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 +1,2 @@
|
||||
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
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1242050,1242050,1048576,256,0,0,8,8,16,64,0x0,0x7fc6f4208ec0,38821,38821,16384,65536,8109,1048656,1410114557095333,1410127432590948,1410127432609509,1410114564821895
|
||||
|
@@ -0,0 +1,2 @@
|
||||
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
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1242238,1242238,1048576,256,0,0,8,8,16,64,0x0,0x7fe8146b0ec0,0,0,0,1410115049761835,1410127432590948,1410127432609509,1410115057489720
|
||||
|
@@ -0,0 +1,2 @@
|
||||
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
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1242423,1242423,1048576,256,0,0,8,8,16,64,0x0,0x7f6929238ec0,65536,91980,11724504,1410115535741786,1410127432590948,1410127432609509,1410115543260466
|
||||
|
@@ -0,0 +1,2 @@
|
||||
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
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1242619,1242619,1048576,256,0,0,8,8,16,64,0x0,0x7fc33f83cec0,32768,653996,83707028,1410116022813727,1410127432590948,1410127432609509,1410116030517617
|
||||
|
@@ -0,0 +1,2 @@
|
||||
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
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1242805,1242805,1048576,256,0,0,8,8,16,64,0x0,0x7fcc21518ec0,38554,38554,11832,308440,16384,22714635,211906,0,91397252,1410116516938870,1410127432590948,1410127432609509,1410116524589600
|
||||
|
@@ -0,0 +1,702 @@
|
||||
Omniperf version: 2.0.0-RC1
|
||||
Profiler choice: rocprofv1
|
||||
Path: /home1/josantos/omniperf/tests/workloads/dispatch_2/MI100
|
||||
Target: MI100
|
||||
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
|
||||
Kernel Selection: None
|
||||
Dispatch Selection: ['1']
|
||||
IP Blocks: All
|
||||
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
Collecting Performance Counters
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/SQ_IFETCH_LEVEL.txt
|
||||
|-> [rocprof] RPL: on '240321_155300' 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/dispatch_2/MI100/perfmon/SQ_IFETCH_LEVEL.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155300_1241890'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155300_1241890/input0_results_240321_155300'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155300_1241890/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155300_1241890/input0_results_240321_155300
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/SQ_IFETCH_LEVEL.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/SQ_INST_LEVEL_LDS.txt
|
||||
|-> [rocprof] RPL: on '240321_155301' 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/dispatch_2/MI100/perfmon/SQ_INST_LEVEL_LDS.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155301_1242075'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155301_1242075/input0_results_240321_155301'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155301_1242075/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155301_1242075/input0_results_240321_155301
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_LDS.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt
|
||||
|-> [rocprof] RPL: on '240321_155301' 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/dispatch_2/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155301_1242263'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155301_1242263/input0_results_240321_155301'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155301_1242263/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155301_1242263/input0_results_240321_155301
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_SMEM.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt
|
||||
|-> [rocprof] RPL: on '240321_155302' 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/dispatch_2/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155302_1242459'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155302_1242459/input0_results_240321_155302'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155302_1242459/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155302_1242459/input0_results_240321_155302
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_VMEM.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/SQ_LEVEL_WAVES.txt
|
||||
|-> [rocprof] RPL: on '240321_155302' 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/dispatch_2/MI100/perfmon/SQ_LEVEL_WAVES.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155302_1242645'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155302_1242645/input0_results_240321_155302'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155302_1242645/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155302_1242645/input0_results_240321_155302
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/SQ_LEVEL_WAVES.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_0.txt
|
||||
|-> [rocprof] RPL: on '240321_155303' 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/dispatch_2/MI100/perfmon/pmc_perf_0.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155303_1242829'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155303_1242829/input0_results_240321_155303'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155303_1242829/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155303_1242829/input0_results_240321_155303
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_0.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_1.txt
|
||||
|-> [rocprof] RPL: on '240321_155303' 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/dispatch_2/MI100/perfmon/pmc_perf_1.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155303_1243015'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155303_1243015/input0_results_240321_155303'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155303_1243015/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155303_1243015/input0_results_240321_155303
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_1.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_10.txt
|
||||
|-> [rocprof] RPL: on '240321_155303' 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/dispatch_2/MI100/perfmon/pmc_perf_10.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155303_1243202'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155303_1243202/input0_results_240321_155303'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155303_1243202/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155303_1243202/input0_results_240321_155303
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_10.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_11.txt
|
||||
|-> [rocprof] RPL: on '240321_155304' 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/dispatch_2/MI100/perfmon/pmc_perf_11.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155304_1243388'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155304_1243388/input0_results_240321_155304'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155304_1243388/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155304_1243388/input0_results_240321_155304
