Add 'projects/rocprofiler-compute/' from commit 'd2cec001161fc49761bd71a498474a447b1d6975'
git-subtree-dir: projects/rocprofiler-compute git-subtree-mainline:8a4d7262f8git-subtree-split:d2cec00116
This commit is contained in:
systems-assistant[bot]
@@ -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]",2,0,0,1225967,1225967,1048576,256,0,0,8,8,16,64,0x0,0x7f1a76c30ec0,48280,48280,16384,65536,12983,1679996,1410066882102360,1410078545959517,1410078545984317,1410066889784789
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1225967,1225967,1048576,256,0,0,8,8,16,64,0x0,0x7f1a76c30ec0,42583,42583,16384,65536,8224,1048592,1410066889807272,1410078546083997,1410078546102877,1410066890267580
|
||||
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1225967,1225967,1048576,256,0,0,8,8,16,64,0x0,0x7f1a76c30ec0,42228,42228,16384,65536,8413,1048584,1410066890299460,1410078546122717,1410078546141597,1410066890460213
|
||||
|
@@ -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]",2,0,0,1226153,1226153,1048576,256,0,0,8,8,16,64,0x0,0x7feaeff04ec0,0,0,0,1410067370617243,1410078545959517,1410078545984317,1410067378299552
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1226153,1226153,1048576,256,0,0,8,8,16,64,0x0,0x7feaeff04ec0,0,0,0,1410067378319499,1410078546083997,1410078546102877,1410067378620818
|
||||
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1226153,1226153,1048576,256,0,0,8,8,16,64,0x0,0x7feaeff04ec0,0,0,0,1410067378648971,1410078546122717,1410078546141597,1410067378823961
|
||||
|
@@ -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]",2,0,0,1226337,1226337,1048576,256,0,0,8,8,16,64,0x0,0x7f43adec4ec0,65536,216912,27721752,1410067844907387,1410078545959517,1410078545984317,1410067852593644
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1226337,1226337,1048576,256,0,0,8,8,16,64,0x0,0x7f43adec4ec0,65536,174742,22439080,1410067852616707,1410078546083997,1410078546102877,1410067852942802
|
||||
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1226337,1226337,1048576,256,0,0,8,8,16,64,0x0,0x7f43adec4ec0,65536,198278,25317408,1410067852970845,1410078546122717,1410078546141597,1410067853139804
|
||||
|
@@ -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]",2,0,0,1226522,1226522,1048576,256,0,0,8,8,16,64,0x0,0x7fb95f3b0ec0,32768,660786,84583280,1410068324788176,1410078545959517,1410078545984317,1410068332535197
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1226522,1226522,1048576,256,0,0,8,8,16,64,0x0,0x7fb95f3b0ec0,32768,671026,85878140,1410068332555144,1410078546083997,1410078546102877,1410068332853858
|
||||
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1226522,1226522,1048576,256,0,0,8,8,16,64,0x0,0x7fb95f3b0ec0,32768,632212,80916468,1410068332882612,1410078546122717,1410078546141597,1410068333052552
|
||||
|
@@ -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]",2,0,0,1226710,1226710,1048576,256,0,0,8,8,16,64,0x0,0x7efd2e720ec0,49066,49066,17535,392536,16384,25278471,238150,0,101647680,1410068786184713,1410078545959517,1410078545984317,1410068793791259
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1226710,1226710,1048576,256,0,0,8,8,16,64,0x0,0x7efd2e720ec0,42938,42938,13608,343512,16384,24688741,232286,0,99287100,1410068793822348,1410078546083997,1410078546102877,1410068794118977
|
||||
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1226710,1226710,1048576,256,0,0,8,8,16,64,0x0,0x7efd2e720ec0,43314,43314,13851,346520,16384,25149283,234233,0,101130872,1410068794157149,1410078546122717,1410078546141597,1410068794339493
|
||||
|
@@ -0,0 +1,679 @@
|
||||
Omniperf version: 2.0.0-RC1
|
||||
Profiler choice: rocprofv1
|
||||
Path: /home1/josantos/omniperf/tests/workloads/path/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/path/MI100/perfmon/SQ_IFETCH_LEVEL.txt
|
||||
|-> [rocprof] RPL: on '240321_155212' 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/path/MI100/perfmon/SQ_IFETCH_LEVEL.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155212_1225807'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155212_1225807/input0_results_240321_155212'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155212_1225807/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_155212_1225807/input0_results_240321_155212
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/SQ_IFETCH_LEVEL.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/SQ_INST_LEVEL_LDS.txt
|
||||
|-> [rocprof] RPL: on '240321_155213' 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/path/MI100/perfmon/SQ_INST_LEVEL_LDS.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155213_1225993'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155213_1225993/input0_results_240321_155213'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155213_1225993/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_155213_1225993/input0_results_240321_155213
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/SQ_INST_LEVEL_LDS.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt
|
||||
|-> [rocprof] RPL: on '240321_155213' 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/path/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155213_1226177'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155213_1226177/input0_results_240321_155213'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155213_1226177/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_155213_1226177/input0_results_240321_155213
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/SQ_INST_LEVEL_SMEM.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt
|
||||
|-> [rocprof] RPL: on '240321_155214' 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/path/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155214_1226362'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155214_1226362/input0_results_240321_155214'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155214_1226362/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_155214_1226362/input0_results_240321_155214
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/SQ_INST_LEVEL_VMEM.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/SQ_LEVEL_WAVES.txt
