosan 289584 új sor hozzáadva és 0 régi sor törölve
@@ -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]",2,0,0,1267481,1267481,1048576,256,0,0,8,8,16,64,0x0,0x7f0eb8168ec0,120424,120424,16384,65536,13369,1717376,1410193234401133,1410204895308401,1410204895332881,1410193242172960
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1267481,1267481,1048576,256,0,0,8,8,16,64,0x0,0x7f0eb8168ec0,46836,46836,16384,65536,8058,1048584,1410193242195944,1410204895428561,1410204895447761,1410193242512571
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1267481,1267481,1048576,256,0,0,8,8,16,64,0x0,0x7f0eb8168ec0,43828,43828,16384,65536,7998,1048588,1410193242544701,1410204895469361,1410204895488081,1410193242740050
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 1267481 1267481 1048576 256 0 0 8 8 16 64 0x0 0x7f0eb8168ec0 120424 120424 16384 65536 13369 1717376 1410193234401133 1410204895308401 1410204895332881 1410193242172960
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 1267481 1267481 1048576 256 0 0 8 8 16 64 0x0 0x7f0eb8168ec0 46836 46836 16384 65536 8058 1048584 1410193242195944 1410204895428561 1410204895447761 1410193242512571
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 1267481 1267481 1048576 256 0 0 8 8 16 64 0x0 0x7f0eb8168ec0 43828 43828 16384 65536 7998 1048588 1410193242544701 1410204895469361 1410204895488081 1410193242740050
@@ -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]",2,0,0,1267667,1267667,1048576,256,0,0,8,8,16,64,0x0,0x7f9eef0c0ec0,0,0,0,1410193715977501,1410204895308401,1410204895332881,1410193723553168
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1267667,1267667,1048576,256,0,0,8,8,16,64,0x0,0x7f9eef0c0ec0,0,0,0,1410193723574359,1410204895428561,1410204895447761,1410193723871880
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1267667,1267667,1048576,256,0,0,8,8,16,64,0x0,0x7f9eef0c0ec0,0,0,0,1410193723900664,1410204895469361,1410204895488081,1410193724075433
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 1267667 1267667 1048576 256 0 0 8 8 16 64 0x0 0x7f9eef0c0ec0 0 0 0 1410193715977501 1410204895308401 1410204895332881 1410193723553168
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 1267667 1267667 1048576 256 0 0 8 8 16 64 0x0 0x7f9eef0c0ec0 0 0 0 1410193723574359 1410204895428561 1410204895447761 1410193723871880
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 1267667 1267667 1048576 256 0 0 8 8 16 64 0x0 0x7f9eef0c0ec0 0 0 0 1410193723900664 1410204895469361 1410204895488081 1410193724075433
@@ -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]",2,0,0,1267850,1267850,1048576,256,0,0,8,8,16,64,0x0,0x7f29fc24cec0,65536,217080,27847144,1410194196106960,1410204895308401,1410204895332881,1410194203543485
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1267850,1267850,1048576,256,0,0,8,8,16,64,0x0,0x7f29fc24cec0,65536,201340,25741952,1410194203562862,1410204895428561,1410204895447761,1410194203889688
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1267850,1267850,1048576,256,0,0,8,8,16,64,0x0,0x7f29fc24cec0,65536,200810,25639968,1410194203918102,1410204895469361,1410204895488081,1410194204085558
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 1267850 1267850 1048576 256 0 0 8 8 16 64 0x0 0x7f29fc24cec0 65536 217080 27847144 1410194196106960 1410204895308401 1410204895332881 1410194203543485
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 1267850 1267850 1048576 256 0 0 8 8 16 64 0x0 0x7f29fc24cec0 65536 201340 25741952 1410194203562862 1410204895428561 1410204895447761 1410194203889688
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 1267850 1267850 1048576 256 0 0 8 8 16 64 0x0 0x7f29fc24cec0 65536 200810 25639968 1410194203918102 1410204895469361 1410204895488081 1410194204085558
@@ -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]",2,0,0,1268033,1268033,1048576,256,0,0,8,8,16,64,0x0,0x7fedffc74ec0,32768,609944,78081400,1410194670380245,1410204895308401,1410204895332881,1410194678086308
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1268033,1268033,1048576,256,0,0,8,8,16,64,0x0,0x7fedffc74ec0,32768,673533,86217068,1410194678107769,1410204895428561,1410204895447761,1410194678459913
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1268033,1268033,1048576,256,0,0,8,8,16,64,0x0,0x7fedffc74ec0,32768,625490,80060980,1410194678486053,1410204895469361,1410204895488081,1410194678661503
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 1268033 1268033 1048576 256 0 0 8 8 16 64 0x0 0x7fedffc74ec0 32768 609944 78081400 1410194670380245 1410204895308401 1410204895332881 1410194678086308
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 1268033 1268033 1048576 256 0 0 8 8 16 64 0x0 0x7fedffc74ec0 32768 673533 86217068 1410194678107769 1410204895428561 1410204895447761 1410194678459913
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 1268033 1268033 1048576 256 0 0 8 8 16 64 0x0 0x7fedffc74ec0 32768 625490 80060980 1410194678486053 1410204895469361 1410204895488081 1410194678661503
@@ -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]",2,0,0,1268218,1268218,1048576,256,0,0,8,8,16,64,0x0,0x7fa94f5d4ec0,48952,48952,18068,391624,16384,25128672,238750,0,101043548,1410195147235800,1410204895308401,1410204895332881,1410195154883924
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1268218,1268218,1048576,256,0,0,8,8,16,64,0x0,0x7fa94f5d4ec0,42936,42936,13804,343496,16384,24583226,234692,0,98863936,1410195154913951,1410204895428561,1410204895447761,1410195155354471
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1268218,1268218,1048576,256,0,0,8,8,16,64,0x0,0x7fa94f5d4ec0,42192,42192,13020,337544,16384,24104198,233666,0,96939712,1410195155392643,1410204895469361,1410204895488081,1410195155592380
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 1268218 1268218 1048576 256 0 0 8 8 16 64 0x0 0x7fa94f5d4ec0 48952 48952 18068 391624 16384 25128672 238750 0 101043548 1410195147235800 1410204895308401 1410204895332881 1410195154883924
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 1268218 1268218 1048576 256 0 0 8 8 16 64 0x0 0x7fa94f5d4ec0 42936 42936 13804 343496 16384 24583226 234692 0 98863936 1410195154913951 1410204895428561 1410204895447761 1410195155354471
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 1268218 1268218 1048576 256 0 0 8 8 16 64 0x0 0x7fa94f5d4ec0 42192 42192 13020 337544 16384 24104198 233666 0 96939712 1410195155392643 1410204895469361 1410204895488081 1410195155592380
@@ -0,0 +1,679 @@
Omniperf version: 2.0.0-RC1
Profiler choice: rocprofv1
Path: /home1/josantos/omniperf/tests/workloads/device_filter/MI100
Target: MI100
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
Kernel Selection: None
Dispatch Selection: None
IP Blocks: All
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Collecting Performance Counters
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/SQ_IFETCH_LEVEL.txt
|-> [rocprof] RPL: on '240321_155419' 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/device_filter/MI100/perfmon/SQ_IFETCH_LEVEL.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155419_1267321'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155419_1267321/input0_results_240321_155419'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155419_1267321/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155419_1267321/input0_results_240321_155419
|-> [rocprof] File 'tests/workloads/device_filter/MI100/SQ_IFETCH_LEVEL.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/SQ_INST_LEVEL_LDS.txt
|-> [rocprof] RPL: on '240321_155419' 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/device_filter/MI100/perfmon/SQ_INST_LEVEL_LDS.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155419_1267507'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155419_1267507/input0_results_240321_155419'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155419_1267507/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155419_1267507/input0_results_240321_155419