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_11.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_12.txt
|
||||
|-> [rocprof] RPL: on '240321_155305' 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/dispatch_2/MI100/perfmon/pmc_perf_12.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155305_1243574'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155305_1243574/input0_results_240321_155305'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155305_1243574/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155305_1243574/input0_results_240321_155305
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_12.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_13.txt
|
||||
|-> [rocprof] RPL: on '240321_155305' 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/dispatch_2/MI100/perfmon/pmc_perf_13.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155305_1243760'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155305_1243760/input0_results_240321_155305'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155305_1243760/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155305_1243760/input0_results_240321_155305
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_13.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_14.txt
|
||||
|-> [rocprof] RPL: on '240321_155306' 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/dispatch_2/MI100/perfmon/pmc_perf_14.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155306_1243945'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155306_1243945/input0_results_240321_155306'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155306_1243945/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155306_1243945/input0_results_240321_155306
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_14.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_15.txt
|
||||
|-> [rocprof] RPL: on '240321_155307' 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/dispatch_2/MI100/perfmon/pmc_perf_15.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155307_1244129'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155307_1244129/input0_results_240321_155307'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155307_1244129/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155307_1244129/input0_results_240321_155307
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_15.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_16.txt
|
||||
|-> [rocprof] RPL: on '240321_155307' 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/dispatch_2/MI100/perfmon/pmc_perf_16.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155307_1244317'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155307_1244317/input0_results_240321_155307'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155307_1244317/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155307_1244317/input0_results_240321_155307
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_16.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_2.txt
|
||||
|-> [rocprof] RPL: on '240321_155308' 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/dispatch_2/MI100/perfmon/pmc_perf_2.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155308_1244502'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155308_1244502/input0_results_240321_155308'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155308_1244502/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155308_1244502/input0_results_240321_155308
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_2.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_3.txt
|
||||
|-> [rocprof] RPL: on '240321_155308' 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/dispatch_2/MI100/perfmon/pmc_perf_3.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155308_1244689'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155308_1244689/input0_results_240321_155308'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155308_1244689/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155308_1244689/input0_results_240321_155308
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_3.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_4.txt
|
||||
|-> [rocprof] RPL: on '240321_155309' 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/dispatch_2/MI100/perfmon/pmc_perf_4.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155309_1244875'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155309_1244875/input0_results_240321_155309'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155309_1244875/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155309_1244875/input0_results_240321_155309
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_4.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_5.txt
|
||||
|-> [rocprof] RPL: on '240321_155309' 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/dispatch_2/MI100/perfmon/pmc_perf_5.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155309_1245063'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155309_1245063/input0_results_240321_155309'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155309_1245063/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155309_1245063/input0_results_240321_155309
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_5.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_6.txt
|
||||
|-> [rocprof] RPL: on '240321_155310' 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/dispatch_2/MI100/perfmon/pmc_perf_6.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155310_1245250'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155310_1245250/input0_results_240321_155310'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155310_1245250/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155310_1245250/input0_results_240321_155310
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_6.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_7.txt
|
||||
|-> [rocprof] RPL: on '240321_155310' 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/dispatch_2/MI100/perfmon/pmc_perf_7.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155310_1245437'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155310_1245437/input0_results_240321_155310'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155310_1245437/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155310_1245437/input0_results_240321_155310
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_7.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_8.txt
|
||||
|-> [rocprof] RPL: on '240321_155311' 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/dispatch_2/MI100/perfmon/pmc_perf_8.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155311_1245623'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155311_1245623/input0_results_240321_155311'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155311_1245623/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155311_1245623/input0_results_240321_155311
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_8.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_9.txt
