Add CI workloads for MI300A_A1 and MI300X_A1
Signed-off-by: coleramos425 <colramos@amd.com>
Esse commit está contido em:
1 pai
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
|
||||
0,11995,1,146027,146027,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370067592,73646370075364,0,205597.0,205597.0,16384.0,65536.0,28177.0,2243556.0
|
||||
1,11995,1,146027,146027,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370113222,73646370119351,0,203828.0,203828.0,16384.0,65536.0,13020.0,1048748.0
|
||||
2,11995,1,146027,146027,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370091949,73646370098199,0,173664.0,173664.0,16384.0,65536.0,13143.0,1049300.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES
|
||||
0,11995,1,146039,146039,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370067592,73646370075364,0,0.0,0.0,0.0
|
||||
1,11995,1,146039,146039,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370113222,73646370119351,0,0.0,0.0,0.0
|
||||
2,11995,1,146039,146039,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370091949,73646370098199,0,0.0,0.0,0.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES
|
||||
0,11995,1,146051,146051,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370067592,73646370075364,0,65536.0,354418.0,28284424.0
|
||||
1,11995,1,146051,146051,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370113222,73646370119351,0,65536.0,313544.0,25075912.0
|
||||
2,11995,1,146051,146051,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370091949,73646370098199,0,65536.0,204760.0,16360664.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES
|
||||
0,11995,1,146063,146063,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370067592,73646370075364,0,32768.0,523237.0,41854716.0
|
||||
1,11995,1,146063,146063,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370113222,73646370119351,0,32768.0,412345.0,32985768.0
|
||||
2,11995,1,146063,146063,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370091949,73646370098199,0,32768.0,413603.0,33086332.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES
|
||||
0,11995,1,146075,146075,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370067592,73646370075364,0,207757.0,207757.0,113371.0,831028.0,16384.0,13995408.0,250575.0,0.0,56383412.0
|
||||
1,11995,1,146075,146075,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370113222,73646370119351,0,176985.0,176985.0,95417.0,707940.0,16384.0,10673662.0,197120.0,0.0,43079648.0
|
||||
2,11995,1,146075,146075,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370091949,73646370098199,0,186914.0,186914.0,105051.0,747656.0,16384.0,10577047.0,196398.0,0.0,42695668.0
|
||||
|
@@ -0,0 +1,267 @@
|
||||
Omniperf version: 2.0.0
|
||||
Profiler choice: rocprofv2
|
||||
Path: /home/colramos/omniperf/tests/workloads/dispatch_2/MI300A_A1
|
||||
Target: MI300A_A1
|
||||
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
|
||||
Kernel Selection: None
|
||||
Dispatch Selection: ['1']
|
||||
Hardware Blocks: All
|
||||
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
Collecting Performance Counters
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/SQ_IFETCH_LEVEL.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - GRBM_COUNT
|
||||
|-> [/opt/rocm/bin/rocprofv2] - GRBM_GUI_ACTIVE
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/SQ_INST_LEVEL_LDS.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_LDS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|
||||
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|
||||
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/SQ_INST_LEVEL_SMEM.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_SMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|
||||
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|
||||
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/SQ_INST_LEVEL_VMEM.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INST_LEVEL_VMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|
||||
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|
||||
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/SQ_LEVEL_WAVES.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - GRBM_COUNT
|
||||
|-> [/opt/rocm/bin/rocprofv2] - GRBM_GUI_ACTIVE
|
||||
|-> [/opt/rocm/bin/rocprofv2] - CPC_ME1_BUSY_FOR_PACKET_DECODE
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_CYCLES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVE_CYCLES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CYCLES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_LEVEL_WAVES
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_0.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_CYCLES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CYCLES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_BUSY_CU_CYCLES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVE_CYCLES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_CVT