|
||||
|-> [rocprof] RPL: on '240321_155214' 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/path/MI100/perfmon/SQ_LEVEL_WAVES.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155214_1226550'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155214_1226550/input0_results_240321_155214'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155214_1226550/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_155214_1226550/input0_results_240321_155214
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/SQ_LEVEL_WAVES.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_0.txt
|
||||
|-> [rocprof] RPL: on '240321_155215' 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/path/MI100/perfmon/pmc_perf_0.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155215_1226735'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155215_1226735/input0_results_240321_155215'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155215_1226735/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_155215_1226735/input0_results_240321_155215
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_0.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_1.txt
|
||||
|-> [rocprof] RPL: on '240321_155215' 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/path/MI100/perfmon/pmc_perf_1.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155215_1226918'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155215_1226918/input0_results_240321_155215'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155215_1226918/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_155215_1226918/input0_results_240321_155215
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_1.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_10.txt
|
||||
|-> [rocprof] RPL: on '240321_155216' 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/path/MI100/perfmon/pmc_perf_10.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155216_1227103'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155216_1227103/input0_results_240321_155216'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155216_1227103/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_155216_1227103/input0_results_240321_155216
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_10.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_11.txt
|
||||
|-> [rocprof] RPL: on '240321_155216' 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/path/MI100/perfmon/pmc_perf_11.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155216_1227289'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155216_1227289/input0_results_240321_155216'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155216_1227289/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_155216_1227289/input0_results_240321_155216
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_11.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_12.txt
|
||||
|-> [rocprof] RPL: on '240321_155217' 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/path/MI100/perfmon/pmc_perf_12.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155217_1227490'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155217_1227490/input0_results_240321_155217'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155217_1227490/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_155217_1227490/input0_results_240321_155217
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_12.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_13.txt
|
||||
|-> [rocprof] RPL: on '240321_155218' 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/path/MI100/perfmon/pmc_perf_13.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155218_1227691'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155218_1227691/input0_results_240321_155218'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155218_1227691/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_155218_1227691/input0_results_240321_155218
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_13.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_14.txt
|
||||
|-> [rocprof] RPL: on '240321_155218' 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/path/MI100/perfmon/pmc_perf_14.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155218_1227878'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155218_1227878/input0_results_240321_155218'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155218_1227878/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_155218_1227878/input0_results_240321_155218
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_14.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_15.txt
|
||||
|-> [rocprof] RPL: on '240321_155219' 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/path/MI100/perfmon/pmc_perf_15.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155219_1228062'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155219_1228062/input0_results_240321_155219'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155219_1228062/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_155219_1228062/input0_results_240321_155219
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_15.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_16.txt
|
||||
|-> [rocprof] RPL: on '240321_155220' 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/path/MI100/perfmon/pmc_perf_16.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155220_1228263'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155220_1228263/input0_results_240321_155220'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155220_1228263/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_155220_1228263/input0_results_240321_155220
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_16.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_2.txt
|
||||
|-> [rocprof] RPL: on '240321_155220' 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/path/MI100/perfmon/pmc_perf_2.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155220_1228465'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155220_1228465/input0_results_240321_155220'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155220_1228465/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_155220_1228465/input0_results_240321_155220