|
||||
|-> [rocprof] RPL: on '240321_155312' 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/dispatch_2/MI100/perfmon/pmc_perf_9.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155312_1245809'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155312_1245809/input0_results_240321_155312'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155312_1245809/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155312_1245809/input0_results_240321_155312
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_9.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/timestamps.txt
|
||||
|-> [rocprof] RPL: on '240321_155313' 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/dispatch_2/MI100/perfmon/timestamps.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155313_1245995'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155313_1245995/input0_results_240321_155313'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155313_1245995/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_155313_1245995/input0_results_240321_155313
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI100/timestamps.csv' is generating
|
||||
|-> [rocprof]
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_EA_ATOMIC_LEVEL_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc:
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID
|
||||
1,"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 +1,2 @@
|
||||
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
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1246155,1246155,1048576,256,0,0,8,8,16,64,0x0,0x7fd9c2848ec0,1410127432560491,1410127432590948,1410127432609509,1410127432620744
|
||||
|
@@ -0,0 +1,2 @@
|
||||
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
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4124736,4124736,1048576,256,0,0,8,0,16,64,0x0,0x7f7cc2578ec0,22637,22637,16384,65536,9404,1048700,1411868153949415,1411881076677985,1411881076693505,1411868170088366
|
||||
|
@@ -0,0 +1,2 @@
|
||||
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
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4124923,4124923,1048576,256,0,0,8,0,16,64,0x0,0x7f10f6d40ec0,0,0,0,1411868641572741,1411881076677985,1411881076693505,1411868657447011
|
||||
|
@@ -0,0 +1,2 @@
|
||||
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
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4125108,4125108,1048576,256,0,0,8,0,16,64,0x0,0x7fe12a7b0ec0,65536,76600,8662264,1411869123353968,1411881076677985,1411881076693505,1411869139369646
|
||||
|
@@ -0,0 +1,2 @@
|
||||
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
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4125292,4125292,1048576,256,0,0,8,0,16,64,0x0,0x7f4afb100ec0,32768,274852,30773868,1411869608729593,1411881076677985,1411881076693505,1411869624857423
|
||||
|
@@ -0,0 +1,2 @@
|
||||
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
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4125494,4125494,1048576,256,0,0,8,0,16,64,0x0,0x7fb3c4250ec0,23066,23066,8572,184536,16384,9116494,112642,0,36968384,1411870091555386,1411881076677985,1411881076693505,1411870107458090
|
||||
|
@@ -0,0 +1,764 @@
|
||||
Omniperf version: 2.0.0-RC1
|
||||
Profiler choice: rocprofv1
|
||||
Path: /home1/josantos/omniperf/tests/workloads/dispatch_2/MI200
|
||||
Target: MI200
|
||||
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
|
||||
Kernel Selection: None
|
||||
Dispatch Selection: ['1']
|
||||
IP Blocks: All
|
||||
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
Collecting Performance Counters
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/SQ_IFETCH_LEVEL.txt
|
||||
|-> [rocprof] RPL: on '240321_162215' 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/dispatch_2/MI200/perfmon/SQ_IFETCH_LEVEL.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162215_4124576'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162215_4124576/input0_results_240321_162215'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162215_4124576/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162215_4124576/input0_results_240321_162215
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/SQ_IFETCH_LEVEL.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_LDS.txt
|
||||
|-> [rocprof] RPL: on '240321_162216' 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/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_LDS.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162216_4124763'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162216_4124763/input0_results_240321_162216'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162216_4124763/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162216_4124763/input0_results_240321_162216
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_LDS.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt
|
||||
|-> [rocprof] RPL: on '240321_162216' 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/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162216_4124948'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162216_4124948/input0_results_240321_162216'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162216_4124948/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162216_4124948/input0_results_240321_162216
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_SMEM.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt
|
||||
|-> [rocprof] RPL: on '240321_162217' 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/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162217_4125132'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162217_4125132/input0_results_240321_162217'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162217_4125132/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162217_4125132/input0_results_240321_162217
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_VMEM.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/SQ_LEVEL_WAVES.txt
|
||||
|-> [rocprof] RPL: on '240321_162217' 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/dispatch_2/MI200/perfmon/SQ_LEVEL_WAVES.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162217_4125334'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162217_4125334/input0_results_240321_162217'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162217_4125334/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162217_4125334/input0_results_240321_162217
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/SQ_LEVEL_WAVES.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_0.txt
|
||||
|-> [rocprof] RPL: on '240321_162218' 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/dispatch_2/MI200/perfmon/pmc_perf_0.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162218_4125536'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162218_4125536/input0_results_240321_162218'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162218_4125536/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162218_4125536/input0_results_240321_162218
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_0.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_1.txt
