Add CI workloads for MI300A_A1 and MI300X_A1

Signed-off-by: coleramos425 <colramos@amd.com>
This commit is contained in:
coleramos425 authored and Cole Ramos committed 2024-05-31 16:09:58 -05:00
1 bovenliggende 7d79fcc276
commit b8af814467
1580 files changed
+17548

No files matched your search

@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES
0,11995,1,145295,145295,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152516542,73578152524434,0,206478.0,206478.0,16384.0,65536.0,27426.0,2197528.0
1,11995,1,145295,145295,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152563173,73578152568942,0,189728.0,189728.0,16384.0,65536.0,13109.0,1048768.0
2,11995,1,145295,145295,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152541099,73578152547068,0,166335.0,166335.0,16384.0,65536.0,13122.0,1049488.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
2 0 11995 1 145295 145295 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152516542 73578152524434 0 206478.0 206478.0 16384.0 65536.0 27426.0 2197528.0
3 1 11995 1 145295 145295 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152563173 73578152568942 0 189728.0 189728.0 16384.0 65536.0 13109.0 1048768.0
4 2 11995 1 145295 145295 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152541099 73578152547068 0 166335.0 166335.0 16384.0 65536.0 13122.0 1049488.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES
0,11995,1,145307,145307,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152516542,73578152524434,0,0.0,0.0,0.0
1,11995,1,145307,145307,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152563173,73578152568942,0,0.0,0.0,0.0
2,11995,1,145307,145307,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152541099,73578152547068,0,0.0,0.0,0.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
2 0 11995 1 145307 145307 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152516542 73578152524434 0 0.0 0.0 0.0
3 1 11995 1 145307 145307 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152563173 73578152568942 0 0.0 0.0 0.0
4 2 11995 1 145307 145307 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152541099 73578152547068 0 0.0 0.0 0.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES
0,11995,1,145319,145319,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152516542,73578152524434,0,65536.0,286850.0,23022216.0
1,11995,1,145319,145319,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152563173,73578152568942,0,65536.0,284112.0,22724824.0
2,11995,1,145319,145319,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152541099,73578152547068,0,65536.0,193332.0,15480240.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
2 0 11995 1 145319 145319 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152516542 73578152524434 0 65536.0 286850.0 23022216.0
3 1 11995 1 145319 145319 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152563173 73578152568942 0 65536.0 284112.0 22724824.0
4 2 11995 1 145319 145319 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152541099 73578152547068 0 65536.0 193332.0 15480240.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES
0,11995,1,145331,145331,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152516542,73578152524434,0,32768.0,521655.0,41735128.0
1,11995,1,145331,145331,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152563173,73578152568942,0,32768.0,411382.0,32908148.0
2,11995,1,145331,145331,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152541099,73578152547068,0,32768.0,407969.0,32636212.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
2 0 11995 1 145331 145331 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152516542 73578152524434 0 32768.0 521655.0 41735128.0
3 1 11995 1 145331 145331 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152563173 73578152568942 0 32768.0 411382.0 32908148.0
4 2 11995 1 145331 145331 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152541099 73578152547068 0 32768.0 407969.0 32636212.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES
0,11995,1,145343,145343,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152516542,73578152524434,0,216770.0,216770.0,124638.0,867080.0,16384.0,13528873.0,247296.0,0.0,54536480.0
1,11995,1,145343,145343,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152563173,73578152568942,0,192345.0,192345.0,108619.0,769380.0,16384.0,10930963.0,202980.0,0.0,44128348.0
2,11995,1,145343,145343,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152541099,73578152547068,0,176247.0,176247.0,95064.0,704988.0,16384.0,10384019.0,198974.0,0.0,41996144.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
2 0 11995 1 145343 145343 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152516542 73578152524434 0 216770.0 216770.0 124638.0 867080.0 16384.0 13528873.0 247296.0 0.0 54536480.0
3 1 11995 1 145343 145343 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152563173 73578152568942 0 192345.0 192345.0 108619.0 769380.0 16384.0 10930963.0 202980.0 0.0 44128348.0
4 2 11995 1 145343 145343 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152541099 73578152547068 0 176247.0 176247.0 95064.0 704988.0 16384.0 10384019.0 198974.0 0.0 41996144.0
@@ -0,0 +1,329 @@
Omniperf version: 2.0.0
Profiler choice: rocprofv2
Path: /home/colramos/omniperf/tests/workloads/kernel_substr/MI300A_A1
Target: MI300A_A1
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
Kernel Selection: ['vecCopy']
Dispatch Selection: None
Hardware Blocks: All
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Collecting Performance Counters
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/SQ_IFETCH_LEVEL.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - GRBM_COUNT
|-> [/opt/rocm/bin/rocprofv2] - GRBM_GUI_ACTIVE
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH_LEVEL
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/SQ_INST_LEVEL_LDS.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_LDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/SQ_INST_LEVEL_SMEM.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/SQ_INST_LEVEL_VMEM.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished copying the output vector from the GPU to the CPU
|-> [/opt/rocm/bin/rocprofv2] Releasing GPU memory
|-> [/opt/rocm/bin/rocprofv2] Releasing CPU memory
|-> [/opt/rocm/bin/rocprofv2] Results File: "tests/workloads/kernel_substr/MI300A_A1/out/pmc_1/results_SQ_INST_LEVEL_VMEM.csv"
|-> [/opt/rocm/bin/rocprofv2]
|-> [/opt/rocm/bin/rocprofv2] The output path for the following counters: tests/workloads/kernel_substr/MI300A_A1/out/pmc_1
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/SQ_LEVEL_WAVES.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - GRBM_COUNT
|-> [/opt/rocm/bin/rocprofv2] - GRBM_GUI_ACTIVE
|-> [/opt/rocm/bin/rocprofv2] - CPC_ME1_BUSY_FOR_PACKET_DECODE
|-> [/opt/rocm/bin/rocprofv2] - SQ_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_0.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CU_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVE_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_CVT
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM_WR
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_1.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SALU
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VSKIPPED
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F16
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_10.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_ATOMIC_REQ
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_STALL
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_REQ
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_11.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_INPUT_VALID_READYB
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_ATOMIC
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_8
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_12.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_2
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_4
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_13.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_ATOMIC[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_BUBBLE[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_CYCLE[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_ATOMIC[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_BUBBLE[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_CYCLE[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC[1]
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_14.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[5]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[5]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[5]
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_15.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[1]
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_16.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[3]
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[4]
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[5]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[5]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[5]