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_2.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_3.txt
|
||||
|-> [rocprof] RPL: on '240321_155221' 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/path/MI100/perfmon/pmc_perf_3.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155221_1228650'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155221_1228650/input0_results_240321_155221'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155221_1228650/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_155221_1228650/input0_results_240321_155221
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_3.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_4.txt
|
||||
|-> [rocprof] RPL: on '240321_155221' 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/path/MI100/perfmon/pmc_perf_4.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155221_1228834'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155221_1228834/input0_results_240321_155221'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155221_1228834/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_155221_1228834/input0_results_240321_155221
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_4.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_5.txt
|
||||
|-> [rocprof] RPL: on '240321_155222' 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/path/MI100/perfmon/pmc_perf_5.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155222_1229018'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155222_1229018/input0_results_240321_155222'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155222_1229018/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_155222_1229018/input0_results_240321_155222
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_5.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_6.txt
|
||||
|-> [rocprof] RPL: on '240321_155222' 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/path/MI100/perfmon/pmc_perf_6.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155222_1229202'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155222_1229202/input0_results_240321_155222'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155222_1229202/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_155222_1229202/input0_results_240321_155222
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_6.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_7.txt
|
||||
|-> [rocprof] RPL: on '240321_155223' 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/path/MI100/perfmon/pmc_perf_7.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155223_1229386'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155223_1229386/input0_results_240321_155223'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155223_1229386/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_155223_1229386/input0_results_240321_155223
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_7.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_8.txt
|
||||
|-> [rocprof] RPL: on '240321_155223' 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/path/MI100/perfmon/pmc_perf_8.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155223_1229572'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155223_1229572/input0_results_240321_155223'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155223_1229572/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_155223_1229572/input0_results_240321_155223
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_8.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_9.txt
|
||||
|-> [rocprof] RPL: on '240321_155224' 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/path/MI100/perfmon/pmc_perf_9.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155224_1229760'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155224_1229760/input0_results_240321_155224'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155224_1229760/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_155224_1229760/input0_results_240321_155224
|
||||
|-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_9.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI100/perfmon/timestamps.txt
|
||||
|-> [rocprof] RPL: on '240321_155224' 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/path/MI100/perfmon/timestamps.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155224_1229944'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155224_1229944/input0_results_240321_155224'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155224_1229944/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_155224_1229944/input0_results_240321_155224
|
||||
|-> [rocprof] File 'tests/workloads/path/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
|
||||
|
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
|
||||
|
@@ -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]",2,0,0,1230104,1230104,1048576,256,0,0,8,8,16,64,0x0,0x7febef7c8ec0,1410078545933634,1410078545959517,1410078545984317,1410078545996272
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1230104,1230104,1048576,256,0,0,8,8,16,64,0x0,0x7febef7c8ec0,1410078545996933,1410078546083997,1410078546102877,1410078546104276
|
||||
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1230104,1230104,1048576,256,0,0,8,8,16,64,0x0,0x7febef7c8ec0,1410078546114776,1410078546122717,1410078546141597,1410078546142898
|
||||
|
@@ -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]",2,0,0,4106060,4106060,1048576,256,0,0,8,0,16,64,0x0,0x7fd0b9184ec0,27003,27003,16384,65536,13592,1540604,1411538900424691,1411551767635712,1411551767656192,1411538916711551
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4106060,4106060,1048576,256,0,0,8,0,16,64,0x0,0x7fd0b9184ec0,41252,41252,16384,65536,9433,1048652,1411538916734635,1411551767749472,1411551767765792,1411538916994887
|
||||