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM_WR
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM_RD
|
||||
|-> [/opt/rocm/bin/rocprofv2] - GRBM_COUNT
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_1.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SALU
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VSKIPPED
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F16
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F16
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_10.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_ATOMIC_REQ
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_STALL
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_REQ
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_11.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_INPUT_VALID_READYB
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_ATOMIC
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_8
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_HITS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_MISSES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_MISSES_DUPLICATE
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_1
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_12.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_2
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_REQ_READ_4
|
||||
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|
||||
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_13.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_ATOMIC[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_BUBBLE[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_CYCLE[0]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_14.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_ATOMIC_LEVEL[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_LEVEL[1]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_15.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_64B[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_WRREQ_LEVEL[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_HIT[1]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_16.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_MISS[3]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[3]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[3]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_RW_REQ[3]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_17.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_TOO_MANY_EA_WRREQS_STALL[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_WRITE[0]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_TOO_MANY_EA_WRREQS_STALL[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_WRITE[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_TOO_MANY_EA_WRREQS_STALL[2]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_2.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F16
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_FMA_F64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCP_VOLATILE_sum
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_3.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_INT64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_FLAT
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_GDS
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_4.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_BRANCH
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SENDMSG
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAIT_ANY
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAIT_INST_ANY
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_ANY
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_VMEM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_LDS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_VALU
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_5.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_SCA
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_EXP_GDS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_MISC
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACTIVE_INST_FLAT
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_6.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_THREAD_CYCLES_VALU
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_IFETCH
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_LDS_BANK_CONFLICT
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_7.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_WAVES_LT_16
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_8.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_SMEM_NORM