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_17.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_TOO_MANY_EA_WRREQS_STALL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_WRITE[0]
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_2.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F64
|-> [/opt/rocm/bin/rocprofv2] - TCP_VOLATILE_sum
|-> [/opt/rocm/bin/rocprofv2] - TCP_TOTAL_ACCESSES_sum
|-> [/opt/rocm/bin/rocprofv2] - TCP_TOTAL_READ_sum
|-> [/opt/rocm/bin/rocprofv2] - TCP_TOTAL_WRITE_sum
|-> [/opt/rocm/bin/rocprofv2] - TA_BUFFER_ATOMIC_WAVEFRONTS_sum
|-> [/opt/rocm/bin/rocprofv2] - TA_BUFFER_TOTAL_CYCLES_sum
|-> [/opt/rocm/bin/rocprofv2] - TD_ATOMIC_WAVEFRONT_sum
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_3.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_FLAT
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_GDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_EXP_GDS
|-> [/opt/rocm/bin/rocprofv2] - TCP_TOTAL_ATOMIC_WITH_RET_sum
|-> [/opt/rocm/bin/rocprofv2] - TCP_TOTAL_ATOMIC_WITHOUT_RET_sum
|-> [/opt/rocm/bin/rocprofv2] - TCP_TOTAL_WRITEBACK_INVALIDATES_sum
|-> [/opt/rocm/bin/rocprofv2] - TCP_TOTAL_CACHE_ACCESSES_sum
|-> [/opt/rocm/bin/rocprofv2] - TA_BUFFER_COALESCED_READ_CYCLES_sum
|-> [/opt/rocm/bin/rocprofv2] - TA_BUFFER_COALESCED_WRITE_CYCLES_sum
|-> [/opt/rocm/bin/rocprofv2] - TD_COALESCABLE_WAVEFRONT_sum
|-> [/opt/rocm/bin/rocprofv2] - SPI_RA_RES_STALL_CSN
|-> [/opt/rocm/bin/rocprofv2] - SPI_RA_TMP_STALL_CSN
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_4.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_BRANCH
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SENDMSG
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAIT_ANY
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAIT_INST_ANY
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_ANY
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_LDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_VALU
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_5.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_SCA
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_EXP_GDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_MISC
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_FLAT
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_VMEM_WR
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_VMEM_RD
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_SALU
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_6.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_THREAD_CYCLES_VALU
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_BANK_CONFLICT
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_7.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_32
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_16
|-> [/opt/rocm/bin/rocprofv2] - SQ_ITEMS
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_MEM_VIOLATIONS
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_ATOMIC_RETURN
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_IDX_ACTIVE
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_RESTORED
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_8.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM_NORM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_MFMA
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_I8
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_BF16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_F64
|-> [/opt/rocm/bin/rocprofv2] - SQ_VALU_MFMA_BUSY_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - TCP_TCC_CC_ATOMIC_REQ_sum
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/pmc_perf_9.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_I8
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_BF16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F64
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_INST_REQ
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_READ_REQ
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_WRITE_REQ
[profiling] Current input file: tests/workloads/kernel_substr/MI300A_A1/perfmon/timestamps.txt
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
[roofline] Roofline temporarily disabled in MI300
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_ATOMIC[0] TCC_BUBBLE[0] TCC_CYCLE[0] TCC_EA0_ATOMIC[0] TCC_ATOMIC[1] TCC_BUBBLE[1] TCC_CYCLE[1] TCC_EA0_ATOMIC[1] TCC_ATOMIC[2] TCC_BUBBLE[2] TCC_CYCLE[2] TCC_EA0_ATOMIC[2] TCC_ATOMIC[3] TCC_BUBBLE[3] TCC_CYCLE[3] TCC_EA0_ATOMIC[3] TCC_ATOMIC[4] TCC_BUBBLE[4] TCC_CYCLE[4] TCC_EA0_ATOMIC[4] TCC_ATOMIC[5] TCC_BUBBLE[5] TCC_CYCLE[5] TCC_EA0_ATOMIC[5] TCC_ATOMIC[6] TCC_BUBBLE[6] TCC_CYCLE[6] TCC_EA0_ATOMIC[6] TCC_ATOMIC[7] TCC_BUBBLE[7] TCC_CYCLE[7] TCC_EA0_ATOMIC[7] TCC_ATOMIC[8] TCC_BUBBLE[8] TCC_CYCLE[8] TCC_EA0_ATOMIC[8] TCC_ATOMIC[9] TCC_BUBBLE[9] TCC_CYCLE[9] TCC_EA0_ATOMIC[9] TCC_ATOMIC[10] TCC_BUBBLE[10] TCC_CYCLE[10] TCC_EA0_ATOMIC[10] TCC_ATOMIC[11] TCC_BUBBLE[11] TCC_CYCLE[11] TCC_EA0_ATOMIC[11] TCC_ATOMIC[12] TCC_BUBBLE[12] TCC_CYCLE[12] TCC_EA0_ATOMIC[12] TCC_ATOMIC[13] TCC_BUBBLE[13] TCC_CYCLE[13] TCC_EA0_ATOMIC[13] TCC_ATOMIC[14] TCC_BUBBLE[14] TCC_CYCLE[14] TCC_EA0_ATOMIC[14] TCC_ATOMIC[15] TCC_BUBBLE[15] TCC_CYCLE[15] TCC_EA0_ATOMIC[15]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_EA0_ATOMIC_LEVEL[0] TCC_EA0_RDREQ[0] TCC_EA0_RDREQ_32B[0] TCC_EA0_RDREQ_LEVEL[0] TCC_EA0_ATOMIC_LEVEL[1] TCC_EA0_RDREQ[1] TCC_EA0_RDREQ_32B[1] TCC_EA0_RDREQ_LEVEL[1] TCC_EA0_ATOMIC_LEVEL[2] TCC_EA0_RDREQ[2] TCC_EA0_RDREQ_32B[2] TCC_EA0_RDREQ_LEVEL[2] TCC_EA0_ATOMIC_LEVEL[3] TCC_EA0_RDREQ[3] TCC_EA0_RDREQ_32B[3] TCC_EA0_RDREQ_LEVEL[3] TCC_EA0_ATOMIC_LEVEL[4] TCC_EA0_RDREQ[4] TCC_EA0_RDREQ_32B[4] TCC_EA0_RDREQ_LEVEL[4] TCC_EA0_ATOMIC_LEVEL[5] TCC_EA0_RDREQ[5] TCC_EA0_RDREQ_32B[5] TCC_EA0_RDREQ_LEVEL[5] TCC_EA0_ATOMIC_LEVEL[6] TCC_EA0_RDREQ[6] TCC_EA0_RDREQ_32B[6] TCC_EA0_RDREQ_LEVEL[6] TCC_EA0_ATOMIC_LEVEL[7] TCC_EA0_RDREQ[7] TCC_EA0_RDREQ_32B[7] TCC_EA0_RDREQ_LEVEL[7] TCC_EA0_ATOMIC_LEVEL[8] TCC_EA0_RDREQ[8] TCC_EA0_RDREQ_32B[8] TCC_EA0_RDREQ_LEVEL[8] TCC_EA0_ATOMIC_LEVEL[9] TCC_EA0_RDREQ[9] TCC_EA0_RDREQ_32B[9] TCC_EA0_RDREQ_LEVEL[9] TCC_EA0_ATOMIC_LEVEL[10] TCC_EA0_RDREQ[10] TCC_EA0_RDREQ_32B[10] TCC_EA0_RDREQ_LEVEL[10] TCC_EA0_ATOMIC_LEVEL[11] TCC_EA0_RDREQ[11] TCC_EA0_RDREQ_32B[11] TCC_EA0_RDREQ_LEVEL[11] TCC_EA0_ATOMIC_LEVEL[12] TCC_EA0_RDREQ[12] TCC_EA0_RDREQ_32B[12] TCC_EA0_RDREQ_LEVEL[12] TCC_EA0_ATOMIC_LEVEL[13] TCC_EA0_RDREQ[13] TCC_EA0_RDREQ_32B[13] TCC_EA0_RDREQ_LEVEL[13] TCC_EA0_ATOMIC_LEVEL[14] TCC_EA0_RDREQ[14] TCC_EA0_RDREQ_32B[14] TCC_EA0_RDREQ_LEVEL[14] TCC_EA0_ATOMIC_LEVEL[15] TCC_EA0_RDREQ[15] TCC_EA0_RDREQ_32B[15] TCC_EA0_RDREQ_LEVEL[15]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_EA0_WRREQ[0] TCC_EA0_WRREQ_64B[0] TCC_EA0_WRREQ_LEVEL[0] TCC_HIT[0] TCC_EA0_WRREQ[1] TCC_EA0_WRREQ_64B[1] TCC_EA0_WRREQ_LEVEL[1] TCC_HIT[1] TCC_EA0_WRREQ[2] TCC_EA0_WRREQ_64B[2] TCC_EA0_WRREQ_LEVEL[2] TCC_HIT[2] TCC_EA0_WRREQ[3] TCC_EA0_WRREQ_64B[3] TCC_EA0_WRREQ_LEVEL[3] TCC_HIT[3] TCC_EA0_WRREQ[4] TCC_EA0_WRREQ_64B[4] TCC_EA0_WRREQ_LEVEL[4] TCC_HIT[4] TCC_EA0_WRREQ[5] TCC_EA0_WRREQ_64B[5] TCC_EA0_WRREQ_LEVEL[5] TCC_HIT[5] TCC_EA0_WRREQ[6] TCC_EA0_WRREQ_64B[6] TCC_EA0_WRREQ_LEVEL[6] TCC_HIT[6] TCC_EA0_WRREQ[7] TCC_EA0_WRREQ_64B[7] TCC_EA0_WRREQ_LEVEL[7] TCC_HIT[7] TCC_EA0_WRREQ[8] TCC_EA0_WRREQ_64B[8] TCC_EA0_WRREQ_LEVEL[8] TCC_HIT[8] TCC_EA0_WRREQ[9] TCC_EA0_WRREQ_64B[9] TCC_EA0_WRREQ_LEVEL[9] TCC_HIT[9] TCC_EA0_WRREQ[10] TCC_EA0_WRREQ_64B[10] TCC_EA0_WRREQ_LEVEL[10] TCC_HIT[10] TCC_EA0_WRREQ[11] TCC_EA0_WRREQ_64B[11] TCC_EA0_WRREQ_LEVEL[11] TCC_HIT[11] TCC_EA0_WRREQ[12] TCC_EA0_WRREQ_64B[12] TCC_EA0_WRREQ_LEVEL[12] TCC_HIT[12] TCC_EA0_WRREQ[13] TCC_EA0_WRREQ_64B[13] TCC_EA0_WRREQ_LEVEL[13] TCC_HIT[13] TCC_EA0_WRREQ[14] TCC_EA0_WRREQ_64B[14] TCC_EA0_WRREQ_LEVEL[14] TCC_HIT[14] TCC_EA0_WRREQ[15] TCC_EA0_WRREQ_64B[15] TCC_EA0_WRREQ_LEVEL[15] TCC_HIT[15]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_RW_REQ[0] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_RW_REQ[1] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_RW_REQ[2] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_RW_REQ[3] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_RW_REQ[4] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_RW_REQ[5] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_RW_REQ[6] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_RW_REQ[7] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_RW_REQ[8] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_RW_REQ[9] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_RW_REQ[10] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_RW_REQ[11] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_RW_REQ[12] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_RW_REQ[13] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_RW_REQ[14] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_RW_REQ[15]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_TAG_STALL[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_TAG_STALL[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_TAG_STALL[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_TAG_STALL[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_TAG_STALL[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_TAG_STALL[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_TAG_STALL[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_TAG_STALL[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_TAG_STALL[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_TAG_STALL[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_TAG_STALL[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_TAG_STALL[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_TAG_STALL[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_TAG_STALL[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_TAG_STALL[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_TAG_STALL[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA0_WRREQ_sum