|-> [rocprof] File 'tests/workloads/device_filter/MI100/SQ_INST_LEVEL_LDS.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt
|-> [rocprof] RPL: on '240321_155420' 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/device_filter/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155420_1267690'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155420_1267690/input0_results_240321_155420'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155420_1267690/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155420_1267690/input0_results_240321_155420
|-> [rocprof] File 'tests/workloads/device_filter/MI100/SQ_INST_LEVEL_SMEM.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt
|-> [rocprof] RPL: on '240321_155420' 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/device_filter/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155420_1267873'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155420_1267873/input0_results_240321_155420'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155420_1267873/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155420_1267873/input0_results_240321_155420
|-> [rocprof] File 'tests/workloads/device_filter/MI100/SQ_INST_LEVEL_VMEM.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/SQ_LEVEL_WAVES.txt
|-> [rocprof] RPL: on '240321_155421' 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/device_filter/MI100/perfmon/SQ_LEVEL_WAVES.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155421_1268058'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155421_1268058/input0_results_240321_155421'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155421_1268058/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155421_1268058/input0_results_240321_155421
|-> [rocprof] File 'tests/workloads/device_filter/MI100/SQ_LEVEL_WAVES.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_0.txt
|-> [rocprof] RPL: on '240321_155421' 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/device_filter/MI100/perfmon/pmc_perf_0.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155421_1268241'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155421_1268241/input0_results_240321_155421'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155421_1268241/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155421_1268241/input0_results_240321_155421
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_0.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_1.txt
|-> [rocprof] RPL: on '240321_155422' 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/device_filter/MI100/perfmon/pmc_perf_1.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155422_1268424'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155422_1268424/input0_results_240321_155422'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155422_1268424/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155422_1268424/input0_results_240321_155422
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_1.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_10.txt
|-> [rocprof] RPL: on '240321_155422' 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/device_filter/MI100/perfmon/pmc_perf_10.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155422_1268607'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155422_1268607/input0_results_240321_155422'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155422_1268607/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155422_1268607/input0_results_240321_155422
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_10.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_11.txt
|-> [rocprof] RPL: on '240321_155423' 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/device_filter/MI100/perfmon/pmc_perf_11.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155423_1268793'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155423_1268793/input0_results_240321_155423'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155423_1268793/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155423_1268793/input0_results_240321_155423
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_11.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_12.txt
|-> [rocprof] RPL: on '240321_155423' 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/device_filter/MI100/perfmon/pmc_perf_12.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155423_1268978'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155423_1268978/input0_results_240321_155423'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155423_1268978/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155423_1268978/input0_results_240321_155423
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_12.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_13.txt
|-> [rocprof] RPL: on '240321_155424' 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/device_filter/MI100/perfmon/pmc_perf_13.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155424_1269161'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155424_1269161/input0_results_240321_155424'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155424_1269161/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155424_1269161/input0_results_240321_155424
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_13.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_14.txt
|-> [rocprof] RPL: on '240321_155425' 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/device_filter/MI100/perfmon/pmc_perf_14.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155425_1269348'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155425_1269348/input0_results_240321_155425'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155425_1269348/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155425_1269348/input0_results_240321_155425
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_14.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_15.txt
|-> [rocprof] RPL: on '240321_155425' 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/device_filter/MI100/perfmon/pmc_perf_15.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155425_1269531'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155425_1269531/input0_results_240321_155425'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155425_1269531/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155425_1269531/input0_results_240321_155425
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_15.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_16.txt
|-> [rocprof] RPL: on '240321_155426' 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/device_filter/MI100/perfmon/pmc_perf_16.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155426_1269719'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155426_1269719/input0_results_240321_155426'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155426_1269719/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155426_1269719/input0_results_240321_155426
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_16.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_2.txt
|-> [rocprof] RPL: on '240321_155427' 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/device_filter/MI100/perfmon/pmc_perf_2.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155427_1269903'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155427_1269903/input0_results_240321_155427'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155427_1269903/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155427_1269903/input0_results_240321_155427
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_2.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_3.txt