|
||||
|-> [rocprof] RPL: on '240321_162218' 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/dispatch_2/MI200/perfmon/pmc_perf_1.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162218_4125738'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162218_4125738/input0_results_240321_162218'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162218_4125738/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162218_4125738/input0_results_240321_162218
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_1.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_10.txt
|
||||
|-> [rocprof] RPL: on '240321_162219' 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/dispatch_2/MI200/perfmon/pmc_perf_10.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162219_4125942'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162219_4125942/input0_results_240321_162219'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162219_4125942/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162219_4125942/input0_results_240321_162219
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_10.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_11.txt
|
||||
|-> [rocprof] RPL: on '240321_162219' 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/dispatch_2/MI200/perfmon/pmc_perf_11.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162219_4126127'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162219_4126127/input0_results_240321_162219'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162219_4126127/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162219_4126127/input0_results_240321_162219
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_11.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_12.txt
|
||||
|-> [rocprof] RPL: on '240321_162220' 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/dispatch_2/MI200/perfmon/pmc_perf_12.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162220_4126312'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162220_4126312/input0_results_240321_162220'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162220_4126312/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162220_4126312/input0_results_240321_162220
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_12.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_13.txt
|
||||
|-> [rocprof] RPL: on '240321_162220' 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/dispatch_2/MI200/perfmon/pmc_perf_13.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162220_4126497'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162220_4126497/input0_results_240321_162220'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162220_4126497/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162220_4126497/input0_results_240321_162220
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_13.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_14.txt
|
||||
|-> [rocprof] RPL: on '240321_162221' 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/dispatch_2/MI200/perfmon/pmc_perf_14.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162221_4126699'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162221_4126699/input0_results_240321_162221'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162221_4126699/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162221_4126699/input0_results_240321_162221
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_14.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_15.txt
|
||||
|-> [rocprof] RPL: on '240321_162222' 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/dispatch_2/MI200/perfmon/pmc_perf_15.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162222_4126886'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162222_4126886/input0_results_240321_162222'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162222_4126886/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162222_4126886/input0_results_240321_162222
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_15.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_16.txt
|
||||
|-> [rocprof] RPL: on '240321_162222' 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/dispatch_2/MI200/perfmon/pmc_perf_16.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162222_4127088'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162222_4127088/input0_results_240321_162222'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162222_4127088/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162222_4127088/input0_results_240321_162222
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_16.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_17.txt
|
||||
|-> [rocprof] RPL: on '240321_162223' 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/dispatch_2/MI200/perfmon/pmc_perf_17.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162223_4127273'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162223_4127273/input0_results_240321_162223'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162223_4127273/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162223_4127273/input0_results_240321_162223
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_17.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_18.txt
|
||||
|-> [rocprof] RPL: on '240321_162224' 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/dispatch_2/MI200/perfmon/pmc_perf_18.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162224_4127460'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162224_4127460/input0_results_240321_162224'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162224_4127460/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162224_4127460/input0_results_240321_162224
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_18.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_2.txt
|
||||
|-> [rocprof] RPL: on '240321_162224' 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/dispatch_2/MI200/perfmon/pmc_perf_2.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162224_4127646'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162224_4127646/input0_results_240321_162224'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162224_4127646/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162224_4127646/input0_results_240321_162224
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_2.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_3.txt
|
||||
|-> [rocprof] RPL: on '240321_162225' 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/dispatch_2/MI200/perfmon/pmc_perf_3.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162225_4127830'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162225_4127830/input0_results_240321_162225'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162225_4127830/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162225_4127830/input0_results_240321_162225
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_3.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_4.txt
|
||||