TCC_EA0_WRREQ_64B_sum TCC_EA0_WR_UNCACHED_32B_sum TCC_EA0_WRREQ_DRAM_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCC_READ_REQ_sum TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA0_RDREQ_sum TCC_EA0_RDREQ_32B_sum TCC_BUBBLE_sum TCC_EA0_RD_UNCACHED_32B_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_NC_READ_REQ_sum TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA0_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_UC_WRITE_REQ_sum TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA0_ATOMIC_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_CC_ATOMIC_REQ_sum TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA0_RDREQ_LEVEL_sum TCC_EA0_WRREQ_LEVEL_sum TCC_EA0_ATOMIC_LEVEL_sum TCC_EA0_WRREQ_STALL_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ TCP_PENDING_STALL_CYCLES_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Correlation_ID,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,TCC_EA0_WRREQ_64B_sum,TCC_EA0_WRREQ_DRAM_sum,TCC_EA0_WRREQ_sum,TCC_EA0_WR_UNCACHED_32B_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_TRANSLATION_MISS_sum,Wave_Size_1,Correlation_ID_1,XCC_Index,TCC_EA0_WRREQ[0],TCC_EA0_WRREQ_64B[0],TCC_EA0_WRREQ_LEVEL[0],TCC_HIT[0],TCC_EA0_WRREQ[1],TCC_EA0_WRREQ_64B[1],TCC_EA0_WRREQ_LEVEL[1],TCC_HIT[1],TCC_EA0_WRREQ[2],TCC_EA0_WRREQ_64B[2],TCC_EA0_WRREQ_LEVEL[2],TCC_HIT[2],TCC_EA0_WRREQ[3],TCC_EA0_WRREQ_64B[3],TCC_EA0_WRREQ_LEVEL[3],TCC_HIT[3],TCC_EA0_WRREQ[4],TCC_EA0_WRREQ_64B[4],TCC_EA0_WRREQ_LEVEL[4],TCC_HIT[4],TCC_EA0_WRREQ[5],TCC_EA0_WRREQ_64B[5],TCC_EA0_WRREQ_LEVEL[5],TCC_HIT[5],TCC_EA0_WRREQ[6],TCC_EA0_WRREQ_64B[6],TCC_EA0_WRREQ_LEVEL[6],TCC_HIT[6],TCC_EA0_WRREQ[7],TCC_EA0_WRREQ_64B[7],TCC_EA0_WRREQ_LEVEL[7],TCC_HIT[7],TCC_EA0_WRREQ[8],TCC_EA0_WRREQ_64B[8],TCC_EA0_WRREQ_LEVEL[8],TCC_HIT[8],TCC_EA0_WRREQ[9],TCC_EA0_WRREQ_64B[9],TCC_EA0_WRREQ_LEVEL[9],TCC_HIT[9],TCC_EA0_WRREQ[10],TCC_EA0_WRREQ_64B[10],TCC_EA0_WRREQ_LEVEL[10],TCC_HIT[10],TCC_EA0_WRREQ[11],TCC_EA0_WRREQ_64B[11],TCC_EA0_WRREQ_LEVEL[11],TCC_HIT[11],TCC_EA0_WRREQ[12],TCC_EA0_WRREQ_64B[12],TCC_EA0_WRREQ_LEVEL[12],TCC_HIT[12],TCC_EA0_WRREQ[13],TCC_EA0_WRREQ_64B[13],TCC_EA0_WRREQ_LEVEL[13],TCC_HIT[13],TCC_EA0_WRREQ[14],TCC_EA0_WRREQ_64B[14],TCC_EA0_WRREQ_LEVEL[14],TCC_HIT[14],TCC_EA0_WRREQ[15],TCC_EA0_WRREQ_64B[15],TCC_EA0_WRREQ_LEVEL[15],TCC_HIT[15],TCC_EA0_WRREQ[16],TCC_EA0_WRREQ_64B[16],TCC_EA0_WRREQ_LEVEL[16],TCC_HIT[16],TCC_EA0_WRREQ[17],TCC_EA0_WRREQ_64B[17],TCC_EA0_WRREQ_LEVEL[17],TCC_HIT[17],TCC_EA0_WRREQ[18],TCC_EA0_WRREQ_64B[18],TCC_EA0_WRREQ_LEVEL[18],TCC_HIT[18],TCC_EA0_WRREQ[19],TCC_EA0_WRREQ_64B[19],TCC_EA0_WRREQ_LEVEL[19],TCC_HIT[19],TCC_EA0_WRREQ[20],TCC_EA0_WRREQ_64B[20],TCC_EA0_WRREQ_LEVEL[20],TCC_HIT[20],TCC_EA0_WRREQ[21],TCC_EA0_WRREQ_64B[21],TCC_EA0_WRREQ_LEVEL[21],TCC_HIT[21],TCC_EA0_WRREQ[22],TCC_EA0_WRREQ_64B[22],TCC_EA0_WRREQ_LEVEL[22],TCC_HIT[22],TCC_EA0_WRREQ[23],TCC_EA0_WRREQ_64B[23],TCC_EA0_WRREQ_LEVEL[23],TCC_HIT[23],TCC_EA0_WRREQ[24],TCC_EA0_WRREQ_64B[24],TCC_EA0_WRREQ_LEVEL[24],TCC_HIT[24],TCC_EA0_WRREQ[25],TCC_EA0_WRREQ_64B[25],TCC_EA0_WRREQ_LEVEL[25],TCC_HIT[25],TCC_EA0_WRREQ[26],TCC_EA0_WRREQ_64B[26],TCC_EA0_WRREQ_LEVEL[26],TCC_HIT[26],TCC_EA0_WRREQ[27],TCC_EA0_WRREQ_64B[27],TCC_EA0_WRREQ_LEVEL[27],TCC_HIT[27],TCC_EA0_WRREQ[28],TCC_EA0_WRREQ_64B[28],TCC_EA0_WRREQ_LEVEL[28],TCC_HIT[28],TCC_EA0_WRREQ[29],TCC_EA0_WRREQ_64B[29],TCC_EA0_WRREQ_LEVEL[29],TCC_HIT[29],TCC_EA0_WRREQ[30],TCC_EA0_WRREQ_64B[30],TCC_EA0_WRREQ_LEVEL[30],TCC_HIT[30],TCC_EA0_WRREQ[31],TCC_EA0_WRREQ_64B[31],TCC_EA0_WRREQ_LEVEL[31],TCC_HIT[31],TCC_EA0_WRREQ[32],TCC_EA0_WRREQ_64B[32],TCC_EA0_WRREQ_LEVEL[32],TCC_HIT[32],TCC_EA0_WRREQ[33],TCC_EA0_WRREQ_64B[33],TCC_EA0_WRREQ_LEVEL[33],TCC_HIT[33],TCC_EA0_WRREQ[34],TCC_EA0_WRREQ_64B[34],TCC_EA0_WRREQ_LEVEL[34],TCC_HIT[34],TCC_EA0_WRREQ[35],TCC_EA0_WRREQ_64B[35],TCC_EA0_WRREQ_LEVEL[35],TCC_HIT[35],TCC_EA0_WRREQ[36],TCC_EA0_WRREQ_64B[36],TCC_EA0_WRREQ_LEVEL[36],TCC_HIT[36],TCC_EA0_WRREQ[37],TCC_EA0_WRREQ_64B[37],TCC_EA0_WRREQ_LEVEL[37],TCC_HIT[37],TCC_EA0_WRREQ[38],TCC_EA0_WRREQ_64B[38],TCC_EA0_WRREQ_LEVEL[38],TCC_HIT[38],TCC_EA0_WRREQ[39],TCC_EA0_WRREQ_64B[39],TCC_EA0_WRREQ_LEVEL[39],TCC_HIT[39],TCC_EA0_WRREQ[40],TCC_EA0_WRREQ_64B[40],TCC_EA0_WRREQ_LEVEL[40],TCC_HIT[40],TCC_EA0_WRREQ[41],TCC_EA0_WRREQ_64B[41],TCC_EA0_WRREQ_LEVEL[41],TCC_HIT[41],TCC_EA0_WRREQ[42],TCC_EA0_WRREQ_64B[42],TCC_EA0_WRREQ_LEVEL[42],TCC_HIT[42],TCC_EA0_WRREQ[43],TCC_EA0_WRREQ_64B[43],TCC_EA0_WRREQ_LEVEL[43],TCC_HIT[43],TCC_EA0_WRREQ[44],TCC_EA0_WRREQ_64B[44],TCC_EA0_WRREQ_LEVEL[44],TCC_HIT[44],TCC_EA0_WRREQ[45],TCC_EA0_WRREQ_64B[45],TCC_EA0_WRREQ_LEVEL[45],TCC_HIT[45],TCC_EA0_WRREQ[46],TCC_EA0_WRREQ_64B[46],TCC_EA0_WRREQ_LEVEL[46],TCC_HIT[46],TCC_EA0_WRREQ[47],TCC_EA0_WRREQ_64B[47],TCC_EA0_WRREQ_LEVEL[47],TCC_HIT[47],TCC_EA0_WRREQ[48],TCC_EA0_WRREQ_64B[48],TCC_EA0_WRREQ_LEVEL[48],TCC_HIT[48],TCC_EA0_WRREQ[49],TCC_EA0_WRREQ_64B[49],TCC_EA0_WRREQ_LEVEL[49],TCC_HIT[49],TCC_EA0_WRREQ[50],TCC_EA0_WRREQ_64B[50],TCC_EA0_WRREQ_LEVEL[50],TCC_HIT[50],TCC_EA0_WRREQ[51],TCC_EA0_WRREQ_64B[51],TCC_EA0_WRREQ_LEVEL[51],TCC_HIT[51],TCC_EA0_WRREQ[52],TCC_EA0_WRREQ_64B[52],TCC_EA0_WRREQ_LEVEL[52],TCC_HIT[52],TCC_EA0_WRREQ[53],TCC_EA0_WRREQ_64B[53],TCC_EA0_WRREQ_LEVEL[53],TCC_HIT[53],TCC_EA0_WRREQ[54],TCC_EA0_WRREQ_64B[54],TCC_EA0_WRREQ_LEVEL[54],TCC_HIT[54],TCC_EA0_WRREQ[55],TCC_EA0_WRREQ_64B[55],TCC_EA0_WRREQ_LEVEL[55],TCC_HIT[55],TCC_EA0_WRREQ[56],TCC_EA0_WRREQ_64B[56],TCC_EA0_WRREQ_LEVEL[56],TCC_HIT[56],TCC_EA0_WRREQ[57Line truncated
0,11995,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,16384.0,16384.0,11763663.0,875425.0,278528.0,0.0,0.0,98304.0,360946.0,0.0,0.0,452417.0,119208.0,32768.0,131072.0,131072.0,131072.0,0.0,0.0,524288.0,453356.0,1824.0,64,0,0,1364.0,1364.0,522202.0,682.0,1364.0,1364.0,536251.0,682.0,1364.0,1364.0,536345.0,682.0,1364.0,1364.0,539261.0,682.0,1364.0,1364.0,529471.0,682.0,1364.0,1364.0,534446.0,682.0,1364.0,1364.0,540331.0,682.0,1364.0,1364.0,535446.0,682.0,1368.0,1368.0,515956.0,684.0,1368.0,1368.0,525667.0,742.0,1368.0,1368.0,531047.0,684.0,1368.0,1368.0,530754.0,703.0,1368.0,1368.0,518309.0,684.0,1368.0,1368.0,520394.0,684.0,1368.0,1368.0,536634.0,684.0,1368.0,1368.0,529257.0,684.0,1364.0,1364.0,527837.0,682.0,1364.0,1364.0,537602.0,740.0,1364.0,1364.0,542363.0,682.0,1364.0,1364.0,543264.0,701.0,1364.0,1364.0,536617.0,682.0,1364.0,1364.0,540603.0,682.0,1364.0,1364.0,553774.0,682.0,1364.0,1364.0,549433.0,682.0,1368.0,1368.0,532733.0,684.0,1368.0,1368.0,548302.0,684.0,1368.0,1368.0,533845.0,684.0,1368.0,1368.0,541334.0,684.0,1368.0,1368.0,536032.0,684.0,1368.0,1368.0,539842.0,684.0,1368.0,1368.0,544736.0,684.0,1368.0,1368.0,539700.0,684.0,1364.0,1364.0,527887.0,682.0,1364.0,1364.0,534228.0,740.0,1364.0,1364.0,543454.0,682.0,1364.0,1364.0,542351.0,701.0,1364.0,1364.0,531585.0,682.0,1364.0,1364.0,534344.0,682.0,1364.0,1364.0,546726.0,682.0,1364.0,1364.0,539325.0,682.0,1364.0,1364.0,531686.0,682.0,1364.0,1364.0,543315.0,682.0,1364.0,1364.0,540923.0,682.0,1364.0,1364.0,547529.0,682.0,1364.0,1364.0,537712.0,682.0,1364.0,1364.0,540435.0,682.0,1364.0,1364.0,549268.0,682.0,1364.0,1364.0,542250.0,682.0,1364.0,1364.0,513842.0,682.0,1364.0,1364.0,526624.0,682.0,1364.0,1364.0,524453.0,682.0,1364.0,1364.0,530647.0,682.0,1364.0,1364.0,526870.0,682.0,1364.0,1364.0,531137.0,682.0,1364.0,1364.0,533563.0,682.0,1364.0,1364.0,529246.0,682.0,1364.0,1364.0,523403.0,682.0,1364.0,1364.0,529060.0,740.0,1364.0,1364.0,537228.0,682.0,1364.0,1364.0,536438.0,701.0,1364.0,1364.0,535826.0,682.0,1364.0,1364.0,533395.0,682.0,1364.0,1364.0,549393.0,682.0,1364.0,1364.0,543010.0,682.0,1364.0,1364.0,541610.0,682.0,1364.0,1364.0,550302.0,740.0,1364.0,1364.0,551511.0,682.0,1364.0,1364.0,558107.0,701.0,1364.0,1364.0,546594.0,682.0,1364.0,1364.0,550981.0,682.0,1364.0,1364.0,559597.0,682.0,1364.0,1364.0,548379.0,682.0,1368.0,1368.0,534165.0,684.0,1368.0,1368.0,541722.0,684.0,1368.0,1368.0,542155.0,684.0,1368.0,1368.0,543848.0,684.0,1368.0,1368.0,539334.0,684.0,1368.0,1368.0,548045.0,684.0,1368.0,1368.0,559709.0,684.0,1368.0,1368.0,555464.0,684.0,1364.0,1364.0,537401.0,682.0,1364.0,1364.0,544228.0,682.0,1364.0,1364.0,553146.0,682.0,1364.0,1364.0,552714.0,682.0,1364.0,1364.0,540516.0,682.0,1364.0,1364.0,542442.0,682.0,1364.0,1364.0,561598.0,682.0,1364.0,1364.0,558055.0,682.0,1368.0,1368.0,563328.0,684.0,1368.0,1368.0,572661.0,742.0,1368.0,1368.0,560473.0,684.0,1368.0,1368.0,565583.0,703.0,1368.0,1368.0,565459.0,684.0,1368.0,1368.0,575982.0,684.0,1368.0,1368.0,572