|-> [rocprof] RPL: on '240321_155427' 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/device_filter/MI100/perfmon/pmc_perf_3.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155427_1270091'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155427_1270091/input0_results_240321_155427'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155427_1270091/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155427_1270091/input0_results_240321_155427
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_3.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_4.txt
|-> [rocprof] RPL: on '240321_155428' 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/device_filter/MI100/perfmon/pmc_perf_4.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155428_1270276'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155428_1270276/input0_results_240321_155428'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155428_1270276/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155428_1270276/input0_results_240321_155428
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_4.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_5.txt
|-> [rocprof] RPL: on '240321_155428' 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/device_filter/MI100/perfmon/pmc_perf_5.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155428_1270459'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155428_1270459/input0_results_240321_155428'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155428_1270459/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155428_1270459/input0_results_240321_155428
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_5.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_6.txt
|-> [rocprof] RPL: on '240321_155428' 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/device_filter/MI100/perfmon/pmc_perf_6.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155428_1270642'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155428_1270642/input0_results_240321_155428'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155428_1270642/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155428_1270642/input0_results_240321_155428
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_6.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_7.txt
|-> [rocprof] RPL: on '240321_155429' 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/device_filter/MI100/perfmon/pmc_perf_7.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155429_1270830'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155429_1270830/input0_results_240321_155429'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155429_1270830/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155429_1270830/input0_results_240321_155429
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_7.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_8.txt
|-> [rocprof] RPL: on '240321_155429' 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/device_filter/MI100/perfmon/pmc_perf_8.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155429_1271014'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155429_1271014/input0_results_240321_155429'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155429_1271014/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155429_1271014/input0_results_240321_155429
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_8.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_9.txt
|-> [rocprof] RPL: on '240321_155430' 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/device_filter/MI100/perfmon/pmc_perf_9.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155430_1271202'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155430_1271202/input0_results_240321_155430'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155430_1271202/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155430_1271202/input0_results_240321_155430
|-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_9.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/timestamps.txt
|-> [rocprof] RPL: on '240321_155430' 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/device_filter/MI100/perfmon/timestamps.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155430_1271386'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155430_1271386/input0_results_240321_155430'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155430_1271386/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_155430_1271386/input0_results_240321_155430
|-> [rocprof] File 'tests/workloads/device_filter/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:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES 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:
@@ -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:
@@ -0,0 +1,5 @@
pmc: TCC_EA_ATOMIC_LEVEL_sum
gpu:
range:
kernel:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel:
@@ -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]",2,0,0,1271546,1271546,1048576,256,0,0,8,8,16,64,0x0,0x7facae2fcec0,1410204895282038,1410204895308401,1410204895332881,1410204895343735
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1271546,1271546,1048576,256,0,0,8,8,16,64,0x0,0x7facae2fcec0,1410204895345248,1410204895428561,1410204895447761,1410204895449153
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1271546,1271546,1048576,256,0,0,8,8,16,64,0x0,0x7facae2fcec0,1410204895459924,1410204895469361,1410204895488081,1410204895489490
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 1271546 1271546 1048576 256 0 0 8 8 16 64 0x0 0x7facae2fcec0 1410204895282038 1410204895308401 1410204895332881 1410204895343735
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 1271546 1271546 1048576 256 0 0 8 8 16 64 0x0 0x7facae2fcec0 1410204895345248 1410204895428561 1410204895447761 1410204895449153
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 1271546 1271546 1048576 256 0 0 8 8 16 64 0x0 0x7facae2fcec0 1410204895459924 1410204895469361 1410204895488081 1410204895489490
@@ -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]",2,0,0,4154776,4154776,1048576,256,0,0,8,0,16,64,0x0,0x7f4aeac78ec0,28399,28399,16384,65536,16539,1859828,1412689608475887,1412702536508356,1412702536528996,1412689624744624
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4154776,4154776,1048576,256,0,0,8,0,16,64,0x0,0x7f4aeac78ec0,41854,41854,16384,65536,9149,1048652,1412689624764922,1412702536548036,1412702536563556,1412689625202329
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4154776,4154776,1048576,256,0,0,8,0,16,64,0x0,0x7f4aeac78ec0,42687,42687,16384,65536,9446,1048640,1412689625231735,1412702536625636,1412702536642116,1412689625401916
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 4154776 4154776 1048576 256 0 0 8 0 16 64 0x0 0x7f4aeac78ec0 28399 28399 16384 65536 16539 1859828 1412689608475887 1412702536508356 1412702536528996 1412689624744624
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 4154776 4154776 1048576 256 0 0 8 0 16 64 0x0 0x7f4aeac78ec0 41854 41854 16384 65536 9149 1048652 1412689624764922 1412702536548036 1412702536563556 1412689625202329
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 4154776 4154776 1048576 256 0 0 8 0 16 64 0x0 0x7f4aeac78ec0 42687 42687 16384 65536 9446 1048640 1412689625231735 1412702536625636 1412702536642116 1412689625401916
@@ -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]",2,0,0,4154974,4154974,1048576,256,0,0,8,0,16,64,0x0,0x7f1046a28ec0,0,0,0,1412690095463857,1412702536508356,1412702536528996,1412690111629429
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4154974,4154974,1048576,256,0,0,8,0,16,64,0x0,0x7f1046a28ec0,0,0,0,1412690111650128,1412702536548036,1412702536563556,1412690111919096