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_MFMA
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_I8
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_F16
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_BF16
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/pmc_perf_9.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] ROCProfilerV2: Collecting the following counters:
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_I8
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F16
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_BF16
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MFMA_MOPS_F64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_INST_REQ
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_READ_REQ
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_TC_DATA_WRITE_REQ
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCP_PENDING_STALL_CYCLES_sum
|
||||
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|
||||
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|
||||
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
||||
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished copying the output vector from the GPU to the CPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Releasing GPU memory
|
||||
|-> [/opt/rocm/bin/rocprofv2] Releasing CPU memory
|
||||
|-> [/opt/rocm/bin/rocprofv2] Results File: "tests/workloads/dispatch_2/MI300A_A1/out/pmc_1/results_pmc_perf_9.csv"
|
||||
|-> [/opt/rocm/bin/rocprofv2]
|
||||
|-> [/opt/rocm/bin/rocprofv2] The output path for the following counters: tests/workloads/dispatch_2/MI300A_A1/out/pmc_1
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/MI300A_A1/perfmon/timestamps.txt
|
||||
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished copying vectors to the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] sw thinks it moved 1.000000 KB per wave
|
||||
|-> [/opt/rocm/bin/rocprofv2] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
||||
|-> [/opt/rocm/bin/rocprofv2] Launching the kernel on the GPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished executing kernel
|
||||
[roofline] Roofline temporarily disabled in MI300
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_ATOMIC[0] TCC_BUBBLE[0] TCC_CYCLE[0] TCC_EA0_ATOMIC[0] TCC_ATOMIC[1] TCC_BUBBLE[1] TCC_CYCLE[1] TCC_EA0_ATOMIC[1] TCC_ATOMIC[2] TCC_BUBBLE[2] TCC_CYCLE[2] TCC_EA0_ATOMIC[2] TCC_ATOMIC[3] TCC_BUBBLE[3] TCC_CYCLE[3] TCC_EA0_ATOMIC[3] TCC_ATOMIC[4] TCC_BUBBLE[4] TCC_CYCLE[4] TCC_EA0_ATOMIC[4] TCC_ATOMIC[5] TCC_BUBBLE[5] TCC_CYCLE[5] TCC_EA0_ATOMIC[5] TCC_ATOMIC[6] TCC_BUBBLE[6] TCC_CYCLE[6] TCC_EA0_ATOMIC[6] TCC_ATOMIC[7] TCC_BUBBLE[7] TCC_CYCLE[7] TCC_EA0_ATOMIC[7] TCC_ATOMIC[8] TCC_BUBBLE[8] TCC_CYCLE[8] TCC_EA0_ATOMIC[8] TCC_ATOMIC[9] TCC_BUBBLE[9] TCC_CYCLE[9] TCC_EA0_ATOMIC[9] TCC_ATOMIC[10] TCC_BUBBLE[10] TCC_CYCLE[10] TCC_EA0_ATOMIC[10] TCC_ATOMIC[11] TCC_BUBBLE[11] TCC_CYCLE[11] TCC_EA0_ATOMIC[11] TCC_ATOMIC[12] TCC_BUBBLE[12] TCC_CYCLE[12] TCC_EA0_ATOMIC[12] TCC_ATOMIC[13] TCC_BUBBLE[13] TCC_CYCLE[13] TCC_EA0_ATOMIC[13] TCC_ATOMIC[14] TCC_BUBBLE[14] TCC_CYCLE[14] TCC_EA0_ATOMIC[14] TCC_ATOMIC[15] TCC_BUBBLE[15] TCC_CYCLE[15] TCC_EA0_ATOMIC[15]
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_EA0_ATOMIC_LEVEL[0] TCC_EA0_RDREQ[0] TCC_EA0_RDREQ_32B[0] TCC_EA0_RDREQ_LEVEL[0] TCC_EA0_ATOMIC_LEVEL[1] TCC_EA0_RDREQ[1] TCC_EA0_RDREQ_32B[1] TCC_EA0_RDREQ_LEVEL[1] TCC_EA0_ATOMIC_LEVEL[2] TCC_EA0_RDREQ[2] TCC_EA0_RDREQ_32B[2] TCC_EA0_RDREQ_LEVEL[2] TCC_EA0_ATOMIC_LEVEL[3] TCC_EA0_RDREQ[3] TCC_EA0_RDREQ_32B[3] TCC_EA0_RDREQ_LEVEL[3] TCC_EA0_ATOMIC_LEVEL[4] TCC_EA0_RDREQ[4] TCC_EA0_RDREQ_32B[4] TCC_EA0_RDREQ_LEVEL[4] TCC_EA0_ATOMIC_LEVEL[5] TCC_EA0_RDREQ[5] TCC_EA0_RDREQ_32B[5] TCC_EA0_RDREQ_LEVEL[5] TCC_EA0_ATOMIC_LEVEL[6] TCC_EA0_RDREQ[6] TCC_EA0_RDREQ_32B[6] TCC_EA0_RDREQ_LEVEL[6] TCC_EA0_ATOMIC_LEVEL[7] TCC_EA0_RDREQ[7] TCC_EA0_RDREQ_32B[7] TCC_EA0_RDREQ_LEVEL[7] TCC_EA0_ATOMIC_LEVEL[8] TCC_EA0_RDREQ[8] TCC_EA0_RDREQ_32B[8] TCC_EA0_RDREQ_LEVEL[8] TCC_EA0_ATOMIC_LEVEL[9] TCC_EA0_RDREQ[9] TCC_EA0_RDREQ_32B[9] TCC_EA0_RDREQ_LEVEL[9] TCC_EA0_ATOMIC_LEVEL[10] TCC_EA0_RDREQ[10] TCC_EA0_RDREQ_32B[10] TCC_EA0_RDREQ_LEVEL[10] TCC_EA0_ATOMIC_LEVEL[11] TCC_EA0_RDREQ[11] TCC_EA0_RDREQ_32B[11] TCC_EA0_RDREQ_LEVEL[11] TCC_EA0_ATOMIC_LEVEL[12] TCC_EA0_RDREQ[12] TCC_EA0_RDREQ_32B[12] TCC_EA0_RDREQ_LEVEL[12] TCC_EA0_ATOMIC_LEVEL[13] TCC_EA0_RDREQ[13] TCC_EA0_RDREQ_32B[13] TCC_EA0_RDREQ_LEVEL[13] TCC_EA0_ATOMIC_LEVEL[14] TCC_EA0_RDREQ[14] TCC_EA0_RDREQ_32B[14] TCC_EA0_RDREQ_LEVEL[14] TCC_EA0_ATOMIC_LEVEL[15] TCC_EA0_RDREQ[15] TCC_EA0_RDREQ_32B[15] TCC_EA0_RDREQ_LEVEL[15]