388.0,684.0,1368.0,1368.0,572129.0,684.0,64,0,6291456.0,65536.0,0.0,0.0,0.0,16384.0,0.0,0.0,0.0,0.0,16384.0,32768.0,53304.0,65596.0,12232.0,31599.0,0.0,0.0,0.0,0.0,64,0,0,942.0,0.0,1368.0,1190.0,0.0,1368.0,1114.0,0.0,1368.0,1184.0,0.0,1368.0,1260.0,0.0,1368.0,873.0,0.0,1368.0,1283.0,0.0,1368.0,1231.0,0.0,1368.0,1133.0,0.0,1364.0,1193.0,0.0,1364.0,1225.0,0.0,1364.0,1008.0,0.0,1364.0,796.0,0.0,1364.0,789.0,0.0,1364.0,793.0,0.0,1364.0,780.0,0.0,1364.0,1180.0,0.0,1368.0,1266.0,0.0,1368.0,1283.0,0.0,1368.0,1073.0,0.0,1368.0,904.0,0.0,1368.0,893.0,0.0,1368.0,966.0,0.0,1368.0,958.0,0.0,1368.0,751.0,0.0,1364.0,1224.0,0.0,1364.0,998.0,0.0,1364.0,1222.0,0.0,1364.0,1207.0,0.0,1364.0,751.0,0.0,1364.0,1201.0,0.0,1364.0,1177.0,0.0,1364.0,1096.0,0.0,1368.0,1130.0,0.0,1368.0,1217.0,0.0,1368.0,982.0,0.0,1368.0,771.0,0.0,1368.0,755.0,0.0,1368.0,773.0,0.0,1368.0,750.0,0.0,1368.0,782.0,0.0,1364.0,1245.0,0.0,1364.0,988.0,0.0,1364.0,1265.0,0.0,1364.0,1283.0,0.0,1364.0,789.0,0.0,1364.0,1224.0,0.0,1364.0,1192.0,0.0,1364.0,700.0,0.0,1368.0,1278.0,0.0,1368.0,924.0,0.0,1368.0,1300.0,0.0,1368.0,1274.0,0.0,1368.0,683.0,0.0,1368.0,1297.0,0.0,1368.0,1295.0,0.0,1368.0,1223.0,0.0,1364.0,1175.0,0.0,1364.0,1287.0,0.0,1364.0,1011.0,0.0,1364.0,797.0,0.0,1364.0,787.0,0.0,1364.0,850.0,0.0,1364.0,834.0,0.0,1364.0,1119.0,0.0,1364.0,1213.0,0.0,1364.0,1215.0,0.0,1364.0,978.0,0.0,1364.0,768.0,0.0,1364.0,766.0,0.0,1364.0,776.0,0.0,1364.0,765.0,0.0,1364.0,823.0,0.0,1364.0,1293.0,0.0,1364.0,1046.0,0.0,1364.0,1282.0,0.0,1364.0,1252.0,0.0,1364.0,848.0,0.0,1364.0,1259.0,0.0,1364.0,1232.0,0.0,1364.0,688.0,0.0,1364.0,1253.0,0.0,1364.0,930.0,0.0,1364.0,1278.0,0.0,1364.0,1294.0,0.0,1364.0,689.0,0.0,1364.0,1283.0,0.0,1364.0,1258.0,0.0,1364.0,1170.0,0.0,1364.0,1381.0,0.0,1364.0,1301.0,0.0,1364.0,994.0,0.0,1364.0,921.0,0.0,1364.0,885.0,0.0,1364.0,782.0,0.0,1364.0,808.0,0.0,1364.0,64,0,0.0,49152.0,32768.0,65536.0,32768.0,0.0,0.0,0.0,11104.0,0.0,510.0,590968.0,78.0,0.0,0.0,0.0,66068.0,65536.0,131072.0,0.0,0.0,524288.0,2Line truncated
1,11995,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,16384.0,16384.0,9828720.0,925301.0,278528.0,0.0,0.0,98304.0,254205.0,0.0,0.0,470730.0,114501.0,32768.0,131072.0,131072.0,131072.0,0.0,0.0,524288.0,453360.0,1824.0,64,0,0,1368.0,1368.0,627184.0,684.0,1368.0,1368.0,649470.0,684.0,1368.0,1368.0,628888.0,684.0,1368.0,1368.0,639465.0,684.0,1368.0,1368.0,614328.0,684.0,1368.0,1368.0,616109.0,684.0,1368.0,1368.0,617193.0,684.0,1368.0,1368.0,623676.0,684.0,1364.0,1364.0,565698.0,682.0,1364.0,1364.0,583603.0,682.0,1364.0,1364.0,580708.0,682.0,1364.0,1364.0,582228.0,701.0,1364.0,1364.0,582712.0,682.0,1364.0,1364.0,584824.0,682.0,1364.0,1364.0,605529.0,682.0,1364.0,1364.0,606362.0,682.0,1364.0,1364.0,568500.0,682.0,1364.0,1364.0,573982.0,682.0,1364.0,1364.0,584902.0,682.0,1364.0,1364.0,587445.0,701.0,1364.0,1364.0,579877.0,682.0,1364.0,1364.0,587696.0,682.0,1364.0,1364.0,598690.0,682.0,1364.0,1364.0,601883.0,682.0,1364.0,1364.0,610129.0,682.0,1364.0,1364.0,635310.0,682.0,1364.0,1364.0,631819.0,682.0,1364.0,1364.0,640749.0,682.0,1364.0,1364.0,603604.0,682.0,1364.0,1364.0,611778.0,682.0,1364.0,1364.0,627472.0,682.0,1364.0,1364.0,622429.0,682.0,1364.0,1364.0,581025.0,682.0,1364.0,1364.0,591130.0,682.0,1364.0,1364.0,601504.0,682.0,1364.0,1364.0,597428.0,701.0,1364.0,1364.0,587261.0,682.0,1364.0,1364.0,595862.0,682.0,1364.0,1364.0,610125.0,682.0,1364.0,1364.0,604213.0,682.0,1364.0,1364.0,580627.0,682.0,1364.0,1364.0,598697.0,682.0,1364.0,1364.0,593398.0,682.0,1364.0,1364.0,603124.0,682.0,1364.0,1364.0,575711.0,682.0,1364.0,1364.0,578072.0,682.0,1364.0,1364.0,593899.0,682.0,1364.0,1364.0,585996.0,682.0,1368.0,1368.0,599535.0,684.0,1368.0,1368.0,613303.0,684.0,1368.0,1368.0,624722.0,684.0,1368.0,1368.0,630627.0,684.0,1368.0,1368.0,606243.0,684.0,1368.0,1368.0,611206.0,684.0,1368.0,1368.0,617115.0,684.0,1368.0,1368.0,609116.0,684.0,1364.0,1364.0,586116.0,682.0,1364.0,1364.0,596191.0,682.0,1364.0,1364.0,601560.0,682.0,1364.0,1364.0,601028.0,701.0,1364.0,1364.0,594851.0,682.0,1364.0,1364.0,600453.0,682.0,1364.0,1364.0,611449.0,682.0,1364.0,1364.0,607763.0,682.0,1368.0,1368.0,575037.0,684.0,1368.0,1368.0,586916.0,684.0,1368.0,1368.0,585118.0,684.0,1368.0,1368.0,589636.0,703.0,1368.0,1368.0,586000.0,684.0,1368.0,1368.0,594413.0,684.0,1368.0,1368.0,590418.0,684.0,1368.0,1368.0,593175.0,684.0,1364.0,1364.0,574880.0,682.0,1364.0,1364.0,568632.0,682.0,1364.0,1364.0,579915.0,682.0,1364.0,1364.0,578847.0,682.0,1364.0,1364.0,569440.0,682.0,1364.0,1364.0,576671.0,682.0,1364.0,1364.0,590286.0,682.0,1364.0,1364.0,581245.0,682.0,1364.0,1364.0,561883.0,682.0,1364.0,1364.0,563583.0,682.0,1364.0,1364.0,566824.0,682.0,1364.0,1364.0,568168.0,682.0,1364.0,1364.0,558564.0,682.0,1364.0,1364.0,564628.0,682.0,1364.0,1364.0,577233.0,682.0,1364.0,1364.0,573550.0,682.0,1368.0,1368.0,583723.0,684.0,1368.0,1368.0,592436.0,684.0,1368.0,1368.0,589606.0,684.0,1368.0,1368.0,594926.0,703.0,1368.0,1368.0,588549.0,684.0,1368.0,1368.0,593205.0,684.0,1368.0,1368.0,594403.0,684.0,1368.0,1368.0,589276.0,684.0,64,0,6291456.0,65536.0,0.0,0.0,0.0,16384.0,0.0,0.0,0.0,0.0,16384.0,32768.0,52634.0,65607.0,12902.0,67192.0,0.0,0.0,0.0,0.0,64,0,0,1038.0,0.0,1364.0,970.0,0.0,1364.0,1006.0,0.0,1364.0,1078.0,0.0,1364.0,1014.0,0.0,1364.0,960.0,0.0,1364.0,1057.0,0.0,1364.0,1017.0,0.0,1364.0,1455.0,0.0,1368.0,1483.0,0.0,1368.0,1446.0,0.0,1368.0,1438.0,0.0,1368.0,1404.0,0.0,1368.0,1396.0,0.0,1368.0,1482.0,0.0,1368.0,1463.0,0.0,1368.0,1405.0,0.0,1368.0,1297.0,0.0,1368.0,1405.0,0.0,1368.0,1375.0,0.0,1368.0,1319.0,0.0,1368.0,1346.0,0.0,1368.0,1457.0,0.0,1368.0,1392.0,0.0,1368.0,1226.0,0.0,1364.0,1309.0,0.0,1364.0,1386.0,0.0,1364.0,1210.0,0.0,1364.0,1407.0,0.0,1364.0,1360.0,0.0,1364.0,1425.0,0.0,1364.0,1345.0,0.0,1364.0,1226.0,0.0,1364.0,1227.0,0.0,1364.0,1212.0,0.0,1364.0,1195.0,0.0,1364.0,1114.0,0.0,1364.0,1100.0,0.0,1364.0,1082.0,0.0,1364.0,1022.0,0.0,1364.0,1349.0,0.0,1368.0,1311.0,0.0,1368.0,1236.0,0.0,1368.0,1396.0,0.0,1368.0,1186.0,0.0,1368.0,1135.0,0.0,1368.0,1335.0,0.0,1368.0,1360.0,0.0,1368.0,942.0,0.0,1364.0,1106.0,0.0,1364.0,987.0,0.0,1364.0,1003.0,0.0,1364.0,1184.0,0.0,1364.0,986.0,0.0,1364.0,1059.0,0.0,1364.0,1142.0,0.0,1364.0,1000.0,0.0,1364.0,1011.0,0.0,1364.0,985.0,0.0,1364.0,1034.0,0.0,1364.0,1118.0,0.0,1364.0,1078.0,0.0,1364.0,1091.0,0.0,1364.0,1105.0,0.0,1364.0,1164.0,0.0,1364.0,982.0,0.0,1364.0,948.0,0.0,1364.0,963.0,0.0,1364.0,1069.0,0.0,1364.0,1106.0,0.0,1364.0,1140.0,0.0,1364.0,900.0,0.0,1364.0,1123.0,0.0,1364.0,1102.0,0.0,1364.0,976.0,0.0,1364.0,980.0,0.0,1364.0,1148.0,0.0,1364.0,1102.0,0.0,1364.0,1138.0,0.0,1364.0,1063.0,0.0,1364.0,1437.0,0.0,1368.0,1427.0,0.0,1368.0,1391.0,0.0,1368.0,1462.0,0.0,1368.0,1373.0,0.0,1368.0,1438.0,0.0,1368.0,1504.0,0.0,1368.0,1439.0,0.0,1368.0,800.0,0.0,1364.0,892.0,0.0,1364.0,928.0,0.0,1364.0,930.0,0.0,1364.0,912.0,0.0,1364.0,920.0,0.0,1364.0,832.0,0.0,1364.0,821.0,0.0,1364.0,64,0,0.0,49152.0,32768.0,65536.0,32768.0,0.0,0.0,0.0,7433.0,0.0,7830.0,575163.0,812.0,0.0,0.0,0.0,65731.0,65536.0,1310Line truncated
2,11995,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,16384.0,16384.0,9535631.0,749313.0,278528.0,0.0,0.0,98304.0,231214.0,0.0,0.0,394867.0,123076.0,32768.0,131072.0,131072.0,131072.0,0.0,0.0,524288.0,453071.0,1824.0,64,0,0,1364.0,1364.0,583331.0,682.0,1364.0,1364.0,593464.0,682.0,1364.0,1364.0,600327.0,682.0,1364.0,1364.0,606336.0,682.0,1364.0,1364.0,597076.0,682.0,1364.0,1364.0,583375.0,682.0,1364.0,1364.0,611217.0,682.0,1364.0,1364.0,604271.0,682.0,1364.0,1364.0,549244.0,682.0,1364.0,1364.0,558646.0,682.0,1364.0,1364.0,563371.0,682.0,1364.0,1364.0,563503.0,701.0,1364.0,1364.0,562133.0,682.0,1364.0,1364.0,565971.0,682.0,1364.0,1364.0,593617.0,682.0,1364.0,1364.0,587337.0,682.0,1364.0,1364.0,578416.0,682.0,1364.0,1364.0,594286.0,682.0,1364.0,1364.0,600221.0,682.0,1364.0,1364.0,598758.0,701.0,1364.0,1364.0,591058.0,682.0,1364.0,1364.0,595550.0,682.0,1364.0,1364.0,622465.0,682.0,1364.0,1364.0,619349.0,682.0,1364.0,1364.0,574842.0,682.0,1364.0,1364.0,585918.0,682.0,1364.0,1364.0,582599.0,682.0,1364.0,1364.0,588733.0,682.0,1364.0,1364.0,583579.0,682.0,1364.0,1364.0,587001.0,682.0,1364.0,1364.0,587697.0,682.0,1364.0,1364.0,580661.0,682.0,1364.0,1364.0,584032.0,682.0,1364.0,1364.0,589284.0,682.0,1364.0,1364.0,593692.0,682.0,1364.0,1364.0,592062.0,701.0,1364.0,1364.0,593399.0,682.0,1364.0,1364.0,597719.0,682.0,1364.0,1364.0,608652.0,682.0,1364.0,1364.0,612702.0,682.0,1368.0,1368.0,602408.0,684.0,1368.0,1368.0,609170.0,684.0,1368.0,1368.0,594890.0,684.0,1368.0,1368.0,609053.0,684.0,1368.0,1368.0,589085.0,684.0,1368.0,1368.0,593161.0,684.0,1368.0,1368.0,606530.0,684.0,1368.0,1368.0,597907.0,684.0,1364.0,1364.0,595247.0,682.0,1364.0,1364.0,600188.0,682.0,1364.0,1364.0,603287.0,682.0,1364.0,1364.0,619763.0,682.0,1364.0,1364.0,589787.0,682.0,1364.0,1364.0,591582.0,682.0,1364.0,1364.0,604295.0,682.0,1364.0,1364.0,600534.0,682.0,1368.0,1368.0,587054.0,684.0,1368.0,1368.0,594529.0,684.0,1368.0,1368.0,608728.0,684.0,1368.0,1368.0,607197.0,703.0,1368.0,1368.0,600314.0,684.0,1368.0,1368.0,606020.0,684.0,1368.0,1368.0,618927.0,684.0,1368.0,1368.0,617536.0,684.0,1368.0,1368.0,577332.0,684.0,1368.0,1368.0,589828.0,684.0,1368.0,1368.0,592611.0,684.0,1368.0,1368.0,595956.0,703.0,1368