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4154974,4154974,1048576,256,0,0,8,0,16,64,0x0,0x7f1046a28ec0,0,0,0,1412690111945456,1412702536625636,1412702536642116,1412690112092594
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 4154974 4154974 1048576 256 0 0 8 0 16 64 0x0 0x7f1046a28ec0 0 0 0 1412690095463857 1412702536508356 1412702536528996 1412690111629429
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 4154974 4154974 1048576 256 0 0 8 0 16 64 0x0 0x7f1046a28ec0 0 0 0 1412690111650128 1412702536548036 1412702536563556 1412690111919096
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 4154974 4154974 1048576 256 0 0 8 0 16 64 0x0 0x7f1046a28ec0 0 0 0 1412690111945456 1412702536625636 1412702536642116 1412690112092594
@@ -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]",2,0,0,4155175,4155175,1048576,256,0,0,8,0,16,64,0x0,0x7fd9f40c4ec0,65536,172670,19277760,1412690576047496,1412702536508356,1412702536528996,1412690592443443
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4155175,4155175,1048576,256,0,0,8,0,16,64,0x0,0x7fd9f40c4ec0,65536,228700,25581136,1412690592461567,1412702536548036,1412702536563556,1412690592741416
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4155175,4155175,1048576,256,0,0,8,0,16,64,0x0,0x7fd9f40c4ec0,65536,231114,25926712,1412690592767165,1412702536625636,1412702536642116,1412690592915886
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 4155175 4155175 1048576 256 0 0 8 0 16 64 0x0 0x7fd9f40c4ec0 65536 172670 19277760 1412690576047496 1412702536508356 1412702536528996 1412690592443443
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 4155175 4155175 1048576 256 0 0 8 0 16 64 0x0 0x7fd9f40c4ec0 65536 228700 25581136 1412690592461567 1412702536548036 1412702536563556 1412690592741416
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 4155175 4155175 1048576 256 0 0 8 0 16 64 0x0 0x7fd9f40c4ec0 65536 231114 25926712 1412690592767165 1412702536625636 1412702536642116 1412690592915886
@@ -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]",2,0,0,4155361,4155361,1048576,256,0,0,8,0,16,64,0x0,0x7f9045bb8ec0,32768,290637,32556924,1412691060480394,1412702536508356,1412702536528996,1412691076529415
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4155361,4155361,1048576,256,0,0,8,0,16,64,0x0,0x7f9045bb8ec0,32768,589721,66052460,1412691076546758,1412702536548036,1412702536563556,1412691076842818
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4155361,4155361,1048576,256,0,0,8,0,16,64,0x0,0x7f9045bb8ec0,32768,574435,64354132,1412691076869588,1412702536625636,1412702536642116,1412691077020423
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 4155361 4155361 1048576 256 0 0 8 0 16 64 0x0 0x7f9045bb8ec0 32768 290637 32556924 1412691060480394 1412702536508356 1412702536528996 1412691076529415
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 4155361 4155361 1048576 256 0 0 8 0 16 64 0x0 0x7f9045bb8ec0 32768 589721 66052460 1412691076546758 1412702536548036 1412702536563556 1412691076842818
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 4155361 4155361 1048576 256 0 0 8 0 16 64 0x0 0x7f9045bb8ec0 32768 574435 64354132 1412691076869588 1412702536625636 1412702536642116 1412691077020423
@@ -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]",2,0,0,4155559,4155559,1048576,256,0,0,8,0,16,64,0x0,0x7f2e47d90ec0,27782,27782,11060,222264,16384,10980955,128903,0,44430920,1412691542352890,1412702536508356,1412702536528996,1412691558586810
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4155559,4155559,1048576,256,0,0,8,0,16,64,0x0,0x7f2e47d90ec0,42364,42364,13501,338920,16384,20566692,235190,0,82737616,1412691558614052,1412702536548036,1412702536563556,1412691558909250
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4155559,4155559,1048576,256,0,0,8,0,16,64,0x0,0x7f2e47d90ec0,40646,40646,12686,325176,16384,19387932,222546,0,78034296,1412691558944307,1412702536625636,1412702536642116,1412691559104820
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 4155559 4155559 1048576 256 0 0 8 0 16 64 0x0 0x7f2e47d90ec0 27782 27782 11060 222264 16384 10980955 128903 0 44430920 1412691542352890 1412702536508356 1412702536528996 1412691558586810
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 4155559 4155559 1048576 256 0 0 8 0 16 64 0x0 0x7f2e47d90ec0 42364 42364 13501 338920 16384 20566692 235190 0 82737616 1412691558614052 1412702536548036 1412702536563556 1412691558909250
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 4155559 4155559 1048576 256 0 0 8 0 16 64 0x0 0x7f2e47d90ec0 40646 40646 12686 325176 16384 19387932 222546 0 78034296 1412691558944307 1412702536625636 1412702536642116 1412691559104820
@@ -0,0 +1,739 @@
Omniperf version: 2.0.0-RC1
Profiler choice: rocprofv1
Path: /home1/josantos/omniperf/tests/workloads/device_filter/MI200
Target: MI200
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
Kernel Selection: None
Dispatch Selection: None
IP Blocks: All
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Collecting Performance Counters
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/SQ_IFETCH_LEVEL.txt
|-> [rocprof] RPL: on '240321_163557' 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/device_filter/MI200/perfmon/SQ_IFETCH_LEVEL.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163557_4154616'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163557_4154616/input0_results_240321_163557'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163557_4154616/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163557_4154616/input0_results_240321_163557
|-> [rocprof] File 'tests/workloads/device_filter/MI200/SQ_IFETCH_LEVEL.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_LDS.txt
|-> [rocprof] RPL: on '240321_163557' 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/device_filter/MI200/perfmon/SQ_INST_LEVEL_LDS.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163557_4154814'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163557_4154814/input0_results_240321_163557'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163557_4154814/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163557_4154814/input0_results_240321_163557
|-> [rocprof] File 'tests/workloads/device_filter/MI200/SQ_INST_LEVEL_LDS.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt
|-> [rocprof] RPL: on '240321_163558' 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/device_filter/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163558_4155015'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163558_4155015/input0_results_240321_163558'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163558_4155015/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163558_4155015/input0_results_240321_163558
|-> [rocprof] File 'tests/workloads/device_filter/MI200/SQ_INST_LEVEL_SMEM.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt
|-> [rocprof] RPL: on '240321_163558' 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/device_filter/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163558_4155199'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163558_4155199/input0_results_240321_163558'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163558_4155199/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163558_4155199/input0_results_240321_163558
|-> [rocprof] File 'tests/workloads/device_filter/MI200/SQ_INST_LEVEL_VMEM.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/SQ_LEVEL_WAVES.txt
|-> [rocprof] RPL: on '240321_163559' 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/device_filter/MI200/perfmon/SQ_LEVEL_WAVES.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163559_4155399'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163559_4155399/input0_results_240321_163559'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163559_4155399/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163559_4155399/input0_results_240321_163559