|-> [rocprof] RPL: on '240321_162225' 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/dispatch_2/MI200/perfmon/pmc_perf_4.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162225_4128014'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162225_4128014/input0_results_240321_162225'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162225_4128014/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162225_4128014/input0_results_240321_162225
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_4.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_5.txt
|
||||
|-> [rocprof] RPL: on '240321_162226' 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/dispatch_2/MI200/perfmon/pmc_perf_5.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162226_4128201'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162226_4128201/input0_results_240321_162226'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162226_4128201/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162226_4128201/input0_results_240321_162226
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_5.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_6.txt
|
||||
|-> [rocprof] RPL: on '240321_162226' 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/dispatch_2/MI200/perfmon/pmc_perf_6.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162226_4128388'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162226_4128388/input0_results_240321_162226'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162226_4128388/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162226_4128388/input0_results_240321_162226
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_6.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_7.txt
|
||||
|-> [rocprof] RPL: on '240321_162227' 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/dispatch_2/MI200/perfmon/pmc_perf_7.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162227_4128575'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162227_4128575/input0_results_240321_162227'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162227_4128575/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162227_4128575/input0_results_240321_162227
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_7.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_8.txt
|
||||
|-> [rocprof] RPL: on '240321_162227' 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/dispatch_2/MI200/perfmon/pmc_perf_8.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162227_4128777'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162227_4128777/input0_results_240321_162227'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162227_4128777/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162227_4128777/input0_results_240321_162227
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_8.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_9.txt
|
||||
|-> [rocprof] RPL: on '240321_162228' 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/dispatch_2/MI200/perfmon/pmc_perf_9.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162228_4128961'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162228_4128961/input0_results_240321_162228'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162228_4128961/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162228_4128961/input0_results_240321_162228
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_9.csv' is generating
|
||||
|-> [rocprof]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/timestamps.txt
|
||||
|-> [rocprof] RPL: on '240321_162228' 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/dispatch_2/MI200/perfmon/timestamps.txt'
|
||||
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162228_4129150'
|
||||
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162228_4129150/input0_results_240321_162228'
|
||||
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162228_4129150/input0.xml"
|
||||
|-> [rocprof] gpu_index =
|
||||
|-> [rocprof] kernel =
|
||||
|-> [rocprof] range = 1
|
||||
|-> [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: 1 contexts collected, output directory /tmp/rpl_data_240321_162228_4129150/input0_results_240321_162228
|
||||
|-> [rocprof] File 'tests/workloads/dispatch_2/MI200/timestamps.csv' is generating
|
||||
|-> [rocprof]
|
||||
[roofline] Checking for roofline.csv in tests/workloads/dispatch_2/MI200
|
||||
[roofline] No roofline data found. Generating...
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
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: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc:
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID
|
||||
1,"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
|
||||
0,1388.9821,1388.3459,1389.6182,5017.0518,5014.043,5020.0605,9225.3008,9224.6426,9225.959,17712.033,17708.768,17715.299,20941.537,20881.26,21001.814,20271.555,20270.965,20272.145,170485.56,170481.81,170489.31,164931.84,164927.7,164935.98,41439.031,41438.484,41439.578,41494.887,41494.223,41495.551,166397.41,165908.08,166886.73
|
||||
1,1389.0138,1388.5118,1389.5157,5029.3579,5027.1226,5031.5933,9236.9922,9236.375,9237.6094,18238.225,18236.686,18239.764,20985.932,20919.07,21052.793,20303.445,20302.893,20303.998,170925.2,170920.75,170929.66,165159.62,165154.52,165164.73,41500.129,41499.258,41501,41555.73,41554.668,41556.793,166913.81,166910.55,166917.08
|
||||
2,1389.1837,1388.6691,1389.6984,5035.3047,5033.166,5037.4434,9260.9502,9260.4004,9261.5,18218.328,18217.295,18219.361,21047.867,21047.35,21048.385,20349.314,20348.729,20349.9,171130.08,171126.06,171134.09,165529.66,165526.56,165532.75,41583.043,41582.23,41583.855,41637.773,41636.875,41638.672,166949.05,166354.7,167543.39
|
||||
3,1388.8503,1388.3158,1389.3849,5032.9028,5031.438,5034.3677,9236.6445,9235.8213,9237.4678,18328.186,18327.355,18329.016,21030.797,21030.383,21031.211,20304.969,20304.414,20305.523,171054.72,171048.48,171060.95,165145.41,165140,165150.81,41432.672,41279.039,41586.305,41571.406,41568.879,41573.934,166963.53,166959.94,166967.12
|
||||
|
@@ -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 +1,2 @@
|
||||
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
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4129310,4129310,1048576,256,0,0,8,0,16,64,0x0,0x7f8a7d178ec0,1411881076659751,1411881076677985,1411881076693505,1411881076706139
|
||||
|
@@ -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
|
||||
0,11995,1,146027,146027,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370067592,73646370075364,0,205597.0,205597.0,16384.0,65536.0,28177.0,2243556.0
|
||||
1,11995,1,146027,146027,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370113222,73646370119351,0,203828.0,203828.0,16384.0,65536.0,13020.0,1048748.0
|
||||
2,11995,1,146027,146027,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370091949,73646370098199,0,173664.0,173664.0,16384.0,65536.0,13143.0,1049300.0
|
||||
|
+4
@@ -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
|
||||
0,11995,1,146039,146039,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370067592,73646370075364,0,0.0,0.0,0.0
|
||||