.0,1368.0,588554.0,684.0,1368.0,1368.0,594632.0,684.0,1368.0,1368.0,602720.0,684.0,1368.0,1368.0,598581.0,684.0,1364.0,1364.0,570062.0,682.0,1364.0,1364.0,576237.0,682.0,1364.0,1364.0,588179.0,682.0,1364.0,1364.0,583629.0,682.0,1364.0,1364.0,578316.0,682.0,1364.0,1364.0,582925.0,682.0,1364.0,1364.0,589987.0,682.0,1364.0,1364.0,589400.0,682.0,1368.0,1368.0,583566.0,684.0,1368.0,1368.0,590793.0,684.0,1368.0,1368.0,595175.0,684.0,1368.0,1368.0,591895.0,684.0,1368.0,1368.0,582543.0,684.0,1368.0,1368.0,587905.0,684.0,1368.0,1368.0,601036.0,684.0,1368.0,1368.0,598185.0,684.0,1364.0,1364.0,568054.0,682.0,1364.0,1364.0,581222.0,682.0,1364.0,1364.0,577479.0,682.0,1364.0,1364.0,587571.0,701.0,1364.0,1364.0,575737.0,682.0,1364.0,1364.0,579854.0,682.0,1364.0,1364.0,577819.0,682.0,1364.0,1364.0,571661.0,682.0,64,0,6291456.0,65536.0,0.0,0.0,0.0,16384.0,0.0,0.0,0.0,0.0,16384.0,32768.0,52623.0,65623.0,12913.0,59739.0,0.0,0.0,0.0,0.0,64,0,0,1264.0,0.0,1364.0,1254.0,0.0,1364.0,1271.0,0.0,1364.0,1162.0,0.0,1364.0,1397.0,0.0,1364.0,1374.0,0.0,1364.0,1412.0,0.0,1364.0,1379.0,0.0,1364.0,1260.0,0.0,1368.0,1287.0,0.0,1368.0,1282.0,0.0,1368.0,1321.0,0.0,1368.0,1597.0,0.0,1368.0,1529.0,0.0,1368.0,1323.0,0.0,1368.0,1292.0,0.0,1368.0,1251.0,0.0,1364.0,1181.0,0.0,1364.0,1263.0,0.0,1364.0,1295.0,0.0,1364.0,1235.0,0.0,1364.0,1377.0,0.0,1364.0,1195.0,0.0,1364.0,1277.0,0.0,1364.0,1225.0,0.0,1368.0,1234.0,0.0,1368.0,1364.0,0.0,1368.0,1383.0,0.0,1368.0,1348.0,0.0,1368.0,1241.0,0.0,1368.0,1267.0,0.0,1368.0,1240.0,0.0,1368.0,1070.0,0.0,1364.0,1064.0,0.0,1364.0,1031.0,0.0,1364.0,1039.0,0.0,1364.0,998.0,0.0,1364.0,1038.0,0.0,1364.0,919.0,0.0,1364.0,1186.0,0.0,1364.0,997.0,0.0,1364.0,1064.0,0.0,1364.0,1089.0,0.0,1364.0,1221.0,0.0,1364.0,1150.0,0.0,1364.0,1074.0,0.0,1364.0,1055.0,0.0,1364.0,1051.0,0.0,1364.0,1026.0,0.0,1364.0,859.0,0.0,1364.0,1025.0,0.0,1364.0,938.0,0.0,1364.0,1072.0,0.0,1364.0,1005.0,0.0,1364.0,888.0,0.0,1364.0,877.0,0.0,1364.0,983.0,0.0,1364.0,995.0,0.0,1364.0,985.0,0.0,1364.0,984.0,0.0,1364.0,1131.0,0.0,1364.0,1038.0,0.0,1364.0,980.0,0.0,1364.0,1037.0,0.0,1364.0,949.0,0.0,1364.0,953.0,0.0,1364.0,768.0,0.0,1364.0,759.0,0.0,1364.0,943.0,0.0,1364.0,920.0,0.0,1364.0,1006.0,0.0,1364.0,1025.0,0.0,1364.0,1419.0,0.0,1368.0,1371.0,0.0,1368.0,1397.0,0.0,1368.0,1394.0,0.0,1368.0,1515.0,0.0,1368.0,1477.0,0.0,1368.0,1505.0,0.0,1368.0,1495.0,0.0,1368.0,827.0,0.0,1364.0,894.0,0.0,1364.0,881.0,0.0,1364.0,970.0,0.0,1364.0,1001.0,0.0,1364.0,915.0,0.0,1364.0,1011.0,0.0,1364.0,1013.0,0.0,1364.0,1333.0,0.0,1368.0,1339.0,0.0,1368.0,1338.0,0.0,1368.0,1324.0,0.0,1368.0,1331.0,0.0,1368.0,1397.0,0.0,1368.0,1337.0,0.0,1368.0,1336.0,0.0,1368.0,64,0,0.0,49152.0,32768.0,65536.0,32768.0,0.0,0.0,0.0,7367.0,0.0,7917.0,597797.0,0.0,0.0,0.0,0.0,65699.0,65536.0,131072.0,Line truncated
@@ -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
kernel_substr,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Wed 29 May 2024 01:35:00 PM (CDT),2,sh5-1w300-rg3-3,AMD Instinct MI300A Accelerator,"American Megatrends International, LLC.RMO1002DS",Ubuntu 22.04.2 LTS,5.18.2-mi300-build-140423-ubuntu-22.04+,,131174852,,6.1.2-110,N/A,SPX,NPS1,MI300A_A1,gfx942,32,24576,228,4,24,64,1024,32,2100,1300,2100,1300,96,32,120,4,5324.8,6
1 workload_name command ip_blocks timestamp version hostname cpu_model sbios linux_distro linux_kernel_version amd_gpu_kernel_version cpu_memory gpu_memory rocm_version vbios compute_partition memory_partition gpu_model gpu_arch gpu_l1 gpu_l2 cu_per_gpu simd_per_cu se_per_gpu wave_size workgroup_max_size max_waves_per_cu max_sclk max_mclk cur_sclk cur_mclk total_l2_chan lds_banks_per_cu sqc_per_gpu pipes_per_gpu hbm_bw num_xcd
2 kernel_substr ./tests/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF Wed 29 May 2024 01:35:00 PM (CDT) 2 sh5-1w300-rg3-3 AMD Instinct MI300A Accelerator American Megatrends International, LLC.RMO1002DS Ubuntu 22.04.2 LTS 5.18.2-mi300-build-140423-ubuntu-22.04+ 131174852 6.1.2-110 N/A SPX NPS1 MI300A_A1 gfx942 32 24576 228 4 24 64 1024 32 2100 1300 2100 1300 96 32 120 4 5324.8 6
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID
1,11995,1,145571,145571,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152516542,73578152524434,0
3,11995,1,145571,145571,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152563173,73578152568942,0
2,11995,1,145571,145571,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73578152541099,73578152547068,0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID
2 1 11995 1 145571 145571 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152516542 73578152524434 0
3 3 11995 1 145571 145571 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152563173 73578152568942 0
4 2 11995 1 145571 145571 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 73578152541099 73578152547068 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,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES
0,60633,1,963954,963954,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324090593,716205324106872,0,425673.0,425673.0,16384.0,65536.0,39909.0,3192668.0
1,60633,1,963954,963954,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324129270,716205324143230,0,422132.0,422132.0,16384.0,65536.0,12991.0,1048584.0
2,60633,1,963954,963954,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324163469,716205324176349,0,375841.0,375841.0,16384.0,65536.0,13140.0,1048584.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
2 0 60633 1 963954 963954 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324090593 716205324106872 0 425673.0 425673.0 16384.0 65536.0 39909.0 3192668.0
3 1 60633 1 963954 963954 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324129270 716205324143230 0 422132.0 422132.0 16384.0 65536.0 12991.0 1048584.0
4 2 60633 1 963954 963954 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324163469 716205324176349 0 375841.0 375841.0 16384.0 65536.0 13140.0 1048584.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES
0,60633,1,963966,963966,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324090593,716205324106872,0,0.0,0.0,0.0
1,60633,1,963966,963966,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324129270,716205324143230,0,0.0,0.0,0.0
2,60633,1,963966,963966,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324163469,716205324176349,0,0.0,0.0,0.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
2 0 60633 1 963966 963966 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324090593 716205324106872 0 0.0 0.0 0.0
3 1 60633 1 963966 963966 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324129270 716205324143230 0 0.0 0.0 0.0
4 2 60633 1 963966 963966 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324163469 716205324176349 0 0.0 0.0 0.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES
0,60633,1,963978,963978,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324090593,716205324106872,0,65536.0,3573102.0,285799176.0
1,60633,1,963978,963978,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324129270,716205324143230,0,65536.0,3622516.0,289789600.0
2,60633,1,963978,963978,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324163469,716205324176349,0,65536.0,3639192.0,291107976.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
2 0 60633 1 963978 963978 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324090593 716205324106872 0 65536.0 3573102.0 285799176.0
3 1 60633 1 963978 963978 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324129270 716205324143230 0 65536.0 3622516.0 289789600.0
4 2 60633 1 963978 963978 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324163469 716205324176349 0 65536.0 3639192.0 291107976.0
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES
0,60633,1,963990,963990,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324090593,716205324106872,0,32768.0,455747.0,36450284.0
1,60633,1,963990,963990,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324129270,716205324143230,0,32768.0,258596.0,20682628.0
2,60633,1,963990,963990,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324163469,716205324176349,0,32768.0,263497.0,21064296.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
2 0 60633 1 963990 963990 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324090593 716205324106872 0 32768.0 455747.0 36450284.0
3 1 60633 1 963990 963990 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324129270 716205324143230 0 32768.0 258596.0 20682628.0
4 2 60633 1 963990 963990 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324163469 716205324176349 0 32768.0 263497.0 21064296.0
@@ -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
0,60633,1,964002,964002,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324090593,716205324106872,0,473793.0,473793.0,279168.0,1895172.0,16384.0,36765735.0,592860.0,0.0,147407688.0
1,60633,1,964002,964002,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324129270,716205324143230,0,457225.0,457225.0,275909.0,1828900.0,16384.0,32700393.0,515314.0,0.0,131158004.0
2,60633,1,964002,964002,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324163469,716205324176349,0,391478.0,391478.0,212196.0,1565912.0,16384.0,31763583.0,508543.0,0.0,127414480.0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