|-> [rocprof] File 'tests/workloads/device_filter/MI200/SQ_LEVEL_WAVES.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_0.txt
|-> [rocprof] RPL: on '240321_163559' 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/device_filter/MI200/perfmon/pmc_perf_0.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163559_4155605'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163559_4155605/input0_results_240321_163559'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163559_4155605/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163559_4155605/input0_results_240321_163559
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_0.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_1.txt
|-> [rocprof] RPL: on '240321_163600' 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/device_filter/MI200/perfmon/pmc_perf_1.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163600_4155792'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163600_4155792/input0_results_240321_163600'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163600_4155792/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163600_4155792/input0_results_240321_163600
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_1.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_10.txt
|-> [rocprof] RPL: on '240321_163600' 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/device_filter/MI200/perfmon/pmc_perf_10.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163600_4155978'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163600_4155978/input0_results_240321_163600'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163600_4155978/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163600_4155978/input0_results_240321_163600
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_10.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_11.txt
|-> [rocprof] RPL: on '240321_163601' 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/device_filter/MI200/perfmon/pmc_perf_11.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163601_4156163'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163601_4156163/input0_results_240321_163601'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163601_4156163/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163601_4156163/input0_results_240321_163601
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_11.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_12.txt
|-> [rocprof] RPL: on '240321_163601' 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/device_filter/MI200/perfmon/pmc_perf_12.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163601_4156379'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163601_4156379/input0_results_240321_163601'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163601_4156379/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163601_4156379/input0_results_240321_163601
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_12.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_13.txt
|-> [rocprof] RPL: on '240321_163602' 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/device_filter/MI200/perfmon/pmc_perf_13.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163602_4156580'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163602_4156580/input0_results_240321_163602'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163602_4156580/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163602_4156580/input0_results_240321_163602
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_13.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_14.txt
|-> [rocprof] RPL: on '240321_163602' 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/device_filter/MI200/perfmon/pmc_perf_14.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163602_4156781'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163602_4156781/input0_results_240321_163602'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163602_4156781/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163602_4156781/input0_results_240321_163602
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_14.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_15.txt
|-> [rocprof] RPL: on '240321_163603' 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/device_filter/MI200/perfmon/pmc_perf_15.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163603_4156967'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163603_4156967/input0_results_240321_163603'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163603_4156967/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163603_4156967/input0_results_240321_163603
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_15.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_16.txt
|-> [rocprof] RPL: on '240321_163604' 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/device_filter/MI200/perfmon/pmc_perf_16.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163604_4157155'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163604_4157155/input0_results_240321_163604'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163604_4157155/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163604_4157155/input0_results_240321_163604
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_16.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_17.txt
|-> [rocprof] RPL: on '240321_163605' 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/device_filter/MI200/perfmon/pmc_perf_17.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163605_4157340'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163605_4157340/input0_results_240321_163605'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163605_4157340/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163605_4157340/input0_results_240321_163605
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_17.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_18.txt
|-> [rocprof] RPL: on '240321_163605' 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/device_filter/MI200/perfmon/pmc_perf_18.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163605_4157525'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163605_4157525/input0_results_240321_163605'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163605_4157525/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163605_4157525/input0_results_240321_163605
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_18.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_2.txt
|-> [rocprof] RPL: on '240321_163606' 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/device_filter/MI200/perfmon/pmc_perf_2.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163606_4157708'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163606_4157708/input0_results_240321_163606'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163606_4157708/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163606_4157708/input0_results_240321_163606
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_2.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_3.txt
|-> [rocprof] RPL: on '240321_163606' 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/device_filter/MI200/perfmon/pmc_perf_3.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163606_4157893'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163606_4157893/input0_results_240321_163606'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163606_4157893/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163606_4157893/input0_results_240321_163606
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_3.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_4.txt