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4106060,4106060,1048576,256,0,0,8,0,16,64,0x0,0x7fd0b9184ec0,40493,40493,16384,65536,9496,1048672,1411538917024403,1411551767786592,1411551767802112,1411538917176591
|
||||
|
@@ -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]",2,0,0,4106253,4106253,1048576,256,0,0,8,0,16,64,0x0,0x7f677cde8ec0,0,0,0,1411539386407497,1411551767635712,1411551767656192,1411539402298088
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4106253,4106253,1048576,256,0,0,8,0,16,64,0x0,0x7f677cde8ec0,0,0,0,1411539402313307,1411551767749472,1411551767765792,1411539402615388
|
||||
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4106253,4106253,1048576,256,0,0,8,0,16,64,0x0,0x7f677cde8ec0,0,0,0,1411539402642058,1411551767786592,1411551767802112,1411539402793835
|
||||
|
@@ -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]",2,0,0,4106436,4106436,1048576,256,0,0,8,0,16,64,0x0,0x7f5bb2338ec0,65536,172104,19399360,1411539868015720,1411551767635712,1411551767656192,1411539884298563
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4106436,4106436,1048576,256,0,0,8,0,16,64,0x0,0x7f5bb2338ec0,65536,225136,25260328,1411539884315856,1411551767749472,1411551767765792,1411539884617747
|
||||
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4106436,4106436,1048576,256,0,0,8,0,16,64,0x0,0x7f5bb2338ec0,65536,237466,26615144,1411539884643485,1411551767786592,1411551767802112,1411539884796224
|
||||
|
@@ -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]",2,0,0,4106628,4106628,1048576,256,0,0,8,0,16,64,0x0,0x7f187a930ec0,32768,296920,33259784,1411540349957093,1411551767635712,1411551767656192,1411540365771640
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4106628,4106628,1048576,256,0,0,8,0,16,64,0x0,0x7f187a930ec0,32768,589718,66068516,1411540365791388,1411551767749472,1411551767765792,1411540366061018
|
||||
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4106628,4106628,1048576,256,0,0,8,0,16,64,0x0,0x7f187a930ec0,32768,602871,67508252,1411540366087468,1411551767786592,1411551767802112,1411540366250446
|
||||
|
@@ -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]",2,0,0,4106830,4106830,1048576,256,0,0,8,0,16,64,0x0,0x7f0003c04ec0,27964,27964,11091,223720,16384,11075620,130670,0,44799316,1411540838121846,1411551767635712,1411551767656192,1411540853905555
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4106830,4106830,1048576,256,0,0,8,0,16,64,0x0,0x7f0003c04ec0,40878,40878,12739,327032,16384,19248292,223753,0,77475332,1411540853935701,1411551767749472,1411551767765792,1411540854159996
|
||||
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4106830,4106830,1048576,256,0,0,8,0,16,64,0x0,0x7f0003c04ec0,40812,40812,13091,326504,16384,19800227,224876,0,79703012,1411540854195663,1411551767786592,1411551767802112,1411540854346158
|
||||
|
@@ -0,0 +1,739 @@
|
||||
Omniperf version: 2.0.0-RC1
|
||||
Profiler choice: rocprofv1
|
||||
Path: /home1/josantos/omniperf/tests/workloads/path/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/path/MI200/perfmon/SQ_IFETCH_LEVEL.txt
|
||||
|-> [rocprof] RPL: on '240321_161646' 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/path/MI200/perfmon/SQ_IFETCH_LEVEL.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161646_4105900'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161646_4105900/input0_results_240321_161646'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161646_4105900/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_161646_4105900/input0_results_240321_161646
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/SQ_IFETCH_LEVEL.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_LDS.txt
|
||||
|-> [rocprof] RPL: on '240321_161647' 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/path/MI200/perfmon/SQ_INST_LEVEL_LDS.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161647_4106093'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161647_4106093/input0_results_240321_161647'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161647_4106093/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_161647_4106093/input0_results_240321_161647
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/SQ_INST_LEVEL_LDS.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt
|
||||
|-> [rocprof] RPL: on '240321_161647' 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/path/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161647_4106276'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161647_4106276/input0_results_240321_161647'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161647_4106276/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_161647_4106276/input0_results_240321_161647
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/SQ_INST_LEVEL_SMEM.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt
|
||||
|-> [rocprof] RPL: on '240321_161648' 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/path/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161648_4106468'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161648_4106468/input0_results_240321_161648'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161648_4106468/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_161648_4106468/input0_results_240321_161648
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/SQ_INST_LEVEL_VMEM.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/SQ_LEVEL_WAVES.txt
|
||||
|-> [rocprof] RPL: on '240321_161648' 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/path/MI200/perfmon/SQ_LEVEL_WAVES.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161648_4106670'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161648_4106670/input0_results_240321_161648'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161648_4106670/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_161648_4106670/input0_results_240321_161648
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/SQ_LEVEL_WAVES.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_0.txt
|
||||