2 0 60633 1 964002 964002 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324090593 716205324106872 0 473793.0 473793.0 279168.0 1895172.0 16384.0 36765735.0 592860.0 0.0 147407688.0
3 1 60633 1 964002 964002 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324129270 716205324143230 0 457225.0 457225.0 275909.0 1828900.0 16384.0 32700393.0 515314.0 0.0 131158004.0
4 2 60633 1 964002 964002 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324163469 716205324176349 0 391478.0 391478.0 212196.0 1565912.0 16384.0 31763583.0 508543.0 0.0 127414480.0
@@ -0,0 +1,234 @@
Omniperf version: 2.0.0
Profiler choice: rocprofv2
Path: /home/colramos/omniperf/tests/workloads/kernel_substr/MI300X_A1
Target: MI300X_A1
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
Kernel Selection: ['vecCopy']
Dispatch Selection: None
Hardware Blocks: All
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Collecting Performance Counters
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/SQ_IFETCH_LEVEL.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - GRBM_COUNT
|-> [/opt/rocm/bin/rocprofv2] - GRBM_GUI_ACTIVE
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH_LEVEL
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/SQ_INST_LEVEL_LDS.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_LDS
|-> [/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/kernel_substr/MI300X_A1/perfmon/SQ_INST_LEVEL_SMEM.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/SQ_INST_LEVEL_VMEM.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/SQ_LEVEL_WAVES.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - GRBM_COUNT
|-> [/opt/rocm/bin/rocprofv2] - GRBM_GUI_ACTIVE
|-> [/opt/rocm/bin/rocprofv2] - CPC_ME1_BUSY_FOR_PACKET_DECODE
|-> [/opt/rocm/bin/rocprofv2] - SQ_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVE_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CYCLES
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_0.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CYCLES
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CU_CYCLES
|-> [/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
|-> [/opt/rocm/bin/rocprofv2] - GRBM_GUI_ACTIVE
|-> [/opt/rocm/bin/rocprofv2] - TCP_GATE_EN1_sum
|-> [/opt/rocm/bin/rocprofv2] - TCP_GATE_EN2_sum
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_1.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SALU
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VSKIPPED
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_10.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_ATOMIC_REQ
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_STALL
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_REQ
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_16
|-> [/opt/rocm/bin/rocprofv2] - SQC_ICACHE_REQ
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_11.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_INPUT_VALID_READYB
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_ATOMIC
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_8
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_12.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_2
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_4
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_13.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_ATOMIC[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_BUBBLE[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_CYCLE[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_ATOMIC[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_BUBBLE[1]
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_14.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[1]
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_15.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[1]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[2]
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[2]
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_16.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[1]
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_17.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_TOO_MANY_EA_WRREQS_STALL[0]
|-> [/opt/rocm/bin/rocprofv2] - TCC_WRITE[0]
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_2.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F32
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_3.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT64
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_FLAT
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_4.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_BRANCH
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SENDMSG
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAIT_ANY
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAIT_INST_ANY
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_ANY
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_VMEM
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_5.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_SCA
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_EXP_GDS
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_MISC
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_FLAT
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_VMEM_WR
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_CYCLES_VMEM_RD
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_6.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_THREAD_CYCLES_VALU
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_BANK_CONFLICT
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_ADDR_CONFLICT
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_UNALIGNED_STALL
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_7.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_32
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_16
|-> [/opt/rocm/bin/rocprofv2] - SQ_ITEMS
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_MEM_VIOLATIONS
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_ATOMIC_RETURN
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_IDX_ACTIVE
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_RESTORED
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_SAVED
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_8.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM_NORM
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_MFMA
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_I8
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_BF16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_F32
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/pmc_perf_9.txt
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_I8
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_BF16
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F32
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F64
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_INST_REQ
[profiling] Current input file: tests/workloads/kernel_substr/MI300X_A1/perfmon/timestamps.txt
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|-> [/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:
[roofline] Roofline temporarily disabled in MI300
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_ATOMIC[0] TCC_BUBBLE[0] TCC_CYCLE[0] TCC_EA0_ATOMIC[0] TCC_ATOMIC[1] TCC_BUBBLE[1] TCC_CYCLE[1] TCC_EA0_ATOMIC[1] TCC_ATOMIC[2] TCC_BUBBLE[2] TCC_CYCLE[2] TCC_EA0_ATOMIC[2] TCC_ATOMIC[3] TCC_BUBBLE[3] TCC_CYCLE[3] TCC_EA0_ATOMIC[3] TCC_ATOMIC[4] TCC_BUBBLE[4] TCC_CYCLE[4] TCC_EA0_ATOMIC[4] TCC_ATOMIC[5] TCC_BUBBLE[5] TCC_CYCLE[5] TCC_EA0_ATOMIC[5] TCC_ATOMIC[6] TCC_BUBBLE[6] TCC_CYCLE[6] TCC_EA0_ATOMIC[6] TCC_ATOMIC[7] TCC_BUBBLE[7] TCC_CYCLE[7] TCC_EA0_ATOMIC[7] TCC_ATOMIC[8] TCC_BUBBLE[8] TCC_CYCLE[8] TCC_EA0_ATOMIC[8] TCC_ATOMIC[9] TCC_BUBBLE[9] TCC_CYCLE[9] TCC_EA0_ATOMIC[9] TCC_ATOMIC[10] TCC_BUBBLE[10] TCC_CYCLE[10] TCC_EA0_ATOMIC[10] TCC_ATOMIC[11] TCC_BUBBLE[11] TCC_CYCLE[11] TCC_EA0_ATOMIC[11] TCC_ATOMIC[12] TCC_BUBBLE[12] TCC_CYCLE[12] TCC_EA0_ATOMIC[12] TCC_ATOMIC[13] TCC_BUBBLE[13] TCC_CYCLE[13] TCC_EA0_ATOMIC[13] TCC_ATOMIC[14] TCC_BUBBLE[14] TCC_CYCLE[14] TCC_EA0_ATOMIC[14] TCC_ATOMIC[15] TCC_BUBBLE[15] TCC_CYCLE[15] TCC_EA0_ATOMIC[15]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_EA0_ATOMIC_LEVEL[0] TCC_EA0_RDREQ[0] TCC_EA0_RDREQ_32B[0] TCC_EA0_RDREQ_LEVEL[0] TCC_EA0_ATOMIC_LEVEL[1] TCC_EA0_RDREQ[1] TCC_EA0_RDREQ_32B[1] TCC_EA0_RDREQ_LEVEL[1] TCC_EA0_ATOMIC_LEVEL[2] TCC_EA0_RDREQ[2] TCC_EA0_RDREQ_32B[2] TCC_EA0_RDREQ_LEVEL[2] TCC_EA0_ATOMIC_LEVEL[3] TCC_EA0_RDREQ[3] TCC_EA0_RDREQ_32B[3] TCC_EA0_RDREQ_LEVEL[3] TCC_EA0_ATOMIC_LEVEL[4] TCC_EA0_RDREQ[4] TCC_EA0_RDREQ_32B[4] TCC_EA0_RDREQ_LEVEL[4] TCC_EA0_ATOMIC_LEVEL[5] TCC_EA0_RDREQ[5] TCC_EA0_RDREQ_32B[5] TCC_EA0_RDREQ_LEVEL[5] TCC_EA0_ATOMIC_LEVEL[6] TCC_EA0_RDREQ[6] TCC_EA0_RDREQ_32B[6] TCC_EA0_RDREQ_LEVEL[6] TCC_EA0_ATOMIC_LEVEL[7] TCC_EA0_RDREQ[7] TCC_EA0_RDREQ_32B[7] TCC_EA0_RDREQ_LEVEL[7] TCC_EA0_ATOMIC_LEVEL[8] TCC_EA0_RDREQ[8] TCC_EA0_RDREQ_32B[8] TCC_EA0_RDREQ_LEVEL[8] TCC_EA0_ATOMIC_LEVEL[9] TCC_EA0_RDREQ[9] TCC_EA0_RDREQ_32B[9] TCC_EA0_RDREQ_LEVEL[9] TCC_EA0_ATOMIC_LEVEL[10] TCC_EA0_RDREQ[10] TCC_EA0_RDREQ_32B[10] TCC_EA0_RDREQ_LEVEL[10] TCC_EA0_ATOMIC_LEVEL[11] TCC_EA0_RDREQ[11] TCC_EA0_RDREQ_32B[11] TCC_EA0_RDREQ_LEVEL[11] TCC_EA0_ATOMIC_LEVEL[12] TCC_EA0_RDREQ[12] TCC_EA0_RDREQ_32B[12] TCC_EA0_RDREQ_LEVEL[12] TCC_EA0_ATOMIC_LEVEL[13] TCC_EA0_RDREQ[13] TCC_EA0_RDREQ_32B[13] TCC_EA0_RDREQ_LEVEL[13] TCC_EA0_ATOMIC_LEVEL[14] TCC_EA0_RDREQ[14] TCC_EA0_RDREQ_32B[14] TCC_EA0_RDREQ_LEVEL[14] TCC_EA0_ATOMIC_LEVEL[15] TCC_EA0_RDREQ[15] TCC_EA0_RDREQ_32B[15] TCC_EA0_RDREQ_LEVEL[15]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_EA0_WRREQ[0] TCC_EA0_WRREQ_64B[0] TCC_EA0_WRREQ_LEVEL[0] TCC_HIT[0] TCC_EA0_WRREQ[1] TCC_EA0_WRREQ_64B[1] TCC_EA0_WRREQ_LEVEL[1] TCC_HIT[1] TCC_EA0_WRREQ[2] TCC_EA0_WRREQ_64B[2] TCC_EA0_WRREQ_LEVEL[2] TCC_HIT[2] TCC_EA0_WRREQ[3] TCC_EA0_WRREQ_64B[3] TCC_EA0_WRREQ_LEVEL[3] TCC_HIT[3] TCC_EA0_WRREQ[4] TCC_EA0_WRREQ_64B[4] TCC_EA0_WRREQ_LEVEL[4] TCC_HIT[4] TCC_EA0_WRREQ[5] TCC_EA0_WRREQ_64B[5] TCC_EA0_WRREQ_LEVEL[5] TCC_HIT[5] TCC_EA0_WRREQ[6] TCC_EA0_WRREQ_64B[6] TCC_EA0_WRREQ_LEVEL[6] TCC_HIT[6] TCC_EA0_WRREQ[7] TCC_EA0_WRREQ_64B[7] TCC_EA0_WRREQ_LEVEL[7] TCC_HIT[7] TCC_EA0_WRREQ[8] TCC_EA0_WRREQ_64B[8] TCC_EA0_WRREQ_LEVEL[8] TCC_HIT[8] TCC_EA0_WRREQ[9] TCC_EA0_WRREQ_64B[9] TCC_EA0_WRREQ_LEVEL[9] TCC_HIT[9] TCC_EA0_WRREQ[10] TCC_EA0_WRREQ_64B[10] TCC_EA0_WRREQ_LEVEL[10] TCC_HIT[10] TCC_EA0_WRREQ[11] TCC_EA0_WRREQ_64B[11] TCC_EA0_WRREQ_LEVEL[11] TCC_HIT[11] TCC_EA0_WRREQ[12] TCC_EA0_WRREQ_64B[12] TCC_EA0_WRREQ_LEVEL[12] TCC_HIT[12] TCC_EA0_WRREQ[13] TCC_EA0_WRREQ_64B[13] TCC_EA0_WRREQ_LEVEL[13] TCC_HIT[13] TCC_EA0_WRREQ[14] TCC_EA0_WRREQ_64B[14] TCC_EA0_WRREQ_LEVEL[14] TCC_HIT[14] TCC_EA0_WRREQ[15] TCC_EA0_WRREQ_64B[15] TCC_EA0_WRREQ_LEVEL[15] TCC_HIT[15]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_RW_REQ[0] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_RW_REQ[1] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_RW_REQ[2] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_RW_REQ[3] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_RW_REQ[4] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_RW_REQ[5] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_RW_REQ[6] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_RW_REQ[7] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_RW_REQ[8] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_RW_REQ[9] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_RW_REQ[10] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_RW_REQ[11] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_RW_REQ[12] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_RW_REQ[13] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_RW_REQ[14] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_RW_REQ[15]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: TCC_TAG_STALL[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_TAG_STALL[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_TAG_STALL[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_TAG_STALL[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_TAG_STALL[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_TAG_STALL[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_TAG_STALL[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_TAG_STALL[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_TAG_STALL[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_TAG_STALL[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_TAG_STALL[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_TAG_STALL[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_TAG_STALL[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_TAG_STALL[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_TAG_STALL[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_TAG_STALL[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15]
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA0_WRREQ_sum TCC_EA0_WRREQ_64B_sum TCC_EA0_WR_UNCACHED_32B_sum TCC_EA0_WRREQ_DRAM_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCC_READ_REQ_sum TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA0_RDREQ_sum TCC_EA0_RDREQ_32B_sum TCC_BUBBLE_sum TCC_EA0_RD_UNCACHED_32B_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_NC_READ_REQ_sum TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA0_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_UC_WRITE_REQ_sum TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA0_ATOMIC_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_CC_ATOMIC_REQ_sum TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA0_RDREQ_LEVEL_sum TCC_EA0_WRREQ_LEVEL_sum TCC_EA0_ATOMIC_LEVEL_sum TCC_EA0_WRREQ_STALL_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ TCP_PENDING_STALL_CYCLES_sum
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Correlation_ID,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,Wave_Size_1,Correlation_ID_1,XCC_Index,TCC_ATOMIC[0],TCC_BUBBLE[0],TCC_CYCLE[0],TCC_EA0_ATOMIC[0],TCC_ATOMIC[1],TCC_BUBBLE[1],TCC_CYCLE[1],TCC_EA0_ATOMIC[1],TCC_ATOMIC[2],TCC_BUBBLE[2],TCC_CYCLE[2],TCC_EA0_ATOMIC[2],TCC_ATOMIC[3],TCC_BUBBLE[3],TCC_CYCLE[3],TCC_EA0_ATOMIC[3],TCC_ATOMIC[4],TCC_BUBBLE[4],TCC_CYCLE[4],TCC_EA0_ATOMIC[4],TCC_ATOMIC[5],TCC_BUBBLE[5],TCC_CYCLE[5],TCC_EA0_ATOMIC[5],TCC_ATOMIC[6],TCC_BUBBLE[6],TCC_CYCLE[6],TCC_EA0_ATOMIC[6],TCC_ATOMIC[7],TCC_BUBBLE[7],TCC_CYCLE[7],TCC_EA0_ATOMIC[7],TCC_ATOMIC[8],TCC_BUBBLE[8],TCC_CYCLE[8],TCC_EA0_ATOMIC[8],TCC_ATOMIC[9],TCC_BUBBLE[9],TCC_CYCLE[9],TCC_EA0_ATOMIC[9],TCC_ATOMIC[10],TCC_BUBBLE[10],TCC_CYCLE[10],TCC_EA0_ATOMIC[10],TCC_ATOMIC[11],TCC_BUBBLE[11],TCC_CYCLE[11],TCC_EA0_ATOMIC[11],TCC_ATOMIC[12],TCC_BUBBLE[12],TCC_CYCLE[12],TCC_EA0_ATOMIC[12],TCC_ATOMIC[13],TCC_BUBBLE[13],TCC_CYCLE[13],TCC_EA0_ATOMIC[13],TCC_ATOMIC[14],TCC_BUBBLE[14],TCC_CYCLE[14],TCC_EA0_ATOMIC[14],TCC_ATOMIC[15],TCC_BUBBLE[15],TCC_CYCLE[15],TCC_EA0_ATOMIC[15],TCC_ATOMIC[16],TCC_BUBBLE[16],TCC_CYCLE[16],TCC_EA0_ATOMIC[16],TCC_ATOMIC[17],TCC_BUBBLE[17],TCC_CYCLE[17],TCC_EA0_ATOMIC[17],TCC_ATOMIC[18],TCC_BUBBLE[18],TCC_CYCLE[18],TCC_EA0_ATOMIC[18],TCC_ATOMIC[19],TCC_BUBBLE[19],TCC_CYCLE[19],TCC_EA0_ATOMIC[19],TCC_ATOMIC[20],TCC_BUBBLE[20],TCC_CYCLE[20],TCC_EA0_ATOMIC[20],TCC_ATOMIC[21],TCC_BUBBLE[21],TCC_CYCLE[21],TCC_EA0_ATOMIC[21],TCC_ATOMIC[22],TCC_BUBBLE[22],TCC_CYCLE[22],TCC_EA0_ATOMIC[22],TCC_ATOMIC[23],TCC_BUBBLE[23],TCC_CYCLE[23],TCC_EA0_ATOMIC[23],TCC_ATOMIC[24],TCC_BUBBLE[24],TCC_CYCLE[24],TCC_EA0_ATOMIC[24],TCC_ATOMIC[25],TCC_BUBBLE[25],TCC_CYCLE[25],TCC_EA0_ATOMIC[25],TCC_ATOMIC[26],TCC_BUBBLE[26],TCC_CYCLE[26],TCC_EA0_ATOMIC[26],TCC_ATOMIC[27],TCC_BUBBLE[27],TCC_CYCLE[27],TCC_EA0_ATOMIC[27],TCC_ATOMIC[28],TCC_BUBBLE[28],TCC_CYCLE[28],TCC_EA0_ATOMIC[28],TCC_ATOMIC[29],TCC_BUBBLE[29],TCC_CYCLE[29],TCC_EA0_ATOMIC[29],TCC_ATOMIC[30],TCC_BUBBLE[30],TCC_CYCLE[30],TCC_EA0_ATOMIC[30],TCC_ATOMIC[31],TCC_BUBBLE[31],TCC_CYCLE[31],TCC_EA0_ATOMIC[31],TCC_ATOMIC[32],TCC_BUBBLE[32],TCC_CYCLE[32],TCC_EA0_ATOMIC[32],TCC_ATOMIC[33],TCC_BUBBLE[33],TCC_CYCLE[33],TCC_EA0_ATOMIC[33],TCC_ATOMIC[34],TCC_BUBBLE[34],TCC_CYCLE[34],TCC_EA0_ATOMIC[34],TCC_ATOMIC[35],TCC_BUBBLE[35],TCC_CYCLE[35],TCC_EA0_ATOMIC[35],TCC_ATOMIC[36],TCC_BUBBLE[36],TCC_CYCLE[36],TCC_EA0_ATOMIC[36],TCC_ATOMIC[37],TCC_BUBBLE[37],TCC_CYCLE[37],TCC_EA0_ATOMIC[37],TCC_ATOMIC[38],TCC_BUBBLE[38],TCC_CYCLE[38],TCC_EA0_ATOMIC[38],TCC_ATOMIC[39],TCC_BUBBLE[39],TCC_CYCLE[39],TCC_EA0_ATOMIC[39],TCC_ATOMIC[40],TCC_BUBBLE[40],TCC_CYCLE[40],TCC_EA0_ATOMIC[40],TCC_ATOMIC[41],TCC_BUBBLE[41],TCC_CYCLE[41],TCC_EA0_ATOMIC[41],TCC_ATOMIC[42],TCC_BUBBLE[42],TCC_CYCLE[42],TCC_EA0_ATOMIC[42],TCC_ATOMIC[43],TCC_BUBBLE[43],TCC_CYCLE[43],TCC_EA0_ATOMIC[43],TCC_ATOMIC[44],TCC_BUBBLE[44],TCC_CYCLE[44],TCC_EA0_ATOMIC[44],TCC_ATOMIC[45],TCC_BUBBLE[45],TCC_CYCLE[45],TCC_EA0_ATOMIC[45],TCC_ATOMIC[46],TCC_BUBBLE[46],TCC_CYCLE[46],TCC_EA0_ATOMIC[46],TCC_ATOMIC[47],TCC_BUBBLE[47],TCC_CYCLE[47],TCC_EA0_ATOMIC[47],TCC_ATOMIC[48],TCC_BUBBLE[48],TCC_CYCLE[48],TCC_EA0_ATOMIC[48],TCC_ATOMIC[49],TCC_BUBBLE[49],TCC_CYCLE[49],TCC_EA0_ATOMIC[49],TCC_ATOMIC[50],TCC_BUBBLE[50],TCC_CYCLE[50],TCC_EA0_ATOMIC[50],TCC_ATOMIC[51],TCC_BUBBLE[51],TCC_CYCLE[51],TCC_EA0_ATOMIC[51],TCC_ATOMIC[52],TCC_BUBBLE[52],TCC_CYCLE[52],TCC_EA0_ATOMIC[52],TCC_ATOMIC[53],TCC_BUBBLE[53],TCC_CYCLE[53],TCC_EA0_ATOMIC[53],TCC_ATOMIC[54],TCC_BUBBLE[54],TCC_CYCLE[54],TCC_EA0_ATOMIC[54],TCC_ATOMIC[55],TCC_BUBBLE[55],TCC_CYCLE[55],TCC_EA0_ATOMIC[55],TCC_ATOMIC[56],TCC_BUBBLE[56],TCC_CYCLE[56],TCC_EA0_ATOMIC[56],TCC_ATOMIC[57],TCC_BUBBLE[57],TCC_CYCLE[57],TCC_EA0_ATOMIC[57],TCC_ATOMIC[58],TCC_BUBBLE[58],TCC_CYCLE[58],TCC_EA0_ATOMIC[58],TCC_ATOMIC[59],TCC_BUBBLE[59],TCC_CYCLE[59],TCC_EA0_ATOMIC[59],TCC_ATOMIC[60],TCC_BUBBLE[60],TCC_CYCLE[60],TCC_EA0_ATOMIC[60],TCC_ATOMIC[61],TCC_BUBBLE[61],TCC_CYCLE[61],TCC_EA0_ATOMIC[61],TCC_ATOMIC[62],TCC_BUBBLE[62],TCC_CYCLE[62],TCC_EA0_ATOMIC[62],TCC_ATOMIC[63],TCC_BUBBLE[63],TCC_CYCLE[63],TCC_EA0_ATOMIC[63],TCC_ATOMIC[64],TCC_BUBBLE[64],TCC_CYCLE[64],TCC_EA0_ATOMIC[64],TCC_ATOMIC[65],TCC_BUBBLE[65],TCC_CYCLE[65],TCC_EA0_ATOMIC[65],TCC_ATOMIC[66],TCC_BUBBLE[66],TCC_CYCLE[66],TCC_EA0_ATOMIC[66],TCC_ATOMIC[67],TCC_BUBBLE[67],TCC_CYCLE[67],TCC_EA0_ATOMIC[67],TCC_ATOMIC[68],TCC_BUBBLE[68],TCC_CYCLE[68],TCC_EA0_ATOMIC[68],TCC_ATOMIC[69],TCC_BUBBLE[69],TCC_CYCLE[69],TCC_EA0_ATOMIC[69],TCC_ATOMIC[70],TCC_BUBBLE[70],TCC_CYCLE[70],TCC_EA0_ATOMIC[70],TCC_ATOMIC[71],TCC_BUBBLE[71],TCC_CYCLE[71],TCC_EA0_ATOMIC[71],TCC_ATOMIC[72],TCC_BUBBLE[72],TCC_CYCLE[72],TCC_EA0_ATOMIC[72],TCC_ATOMIC[73],TCC_BUBBLE[73],TCC_CYCLE[73],TCC_EA0_ATOMIC[73],TCC_ATOMIC[74],TCC_BUBBLine truncated