|-> [rocprof] RPL: on '240321_163607' 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/device_filter/MI200/perfmon/pmc_perf_4.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163607_4158080'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163607_4158080/input0_results_240321_163607'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163607_4158080/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163607_4158080/input0_results_240321_163607
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_4.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_5.txt
|-> [rocprof] RPL: on '240321_163607' 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/device_filter/MI200/perfmon/pmc_perf_5.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163607_4158281'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163607_4158281/input0_results_240321_163607'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163607_4158281/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163607_4158281/input0_results_240321_163607
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_5.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_6.txt
|-> [rocprof] RPL: on '240321_163608' 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/device_filter/MI200/perfmon/pmc_perf_6.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163608_4158468'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163608_4158468/input0_results_240321_163608'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163608_4158468/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163608_4158468/input0_results_240321_163608
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_6.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_7.txt
|-> [rocprof] RPL: on '240321_163608' 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/device_filter/MI200/perfmon/pmc_perf_7.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163608_4158670'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163608_4158670/input0_results_240321_163608'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163608_4158670/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163608_4158670/input0_results_240321_163608
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_7.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_8.txt
|-> [rocprof] RPL: on '240321_163609' 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/device_filter/MI200/perfmon/pmc_perf_8.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163609_4158857'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163609_4158857/input0_results_240321_163609'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163609_4158857/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163609_4158857/input0_results_240321_163609
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_8.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_9.txt
|-> [rocprof] RPL: on '240321_163609' 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/device_filter/MI200/perfmon/pmc_perf_9.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163609_4159041'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163609_4159041/input0_results_240321_163609'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163609_4159041/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163609_4159041/input0_results_240321_163609
|-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_9.csv' is generating
|-> [rocprof]
[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/timestamps.txt
|-> [rocprof] RPL: on '240321_163610' 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/device_filter/MI200/perfmon/timestamps.txt'
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163610_4159225'
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163610_4159225/input0_results_240321_163610'
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163610_4159225/input0.xml"
|-> [rocprof] gpu_index =
|-> [rocprof] kernel =
|-> [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_163610_4159225/input0_results_240321_163610
|-> [rocprof] File 'tests/workloads/device_filter/MI200/timestamps.csv' is generating
|-> [rocprof]
[roofline] Checking for roofline.csv in tests/workloads/device_filter/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:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_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:
@@ -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:
@@ -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:
@@ -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:
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
gpu:
range:
kernel:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel:
@@ -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 @@
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
0,1388.7948,1388.2125,1389.3771,5016.1738,5013.2036,5019.144,9226.4229,9225.7852,9227.0605,17715.307,17712.113,17718.5,20942.453,20882.1,21002.807,20272.682,20272.182,20273.182,170487.92,170484.22,170491.62,164932.06,164926.69,164937.44,41438.844,41438.195,41439.492,41498.918,41498.344,41499.492,166413.58,165921.97,166905.19
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 1388.7948 1388.2125 1389.3771 5016.1738 5013.2036 5019.144 9226.4229 9225.7852 9227.0605 17715.307 17712.113 17718.5 20942.453 20882.1 21002.807 20272.682 20272.182 20273.182 170487.92 170484.22 170491.62 164932.06 164926.69 164937.44 41438.844 41438.195 41439.492 41498.918 41498.344 41499.492 166413.58 165921.97 166905.19
@@ -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]",2,0,0,4159385,4159385,1048576,256,0,0,8,0,16,64,0x0,0x7f7aee850ec0,1412702536482286,1412702536508356,1412702536528996,1412702536542951
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4159385,4159385,1048576,256,0,0,8,0,16,64,0x0,0x7f7aee850ec0,1412702536540095,1412702536548036,1412702536563556,1412702536623202
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4159385,4159385,1048576,256,0,0,8,0,16,64,0x0,0x7f7aee850ec0,1412702536574069,1412702536625636,1412702536642116,1412702536643421
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 4159385 4159385 1048576 256 0 0 8 0 16 64 0x0 0x7f7aee850ec0 1412702536482286 1412702536508356 1412702536528996 1412702536542951
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 4159385 4159385 1048576 256 0 0 8 0 16 64 0x0 0x7f7aee850ec0 1412702536540095 1412702536548036 1412702536563556 1412702536623202
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 4159385 4159385 1048576 256 0 0 8 0 16 64 0x0 0x7f7aee850ec0 1412702536574069 1412702536625636 1412702536642116 1412702536643421
@@ -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
0,11995,1,148337,148337,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73843971992178,73843971999909,0,218990.0,218990.0,16384.0,65536.0,28159.0,2249984.0
1,11995,1,148337,148337,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73843972017897,73843972024226,0,194419.0,194419.0,16384.0,65536.0,13100.0,1048608.0
2,11995,1,148337,148337,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73843972039650,73843972045859,0,166313.0,166313.0,16384.0,65536.0,13087.0,1048708.0
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 148337 148337 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73843971992178 73843971999909 0 218990.0 218990.0 16384.0 65536.0 28159.0 2249984.0
3 1 11995 1 148337 148337 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73843972017897 73843972024226 0 194419.0 194419.0 16384.0 65536.0 13100.0 1048608.0
4 2 11995 1 148337 148337 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73843972039650 73843972045859 0 166313.0 166313.0 16384.0 65536.0 13087.0 1048708.0
@@ -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
0,11995,1,148348,148348,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73843971992178,73843971999909,0,0.0,0.0,0.0