|-> [rocprof] RPL: on '240321_161649' 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/path/MI200/perfmon/pmc_perf_0.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161649_4106855'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161649_4106855/input0_results_240321_161649'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161649_4106855/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_161649_4106855/input0_results_240321_161649
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_0.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_1.txt
|
||||
|-> [rocprof] RPL: on '240321_161649' 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/path/MI200/perfmon/pmc_perf_1.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161649_4107038'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161649_4107038/input0_results_240321_161649'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161649_4107038/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_161649_4107038/input0_results_240321_161649
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_1.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_10.txt
|
||||
|-> [rocprof] RPL: on '240321_161650' 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/path/MI200/perfmon/pmc_perf_10.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161650_4107221'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161650_4107221/input0_results_240321_161650'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161650_4107221/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_161650_4107221/input0_results_240321_161650
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_10.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_11.txt
|
||||
|-> [rocprof] RPL: on '240321_161650' 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/path/MI200/perfmon/pmc_perf_11.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161650_4107404'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161650_4107404/input0_results_240321_161650'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161650_4107404/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_161650_4107404/input0_results_240321_161650
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_11.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_12.txt
|
||||
|-> [rocprof] RPL: on '240321_161651' 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/path/MI200/perfmon/pmc_perf_12.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161651_4107588'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161651_4107588/input0_results_240321_161651'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161651_4107588/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_161651_4107588/input0_results_240321_161651
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_12.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_13.txt
|
||||
|-> [rocprof] RPL: on '240321_161651' 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/path/MI200/perfmon/pmc_perf_13.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161651_4107786'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161651_4107786/input0_results_240321_161651'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161651_4107786/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_161651_4107786/input0_results_240321_161651
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_13.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_14.txt
|
||||
|-> [rocprof] RPL: on '240321_161652' 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/path/MI200/perfmon/pmc_perf_14.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161652_4107970'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161652_4107970/input0_results_240321_161652'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161652_4107970/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_161652_4107970/input0_results_240321_161652
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_14.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_15.txt
|
||||
|-> [rocprof] RPL: on '240321_161652' 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/path/MI200/perfmon/pmc_perf_15.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161652_4108161'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161652_4108161/input0_results_240321_161652'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161652_4108161/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_161652_4108161/input0_results_240321_161652
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_15.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_16.txt
|
||||
|-> [rocprof] RPL: on '240321_161653' 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/path/MI200/perfmon/pmc_perf_16.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161653_4108344'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161653_4108344/input0_results_240321_161653'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161653_4108344/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_161653_4108344/input0_results_240321_161653
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_16.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_17.txt
|
||||
|-> [rocprof] RPL: on '240321_161654' 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/path/MI200/perfmon/pmc_perf_17.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161654_4108547'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161654_4108547/input0_results_240321_161654'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161654_4108547/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_161654_4108547/input0_results_240321_161654
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_17.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_18.txt
|
||||
|-> [rocprof] RPL: on '240321_161655' 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/path/MI200/perfmon/pmc_perf_18.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161655_4108730'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161655_4108730/input0_results_240321_161655'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161655_4108730/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_161655_4108730/input0_results_240321_161655