0,60633,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,2692529.0,0.0,0.0,65536.0,60576.0,160.0,4800.0,32768.0,64,0,0,0.0,512.0,46150.0,0.0,0.0,512.0,46150.0,0.0,0.0,512.0,46150.0,0.0,0.0,512.0,46150.0,0.0,0.0,512.0,46150.0,0.0,0.0,512.0,46150.0,0.0,0.0,512.0,46150.0,0.0,0.0,512.0,46150.0,0.0,0.0,512.0,46150.0,0.0,0.0,512.0,46150.0,0.0,0.0,512.0,46150.0,0.0,0.0,512.0,46150.0,0.0,0.0,512.0,46150.0,0.0,0.0,512.0,46150.0,0.0,0.0,512.0,46150.0,0.0,0.0,512.0,46150.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,44185.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,55192.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,64463.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,85451.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,94473.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,98267.0,0.0,0.0,512.0,107274.0,0.0,0.0,512.0,107274.0,0.0,0.0,512.0,107274.0,0.0,0.0,512.0,107274.0,0.0,0.0,512.0,107274.0,0.0,0.0,512.0,107274.0,0.0,0.0,512.0,107274.0,0.0,0.0,512.0,107274.0,0.0,0.0,512.0,107274.0,0.0,0.0,512.0,107274.0,0.0,0.0,512.0,107274.0,0.0,0.0,512.0,107274.0,0.0,0.0,512.0,107274.0,0.0,0.0,512.0,107274.0,0.0,0.0,512.0,107274.0,0.0,0.0,512.0,107274.0,0.0,64,0,0.0,0.0,1048576.0,0.0,0.0,0.0,0.0,0.0,0.0,32768.0,0.0,16384.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,64,0,131072.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,16384.0,0.0,0.0,108788262.0,84266188.0,338633.0,0.0,0.0,65536.0,131072.0,64,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,53011.0,31012.0,2029557.0,696.0,0.0,313134.0,0.0,0.0,66160.0,131298.0,197458.0,0.0,2097152.0,1048576.0,1048576.0,2097152.0,0.0,16384.0,64,0,0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,593.0,1617.0,1616.0,1024.0,512.0,1536.0,1536.0,1028.0,516.0,1540.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,593.0,1617.0,1616.0,1024.0,512.0,1536.0,1536.0,1028.0,516.0,1540.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,593.0,1617.0,1616.0,1024.0,512.0,1536.0,1536.0,1027.0,515.0,1539.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,593.0,1617.0,1616.0,1024.0,512.0,1536.0,1536.0,1029.0,517.0,1541.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,102Line truncated
1,60633,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,2710583.0,0.0,0.0,65536.0,60576.0,160.0,4800.0,32768.0,64,0,0,0.0,512.0,41195.0,0.0,0.0,512.0,41195.0,0.0,0.0,512.0,41195.0,0.0,0.0,512.0,41195.0,0.0,0.0,512.0,41195.0,0.0,0.0,512.0,41195.0,0.0,0.0,512.0,41195.0,0.0,0.0,512.0,41195.0,0.0,0.0,512.0,41195.0,0.0,0.0,512.0,41195.0,0.0,0.0,512.0,41195.0,0.0,0.0,512.0,41195.0,0.0,0.0,512.0,41195.0,0.0,0.0,512.0,41195.0,0.0,0.0,512.0,41195.0,0.0,0.0,512.0,41195.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,41069.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,60595.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,67789.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,81068.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,89678.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,90927.0,0.0,0.0,512.0,98403.0,0.0,0.0,512.0,98403.0,0.0,0.0,512.0,98403.0,0.0,0.0,512.0,98403.0,0.0,0.0,512.0,98403.0,0.0,0.0,512.0,98403.0,0.0,0.0,512.0,98403.0,0.0,0.0,512.0,98403.0,0.0,0.0,512.0,98403.0,0.0,0.0,512.0,98403.0,0.0,0.0,512.0,98403.0,0.0,0.0,512.0,98403.0,0.0,0.0,512.0,98403.0,0.0,0.0,512.0,98403.0,0.0,0.0,512.0,98403.0,0.0,0.0,512.0,98403.0,0.0,64,0,0.0,0.0,1048576.0,0.0,0.0,0.0,0.0,0.0,0.0,32768.0,0.0,16384.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,64,0,131072.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,16384.0,0.0,0.0,66466130.0,90948738.0,355011.0,0.0,0.0,65536.0,131072.0,64,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,42072.0,25906.0,1998456.0,9643.0,0.0,282386.0,0.0,0.0,65536.0,131307.0,196843.0,0.0,2097152.0,1048576.0,1048576.0,2097152.0,0.0,16384.0,64,0,0,1024.0,512.0,1536.0,1536.0,1027.0,515.0,1539.0,1536.0,1025.0,513.0,1537.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1028.0,516.0,1540.0,1536.0,1026.0,514.0,1538.0,1536.0,1026.0,514.0,1538.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1028.0,516.0,1540.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,515.0,1539.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,515.0,1539.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1025.0,513.0,1537.0,1536.0,1026.0,514.0,1538.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,515.0,1539.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0Line truncated
2,60633,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,2686595.0,0.0,0.0,65536.0,60576.0,160.0,4800.0,32768.0,64,0,0,0.0,512.0,41952.0,0.0,0.0,512.0,41952.0,0.0,0.0,512.0,41952.0,0.0,0.0,512.0,41952.0,0.0,0.0,512.0,41952.0,0.0,0.0,512.0,41952.0,0.0,0.0,512.0,41952.0,0.0,0.0,512.0,41952.0,0.0,0.0,512.0,41952.0,0.0,0.0,512.0,41952.0,0.0,0.0,512.0,41952.0,0.0,0.0,512.0,41952.0,0.0,0.0,512.0,41952.0,0.0,0.0,512.0,41952.0,0.0,0.0,512.0,41952.0,0.0,0.0,512.0,41952.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,32876.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,51570.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,59857.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,74401.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,82789.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,86870.0,0.0,0.0,512.0,93405.0,0.0,0.0,512.0,93405.0,0.0,0.0,512.0,93405.0,0.0,0.0,512.0,93405.0,0.0,0.0,512.0,93405.0,0.0,0.0,512.0,93405.0,0.0,0.0,512.0,93405.0,0.0,0.0,512.0,93405.0,0.0,0.0,512.0,93405.0,0.0,0.0,512.0,93405.0,0.0,0.0,512.0,93405.0,0.0,0.0,512.0,93405.0,0.0,0.0,512.0,93405.0,0.0,0.0,512.0,93405.0,0.0,0.0,512.0,93405.0,0.0,0.0,512.0,93405.0,0.0,64,0,0.0,0.0,1048576.0,0.0,0.0,0.0,0.0,0.0,0.0,32768.0,0.0,16384.0,0.0,0.0,29.0,0.0,0.0,0.0,0.0,0.0,64,0,131072.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,16384.0,0.0,0.0,49895024.0,65522895.0,203198.0,0.0,0.0,65536.0,131072.0,64,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,46223.0,26015.0,1992688.0,9702.0,0.0,242148.0,0.0,0.0,65536.0,131314.0,196850.0,0.0,2097152.0,1048576.0,1048576.0,2097152.0,0.0,16384.0,64,0,0,1024.0,512.0,1536.0,1536.0,1027.0,515.0,1539.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1029.0,517.0,1541.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1028.0,516.0,1540.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,515.0,1539.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,515.0,1539.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1028.0,516.0,1540.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1029.0,517.0,1541.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,515.0,1539.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.Line truncated
@@ -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
kernel_substr,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Wed 29 May 2024 12:00:15 PM (CDT),2,splinter-126-wr-c6,AMD Ryzen 9 7950X 16-Core Processor,"American Megatrends International, LLC.VS2683299N.FD",Ubuntu 22.04.4 LTS,5.18.2-mi300-build-140423-ubuntu-22.04+,,114656528,,6.2.0-13611,113-MI3SRIOV-001,SPX,NPS1,MI300X_A1,gfx942,32,4096,304,4,32,64,1024,32,2100,1300,2100,1300,128,32,160,4,5324.8,8
1 workload_name command ip_blocks timestamp version hostname cpu_model sbios linux_distro linux_kernel_version amd_gpu_kernel_version cpu_memory gpu_memory rocm_version vbios compute_partition memory_partition gpu_model gpu_arch gpu_l1 gpu_l2 cu_per_gpu simd_per_cu se_per_gpu wave_size workgroup_max_size max_waves_per_cu max_sclk max_mclk cur_sclk cur_mclk total_l2_chan lds_banks_per_cu sqc_per_gpu pipes_per_gpu hbm_bw num_xcd
2 kernel_substr ./tests/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF Wed 29 May 2024 12:00:15 PM (CDT) 2 splinter-126-wr-c6 AMD Ryzen 9 7950X 16-Core Processor American Megatrends International, LLC.VS2683299N.FD Ubuntu 22.04.4 LTS 5.18.2-mi300-build-140423-ubuntu-22.04+ 114656528 6.2.0-13611 113-MI3SRIOV-001 SPX NPS1 MI300X_A1 gfx942 32 4096 304 4 32 64 1024 32 2100 1300 2100 1300 128 32 160 4 5324.8 8
@@ -0,0 +1,4 @@
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID
1,60633,1,964231,964231,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324090593,716205324106872,0
2,60633,1,964231,964231,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324129270,716205324143230,0
3,60633,1,964231,964231,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716205324163469,716205324176349,0
1 Dispatch_ID GPU_ID Queue_ID PID TID Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR Wave_Size Kernel_Name Start_Timestamp End_Timestamp Correlation_ID
2 1 60633 1 964231 964231 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324090593 716205324106872 0
3 2 60633 1 964231 964231 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324129270 716205324143230 0
4 3 60633 1 964231 964231 1048576 256 0 0 4 4 16 64 vecCopy(double*, double*, double*, int, int) (.kd) 716205324163469 716205324176349 0