1,11995,1,146039,146039,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370113222,73646370119351,0,0.0,0.0,0.0
|
||||
2,11995,1,146039,146039,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370091949,73646370098199,0,0.0,0.0,0.0
|
||||
|
+4
@@ -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
|
||||
0,11995,1,146051,146051,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370067592,73646370075364,0,65536.0,354418.0,28284424.0
|
||||
1,11995,1,146051,146051,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370113222,73646370119351,0,65536.0,313544.0,25075912.0
|
||||
2,11995,1,146051,146051,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370091949,73646370098199,0,65536.0,204760.0,16360664.0
|
||||
|
+4
@@ -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
|
||||
0,11995,1,146063,146063,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370067592,73646370075364,0,32768.0,523237.0,41854716.0
|
||||
1,11995,1,146063,146063,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370113222,73646370119351,0,32768.0,412345.0,32985768.0
|
||||
2,11995,1,146063,146063,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370091949,73646370098199,0,32768.0,413603.0,33086332.0
|
||||
|
@@ -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
|
||||
0,11995,1,146075,146075,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370067592,73646370075364,0,207757.0,207757.0,113371.0,831028.0,16384.0,13995408.0,250575.0,0.0,56383412.0
|
||||
1,11995,1,146075,146075,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370113222,73646370119351,0,176985.0,176985.0,95417.0,707940.0,16384.0,10673662.0,197120.0,0.0,43079648.0
|
||||
2,11995,1,146075,146075,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370091949,73646370098199,0,186914.0,186914.0,105051.0,747656.0,16384.0,10577047.0,196398.0,0.0,42695668.0
|
||||
|
@@ -0,0 +1,267 @@
|
||||
Omniperf version: 2.0.0
|
||||
Profiler choice: rocprofv2
|
||||
Path: /home/colramos/omniperf/tests/workloads/dispatch_2/MI300A_A1
|
||||
Target: MI300A_A1
|
||||
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
|
||||
Kernel Selection: None
|
||||
Dispatch Selection: ['1']
|
||||
Hardware Blocks: All
|
||||
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
Collecting Performance Counters
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/SQ_INST_LEVEL_LDS.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_LDS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|
||||
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|
||||
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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/dispatch_2/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/dispatch_2/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
|
||||
|-> [/opt/rocm/bin/rocprofv2] - GRBM_COUNT
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_1.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SALU
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VSKIPPED
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F16
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F16
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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/dispatch_2/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/dispatch_2/MI300A_A1/perfmon/pmc_perf_12.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_2
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_4
|
||||
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|
||||
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_13.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_ATOMIC[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_BUBBLE[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_CYCLE[0]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_14.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[1]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_15.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[1]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_16.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[3]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[3]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[3]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[3]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_TOO_MANY_EA_WRREQS_STALL[2]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_2.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F16
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCP_VOLATILE_sum
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_3.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_FLAT
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_GDS
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_4.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_BRANCH
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SENDMSG
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAIT_ANY
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAIT_INST_ANY
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_ANY
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_VMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_LDS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_VALU
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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/dispatch_2/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
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_8.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM_NORM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_MFMA
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_I8
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_F16
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_BF16
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCP_PENDING_STALL_CYCLES_sum
|
||||
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|
||||
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|
||||
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
||||
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished copying the output vector from the GPU to the CPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Releasing GPU memory
|
||||
|-> [/opt/rocm/bin/rocprofv2] Releasing CPU memory
|
||||
|-> [/opt/rocm/bin/rocprofv2] Results File: "tests/workloads/dispatch_2/MI300A_A1/out/pmc_1/results_pmc_perf_9.csv"
|
||||
|-> [/opt/rocm/bin/rocprofv2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] The output path for the following counters: tests/workloads/dispatch_2/MI300A_A1/out/pmc_1
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/timestamps.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|
||||
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
||||
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|
||||
[roofline] Roofline temporarily disabled in MI300
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -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: 1
|
||||
kernel:
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
pmc:
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
+4
@@ -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