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_18.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_2.txt
|
||||
|-> [rocprof] RPL: on '240321_161655' 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/path/MI200/perfmon/pmc_perf_2.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161655_4108920'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161655_4108920/input0_results_240321_161655'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161655_4108920/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_161655_4108920/input0_results_240321_161655
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_2.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_3.txt
|
||||
|-> [rocprof] RPL: on '240321_161656' 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/path/MI200/perfmon/pmc_perf_3.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161656_4109119'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161656_4109119/input0_results_240321_161656'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161656_4109119/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_161656_4109119/input0_results_240321_161656
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_3.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_4.txt
|
||||
|-> [rocprof] RPL: on '240321_161656' 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/path/MI200/perfmon/pmc_perf_4.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161656_4109302'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161656_4109302/input0_results_240321_161656'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161656_4109302/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_161656_4109302/input0_results_240321_161656
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_4.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_5.txt
|
||||
|-> [rocprof] RPL: on '240321_161657' 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/path/MI200/perfmon/pmc_perf_5.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161657_4109485'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161657_4109485/input0_results_240321_161657'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161657_4109485/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_161657_4109485/input0_results_240321_161657
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_5.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_6.txt
|
||||
|-> [rocprof] RPL: on '240321_161657' 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/path/MI200/perfmon/pmc_perf_6.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161657_4109668'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161657_4109668/input0_results_240321_161657'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161657_4109668/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_161657_4109668/input0_results_240321_161657
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_6.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_7.txt
|
||||
|-> [rocprof] RPL: on '240321_161658' 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/path/MI200/perfmon/pmc_perf_7.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161658_4109851'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161658_4109851/input0_results_240321_161658'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161658_4109851/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_161658_4109851/input0_results_240321_161658
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_7.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_8.txt
|
||||
|-> [rocprof] RPL: on '240321_161658' 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/path/MI200/perfmon/pmc_perf_8.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161658_4110053'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161658_4110053/input0_results_240321_161658'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161658_4110053/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_161658_4110053/input0_results_240321_161658
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_8.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_9.txt
|
||||
|-> [rocprof] RPL: on '240321_161659' 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/path/MI200/perfmon/pmc_perf_9.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161659_4110244'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161659_4110244/input0_results_240321_161659'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161659_4110244/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_161659_4110244/input0_results_240321_161659
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_9.csv' is generating
|
||||
|-> [rocprof]
|
||||
[profiling] Current input file: tests/workloads/path/MI200/perfmon/timestamps.txt
|
||||
|-> [rocprof] RPL: on '240321_161659' 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/path/MI200/perfmon/timestamps.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161659_4110431'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161659_4110431/input0_results_240321_161659'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161659_4110431/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_161659_4110431/input0_results_240321_161659
|
||||
|-> [rocprof] File 'tests/workloads/path/MI200/timestamps.csv' is generating
|
||||
|-> [rocprof]
|
||||
[roofline] Checking for roofline.csv in tests/workloads/path/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
|
||||
|
File diff suppressed because one or more lines are too long
@@ -0,0 +1,5 @@
|
||||
device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh
|
||||
0,1388.9302,1388.3835,1389.4768,5018.2891,5015.416,5021.1621,9226.7266,9226.168,9227.2852,17717.834,17714.895,17720.773,20941.971,20881.785,21002.156,20272.537,20271.938,20273.137,170483.16,170480.25,170486.06,164938.17,164933.98,164942.36,41438.68,41438.27,41439.09,41497.562,41496.836,41498.289,166402.27,165911.17,166893.36
|
||||