1,11995,1,148348,148348,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73843972017897,73843972024226,0,0.0,0.0,0.0
2,11995,1,148348,148348,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73843972039650,73843972045859,0,0.0,0.0,0.0
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 148348 148348 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73843971992178 73843971999909 0 0.0 0.0 0.0
3 1 11995 1 148348 148348 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73843972017897 73843972024226 0 0.0 0.0 0.0
4 2 11995 1 148348 148348 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73843972039650 73843972045859 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
0,11995,1,148359,148359,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73843971992178,73843971999909,0,65536.0,359830.0,28775024.0
1,11995,1,148359,148359,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73843972017897,73843972024226,0,65536.0,279626.0,22368848.0
2,11995,1,148359,148359,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73843972039650,73843972045859,0,65536.0,212150.0,16965480.0
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 148359 148359 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73843971992178 73843971999909 0 65536.0 359830.0 28775024.0
3 1 11995 1 148359 148359 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73843972017897 73843972024226 0 65536.0 279626.0 22368848.0
4 2 11995 1 148359 148359 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73843972039650 73843972045859 0 65536.0 212150.0 16965480.0
@@ -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
0,11995,1,148370,148370,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73843971992178,73843971999909,0,32768.0,540654.0,43241432.0
1,11995,1,148370,148370,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73843972017897,73843972024226,0,32768.0,423717.0,33892596.0
2,11995,1,148370,148370,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73843972039650,73843972045859,0,32768.0,421757.0,33736452.0
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 148370 148370 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73843971992178 73843971999909 0 32768.0 540654.0 43241432.0
3 1 11995 1 148370 148370 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73843972017897 73843972024226 0 32768.0 423717.0 33892596.0
4 2 11995 1 148370 148370 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73843972039650 73843972045859 0 32768.0 421757.0 33736452.0
@@ -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
0,11995,1,148381,148381,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73843971992178,73843971999909,0,215077.0,215077.0,120524.0,860308.0,16384.0,14073357.0,258076.0,0.0,56727488.0
1,11995,1,148381,148381,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73843972017897,73843972024226,0,186817.0,186817.0,103332.0,747268.0,16384.0,10901162.0,200092.0,0.0,43996920.0
2,11995,1,148381,148381,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73843972039650,73843972045859,0,183393.0,183393.0,102287.0,733572.0,16384.0,10354964.0,192829.0,0.0,41809560.0
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 148381 148381 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73843971992178 73843971999909 0 215077.0 215077.0 120524.0 860308.0 16384.0 14073357.0 258076.0 0.0 56727488.0
3 1 11995 1 148381 148381 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73843972017897 73843972024226 0 186817.0 186817.0 103332.0 747268.0 16384.0 10901162.0 200092.0 0.0 43996920.0
4 2 11995 1 148381 148381 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73843972039650 73843972045859 0 183393.0 183393.0 102287.0 733572.0 16384.0 10354964.0 192829.0 0.0 41809560.0
@@ -0,0 +1,247 @@
Omniperf version: 2.0.0
Profiler choice: rocprofv2
Path: /home/colramos/omniperf/tests/workloads/device_filter/MI300A_A1
Target: MI300A_A1
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
Kernel Selection: None
Dispatch Selection: None
Hardware Blocks: All
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Collecting Performance Counters
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[profiling] Current input file: tests/workloads/device_filter/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
[profiling] Current input file: tests/workloads/device_filter/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:
[profiling] Current input file: tests/workloads/device_filter/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/device_filter/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/device_filter/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/device_filter/MI300A_A1/out/pmc_1
[profiling] Current input file: tests/workloads/device_filter/MI300A_A1/perfmon/SQ_LEVEL_WAVES.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - GRBM_COUNT
|-> [/opt/rocm/bin/rocprofv2] - GRBM_GUI_ACTIVE
|-> [/opt/rocm/bin/rocprofv2] - CPC_ME1_BUSY_FOR_PACKET_DECODE
|-> [/opt/rocm/bin/rocprofv2] - SQ_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVE_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_LEVEL_WAVES
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
[profiling] Current input file: tests/workloads/device_filter/MI300A_A1/perfmon/pmc_perf_0.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CU_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVE_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_CVT
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM_WR
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM_RD
[profiling] Current input file: tests/workloads/device_filter/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
|-> [/opt/rocm/bin/rocprofv2] - GRBM_SPI_BUSY
[profiling] Current input file: tests/workloads/device_filter/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/device_filter/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/device_filter/MI300A_A1/perfmon/pmc_perf_12.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_2
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_4
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
[profiling] Current input file: tests/workloads/device_filter/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]
[profiling] Current input file: tests/workloads/device_filter/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]
[profiling] Current input file: tests/workloads/device_filter/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]
[profiling] Current input file: tests/workloads/device_filter/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]
[profiling] Current input file: tests/workloads/device_filter/MI300A_A1/perfmon/pmc_perf_17.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_TOO_MANY_EA_WRREQS_STALL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_WRITE[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_TOO_MANY_EA_WRREQS_STALL[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_WRITE[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[2]
[profiling] Current input file: tests/workloads/device_filter/MI300A_A1/perfmon/pmc_perf_2.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F64
[profiling] Current input file: tests/workloads/device_filter/MI300A_A1/perfmon/pmc_perf_3.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_FLAT
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_GDS
[profiling] Current input file: tests/workloads/device_filter/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
[profiling] Current input file: tests/workloads/device_filter/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
[profiling] Current input file: tests/workloads/device_filter/MI300A_A1/perfmon/pmc_perf_6.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_THREAD_CYCLES_VALU
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_BANK_CONFLICT
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_ADDR_CONFLICT
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_UNALIGNED_STALL
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_EQ_64
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_64
[profiling] Current input file: tests/workloads/device_filter/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
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_SAVED
[profiling] Current input file: tests/workloads/device_filter/MI300A_A1/perfmon/pmc_perf_8.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM_NORM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_MFMA
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_I8
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_BF16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_F64
[profiling] Current input file: tests/workloads/device_filter/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/device_filter/MI300A_A1/perfmon/timestamps.txt
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
[roofline] Roofline temporarily disabled in MI300
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_ATOMIC[0] TCC_BUBBLE[0] TCC_CYCLE[0] TCC_EA0_ATOMIC[0] TCC_ATOMIC[1] TCC_BUBBLE[1] TCC_CYCLE[1] TCC_EA0_ATOMIC[1] TCC_ATOMIC[2] TCC_BUBBLE[2] TCC_CYCLE[2] TCC_EA0_ATOMIC[2] TCC_ATOMIC[3] TCC_BUBBLE[3] TCC_CYCLE[3] TCC_EA0_ATOMIC[3] TCC_ATOMIC[4] TCC_BUBBLE[4] TCC_CYCLE[4] TCC_EA0_ATOMIC[4] TCC_ATOMIC[5] TCC_BUBBLE[5] TCC_CYCLE[5] TCC_EA0_ATOMIC[5] TCC_ATOMIC[6] TCC_BUBBLE[6] TCC_CYCLE[6] TCC_EA0_ATOMIC[6] TCC_ATOMIC[7] TCC_BUBBLE[7] TCC_CYCLE[7] TCC_EA0_ATOMIC[7] TCC_ATOMIC[8] TCC_BUBBLE[8] TCC_CYCLE[8] TCC_EA0_ATOMIC[8] TCC_ATOMIC[9] TCC_BUBBLE[9] TCC_CYCLE[9] TCC_EA0_ATOMIC[9] TCC_ATOMIC[10] TCC_BUBBLE[10] TCC_CYCLE[10] TCC_EA0_ATOMIC[10] TCC_ATOMIC[11] TCC_BUBBLE[11] TCC_CYCLE[11] TCC_EA0_ATOMIC[11] TCC_ATOMIC[12] TCC_BUBBLE[12] TCC_CYCLE[12] TCC_EA0_ATOMIC[12] TCC_ATOMIC[13] TCC_BUBBLE[13] TCC_CYCLE[13] TCC_EA0_ATOMIC[13] TCC_ATOMIC[14] TCC_BUBBLE[14] TCC_CYCLE[14] TCC_EA0_ATOMIC[14] TCC_ATOMIC[15] TCC_BUBBLE[15] TCC_CYCLE[15] TCC_EA0_ATOMIC[15]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_EA0_ATOMIC_LEVEL[0] TCC_EA0_RDREQ[0] TCC_EA0_RDREQ_32B[0] TCC_EA0_RDREQ_LEVEL[0] TCC_EA0_ATOMIC_LEVEL[1] TCC_EA0_RDREQ[1] TCC_EA0_RDREQ_32B[1] TCC_EA0_RDREQ_LEVEL[1] TCC_EA0_ATOMIC_LEVEL[2] TCC_EA0_RDREQ[2] TCC_EA0_RDREQ_32B[2] TCC_EA0_RDREQ_LEVEL[2] TCC_EA0_ATOMIC_LEVEL[3] TCC_EA0_RDREQ[3] TCC_EA0_RDREQ_32B[3] TCC_EA0_RDREQ_LEVEL[3] TCC_EA0_ATOMIC_LEVEL[4] TCC_EA0_RDREQ[4] TCC_EA0_RDREQ_32B[4] TCC_EA0_RDREQ_LEVEL[4] TCC_EA0_ATOMIC_LEVEL[5] TCC_EA0_RDREQ[5] TCC_EA0_RDREQ_32B[5] TCC_EA0_RDREQ_LEVEL[5] TCC_EA0_ATOMIC_LEVEL[6] TCC_EA0_RDREQ[6] TCC_EA0_RDREQ_32B[6] TCC_EA0_RDREQ_LEVEL[6] TCC_EA0_ATOMIC_LEVEL[7] TCC_EA0_RDREQ[7] TCC_EA0_RDREQ_32B[7] TCC_EA0_RDREQ_LEVEL[7] TCC_EA0_ATOMIC_LEVEL[8] TCC_EA0_RDREQ[8] TCC_EA0_RDREQ_32B[8] TCC_EA0_RDREQ_LEVEL[8] TCC_EA0_ATOMIC_LEVEL[9] TCC_EA0_RDREQ[9] TCC_EA0_RDREQ_32B[9] TCC_EA0_RDREQ_LEVEL[9] TCC_EA0_ATOMIC_LEVEL[10] TCC_EA0_RDREQ[10] TCC_EA0_RDREQ_32B[10] TCC_EA0_RDREQ_LEVEL[10] TCC_EA0_ATOMIC_LEVEL[11] TCC_EA0_RDREQ[11] TCC_EA0_RDREQ_32B[11] TCC_EA0_RDREQ_LEVEL[11] TCC_EA0_ATOMIC_LEVEL[12] TCC_EA0_RDREQ[12] TCC_EA0_RDREQ_32B[12] TCC_EA0_RDREQ_LEVEL[12] TCC_EA0_ATOMIC_LEVEL[13] TCC_EA0_RDREQ[13] TCC_EA0_RDREQ_32B[13] TCC_EA0_RDREQ_LEVEL[13] TCC_EA0_ATOMIC_LEVEL[14] TCC_EA0_RDREQ[14] TCC_EA0_RDREQ_32B[14] TCC_EA0_RDREQ_LEVEL[14] TCC_EA0_ATOMIC_LEVEL[15] TCC_EA0_RDREQ[15] TCC_EA0_RDREQ_32B[15] TCC_EA0_RDREQ_LEVEL[15]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_EA0_WRREQ[0] TCC_EA0_WRREQ_64B[0] TCC_EA0_WRREQ_LEVEL[0] TCC_HIT[0] TCC_EA0_WRREQ[1] TCC_EA0_WRREQ_64B[1] TCC_EA0_WRREQ_LEVEL[1] TCC_HIT[1] TCC_EA0_WRREQ[2] TCC_EA0_WRREQ_64B[2] TCC_EA0_WRREQ_LEVEL[2] TCC_HIT[2] TCC_EA0_WRREQ[3] TCC_EA0_WRREQ_64B[3] TCC_EA0_WRREQ_LEVEL[3] TCC_HIT[3] TCC_EA0_WRREQ[4] TCC_EA0_WRREQ_64B[4] TCC_EA0_WRREQ_LEVEL[4] TCC_HIT[4] TCC_EA0_WRREQ[5] TCC_EA0_WRREQ_64B[5] TCC_EA0_WRREQ_LEVEL[5] TCC_HIT[5] TCC_EA0_WRREQ[6] TCC_EA0_WRREQ_64B[6] TCC_EA0_WRREQ_LEVEL[6] TCC_HIT[6] TCC_EA0_WRREQ[7] TCC_EA0_WRREQ_64B[7] TCC_EA0_WRREQ_LEVEL[7] TCC_HIT[7] TCC_EA0_WRREQ[8] TCC_EA0_WRREQ_64B[8] TCC_EA0_WRREQ_LEVEL[8] TCC_HIT[8] TCC_EA0_WRREQ[9] TCC_EA0_WRREQ_64B[9] TCC_EA0_WRREQ_LEVEL[9] TCC_HIT[9] TCC_EA0_WRREQ[10] TCC_EA0_WRREQ_64B[10] TCC_EA0_WRREQ_LEVEL[10] TCC_HIT[10] TCC_EA0_WRREQ[11] TCC_EA0_WRREQ_64B[11] TCC_EA0_WRREQ_LEVEL[11] TCC_HIT[11] TCC_EA0_WRREQ[12] TCC_EA0_WRREQ_64B[12] TCC_EA0_WRREQ_LEVEL[12] TCC_HIT[12] TCC_EA0_WRREQ[13] TCC_EA0_WRREQ_64B[13] TCC_EA0_WRREQ_LEVEL[13] TCC_HIT[13] TCC_EA0_WRREQ[14] TCC_EA0_WRREQ_64B[14] TCC_EA0_WRREQ_LEVEL[14] TCC_HIT[14] TCC_EA0_WRREQ[15] TCC_EA0_WRREQ_64B[15] TCC_EA0_WRREQ_LEVEL[15] TCC_HIT[15]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_RW_REQ[0] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_RW_REQ[1] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_RW_REQ[2] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_RW_REQ[3] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_RW_REQ[4] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_RW_REQ[5] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_RW_REQ[6] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_RW_REQ[7] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_RW_REQ[8] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_RW_REQ[9] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_RW_REQ[10] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_RW_REQ[11] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_RW_REQ[12] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_RW_REQ[13] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_RW_REQ[14] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_RW_REQ[15]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_TAG_STALL[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_TAG_STALL[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_TAG_STALL[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_TAG_STALL[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_TAG_STALL[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_TAG_STALL[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_TAG_STALL[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_TAG_STALL[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_TAG_STALL[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_TAG_STALL[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_TAG_STALL[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_TAG_STALL[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_TAG_STALL[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_TAG_STALL[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_TAG_STALL[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_TAG_STALL[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA0_WRREQ_sum TCC_EA0_WRREQ_64B_sum TCC_EA0_WR_UNCACHED_32B_sum TCC_EA0_WRREQ_DRAM_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCC_READ_REQ_sum TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA0_RDREQ_sum TCC_EA0_RDREQ_32B_sum TCC_BUBBLE_sum TCC_EA0_RD_UNCACHED_32B_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_NC_READ_REQ_sum TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA0_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_UC_WRITE_REQ_sum TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA0_ATOMIC_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_CC_ATOMIC_REQ_sum TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA0_RDREQ_LEVEL_sum TCC_EA0_WRREQ_LEVEL_sum TCC_EA0_ATOMIC_LEVEL_sum TCC_EA0_WRREQ_STALL_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ TCP_PENDING_STALL_CYCLES_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel:
@@ -0,0 +1,4 @@
Dispatch_ID,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