1,1389.3043,1388.6895,1389.9192,5029.6997,5027.6914,5031.708,9239.2627,9238.5391,9239.9863,18243.783,18241.363,18246.203,20985.506,20918.434,21052.578,20301.832,20301.094,20302.57,170928.06,170923.66,170932.47,165162.06,165158.09,165166.03,41494.691,41493.625,41495.758,41550.176,41549.141,41551.211,166923.81,166920.55,166927.08
|
||||
2,1389.0227,1388.4105,1389.6349,5036.6968,5034.5093,5038.8843,9263.2725,9262.6641,9263.8809,18220.432,18219.43,18221.434,21053.373,21052.924,21053.822,20354.846,20354.256,20355.436,171150.41,171147,171153.81,165537.12,165534.03,165540.22,41587.383,41586.57,41588.195,41645.191,41644.094,41646.289,166970.84,166374.36,167567.33
|
||||
3,1389.0236,1388.4886,1389.5585,5033.541,5031.9014,5035.1807,9237.8057,9237.0996,9238.5117,18326.717,18325.787,18327.646,21032.83,21032.598,21033.062,20308.371,20307.881,20308.861,171040.98,171036.05,171045.92,165174.33,165170.09,165178.56,41430.328,41276.879,41583.777,41578.465,41577.258,41579.672,166994.86,166991.23,166998.48
|
||||
|
@@ -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
|
||||
|
@@ -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]",2,0,0,4110591,4110591,1048576,256,0,0,8,0,16,64,0x0,0x7fc6de634ec0,1411551767610475,1411551767635712,1411551767656192,1411551767669456
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4110591,4110591,1048576,256,0,0,8,0,16,64,0x0,0x7fc6de634ec0,1411551767667252,1411551767749472,1411551767765792,1411551767767061
|
||||
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4110591,4110591,1048576,256,0,0,8,0,16,64,0x0,0x7fc6de634ec0,1411551767776669,1411551767786592,1411551767802112,1411551767803299
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES
|
||||
0,11995,1,144666,144666,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673339483,73517673347095,0,205430.0,205430.0,16384.0,65536.0,26688.0,2149344.0
|
||||
1,11995,1,144666,144666,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673385473,73517673391482,0,178672.0,178672.0,16384.0,65536.0,13299.0,1048656.0
|
||||
2,11995,1,144666,144666,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673363600,73517673369970,0,165003.0,165003.0,16384.0,65536.0,13060.0,1049392.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES
|
||||
0,11995,1,144677,144677,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673339483,73517673347095,0,0.0,0.0,0.0
|
||||
1,11995,1,144677,144677,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673385473,73517673391482,0,0.0,0.0,0.0
|
||||
2,11995,1,144677,144677,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673363600,73517673369970,0,0.0,0.0,0.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES
|
||||
0,11995,1,144688,144688,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673339483,73517673347095,0,65536.0,340786.0,27207344.0
|
||||
1,11995,1,144688,144688,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673385473,73517673391482,0,65536.0,277970.0,22234008.0
|
||||
2,11995,1,144688,144688,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673363600,73517673369970,0,65536.0,215822.0,17342904.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES
|
||||
0,11995,1,144699,144699,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673339483,73517673347095,0,32768.0,534566.0,42752356.0
|
||||
1,11995,1,144699,144699,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673385473,73517673391482,0,32768.0,415032.0,33195988.0
|
||||
2,11995,1,144699,144699,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673363600,73517673369970,0,32768.0,408920.0,32710300.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES
|
||||
0,11995,1,144710,144710,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673339483,73517673347095,0,203242.0,203242.0,108439.0,812968.0,16384.0,13784518.0,249142.0,0.0,55564396.0
|
||||
1,11995,1,144710,144710,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673385473,73517673391482,0,169171.0,169171.0,90620.0,676684.0,16384.0,10365368.0,191706.0,0.0,41854316.0
|
||||
2,11995,1,144710,144710,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73517673363600,73517673369970,0,171791.0,171791.0,90307.0,687164.0,16384.0,10363168.0,193033.0,0.0,41847616.0
|
||||
|
@@ -0,0 +1,229 @@
|
||||
Omniperf version: 2.0.0
|
||||
Profiler choice: rocprofv2
|
||||
Path: /home/colramos/omniperf/tests/workloads/path/MI300A_A1
|
||||
Target: MI300A_A1
|
||||
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
|
||||
Kernel Selection: None
|
||||
Dispatch Selection: None
|
||||
Hardware Blocks: All
|
||||
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
Collecting Performance Counters
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/SQ_IFETCH_LEVEL.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - GRBM_COUNT
|
||||
|-> [/opt/rocm/bin/rocprofv2] - GRBM_GUI_ACTIVE
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/SQ_INST_LEVEL_LDS.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_LDS
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/SQ_INST_LEVEL_SMEM.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_SMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|
||||
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|
||||
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/SQ_INST_LEVEL_VMEM.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_VMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|
||||
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|
||||
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/SQ_LEVEL_WAVES.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - GRBM_COUNT
|
||||
|-> [/opt/rocm/bin/rocprofv2] - GRBM_GUI_ACTIVE
|
||||
|-> [/opt/rocm/bin/rocprofv2] - CPC_ME1_BUSY_FOR_PACKET_DECODE
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_CYCLES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVE_CYCLES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CYCLES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_LEVEL_WAVES
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_0.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_CYCLES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CYCLES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CU_CYCLES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVE_CYCLES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_CVT
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM_WR
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM_RD
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_1.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SALU
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VSKIPPED
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F16
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F16
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F16
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_10.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_ATOMIC_REQ
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_STALL
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_REQ
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_11.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_INPUT_VALID_READYB
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_ATOMIC
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_8
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_HITS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_MISSES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_MISSES_DUPLICATE
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_1
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_12.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_2
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_4
|
||||
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_13.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_ATOMIC[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_BUBBLE[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_CYCLE[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_ATOMIC[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_BUBBLE[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_CYCLE[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC[1]
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_14.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[3]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[3]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[3]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[3]
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_15.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[0]
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_16.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[2]
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_17.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_TOO_MANY_EA_WRREQS_STALL[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_WRITE[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_TOO_MANY_EA_WRREQS_STALL[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_WRITE[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[2]
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_2.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F16
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F64
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_3.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_FLAT
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_GDS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_EXP_GDS
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_4.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_BRANCH
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SENDMSG
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAIT_ANY
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAIT_INST_ANY
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_ANY
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_VMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_LDS
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_5.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_SCA
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_EXP_GDS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_MISC
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_FLAT
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_VMEM_WR
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_VMEM_RD
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_SMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_SALU
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCP_TCC_READ_REQ_sum
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_6.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_THREAD_CYCLES_VALU
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_BANK_CONFLICT
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_7.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_16
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ITEMS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_MEM_VIOLATIONS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_ATOMIC_RETURN
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_IDX_ACTIVE
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_RESTORED
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_8.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM_NORM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_MFMA
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_I8
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/pmc_perf_9.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_I8
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F16
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_BF16
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_INST_REQ
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_READ_REQ
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_WRITE_REQ
|
||||
[profiling] Current input file: tests/workloads/path/MI300A_A1/perfmon/timestamps.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|
||||
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
||||
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|
||||
[roofline] Roofline temporarily disabled in MI300
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
+5
@@ -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
|
||||
|
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user