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_EA0_WRREQ[0] TCC_EA0_WRREQ_64B[0] TCC_EA0_WRREQ_LEVEL[0] TCC_HIT[0] TCC_EA0_WRREQ[1] TCC_EA0_WRREQ_64B[1] TCC_EA0_WRREQ_LEVEL[1] TCC_HIT[1] TCC_EA0_WRREQ[2] TCC_EA0_WRREQ_64B[2] TCC_EA0_WRREQ_LEVEL[2] TCC_HIT[2] TCC_EA0_WRREQ[3] TCC_EA0_WRREQ_64B[3] TCC_EA0_WRREQ_LEVEL[3] TCC_HIT[3] TCC_EA0_WRREQ[4] TCC_EA0_WRREQ_64B[4] TCC_EA0_WRREQ_LEVEL[4] TCC_HIT[4] TCC_EA0_WRREQ[5] TCC_EA0_WRREQ_64B[5] TCC_EA0_WRREQ_LEVEL[5] TCC_HIT[5] TCC_EA0_WRREQ[6] TCC_EA0_WRREQ_64B[6] TCC_EA0_WRREQ_LEVEL[6] TCC_HIT[6] TCC_EA0_WRREQ[7] TCC_EA0_WRREQ_64B[7] TCC_EA0_WRREQ_LEVEL[7] TCC_HIT[7] TCC_EA0_WRREQ[8] TCC_EA0_WRREQ_64B[8] TCC_EA0_WRREQ_LEVEL[8] TCC_HIT[8] TCC_EA0_WRREQ[9] TCC_EA0_WRREQ_64B[9] TCC_EA0_WRREQ_LEVEL[9] TCC_HIT[9] TCC_EA0_WRREQ[10] TCC_EA0_WRREQ_64B[10] TCC_EA0_WRREQ_LEVEL[10] TCC_HIT[10] TCC_EA0_WRREQ[11] TCC_EA0_WRREQ_64B[11] TCC_EA0_WRREQ_LEVEL[11] TCC_HIT[11] TCC_EA0_WRREQ[12] TCC_EA0_WRREQ_64B[12] TCC_EA0_WRREQ_LEVEL[12] TCC_HIT[12] TCC_EA0_WRREQ[13] TCC_EA0_WRREQ_64B[13] TCC_EA0_WRREQ_LEVEL[13] TCC_HIT[13] TCC_EA0_WRREQ[14] TCC_EA0_WRREQ_64B[14] TCC_EA0_WRREQ_LEVEL[14] TCC_HIT[14] TCC_EA0_WRREQ[15] TCC_EA0_WRREQ_64B[15] TCC_EA0_WRREQ_LEVEL[15] TCC_HIT[15]
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_RW_REQ[0] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_RW_REQ[1] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_RW_REQ[2] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_RW_REQ[3] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_RW_REQ[4] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_RW_REQ[5] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_RW_REQ[6] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_RW_REQ[7] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_RW_REQ[8] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_RW_REQ[9] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_RW_REQ[10] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_RW_REQ[11] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_RW_REQ[12] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_RW_REQ[13] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_RW_REQ[14] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_RW_REQ[15]
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_TAG_STALL[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_TAG_STALL[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_TAG_STALL[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_TAG_STALL[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_TAG_STALL[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_TAG_STALL[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_TAG_STALL[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_TAG_STALL[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_TAG_STALL[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_TAG_STALL[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_TAG_STALL[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_TAG_STALL[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_TAG_STALL[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_TAG_STALL[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_TAG_STALL[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_TAG_STALL[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15]
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA0_WRREQ_sum TCC_EA0_WRREQ_64B_sum TCC_EA0_WR_UNCACHED_32B_sum TCC_EA0_WRREQ_DRAM_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCC_READ_REQ_sum TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA0_RDREQ_sum TCC_EA0_RDREQ_32B_sum TCC_BUBBLE_sum TCC_EA0_RD_UNCACHED_32B_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_NC_READ_REQ_sum TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA0_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_UC_WRITE_REQ_sum TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA0_ATOMIC_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_CC_ATOMIC_REQ_sum TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA0_RDREQ_LEVEL_sum TCC_EA0_WRREQ_LEVEL_sum TCC_EA0_ATOMIC_LEVEL_sum TCC_EA0_WRREQ_STALL_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ TCP_PENDING_STALL_CYCLES_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc:
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -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)",0,16384.0,16384.0,11970482.0,1145704.0,278528.0,0.0,0.0,98304.0,403390.0,0.0,0.0,471421.0,140763.0,32768.0,131072.0,131072.0,131072.0,0.0,0.0,524288.0,453229.0,1822.0,64,0,0,1364.0,1364.0,518982.0,682.0,1364.0,1364.0,530284.0,682.0,1364.0,1364.0,533691.0,682.0,1364.0,1364.0,539396.0,682.0,1364.0,1364.0,526477.0,682.0,1364.0,1364.0,532445.0,682.0,1364.0,1364.0,542349.0,682.0,1364.0,1364.0,533749.0,740.0,1368.0,1368.0,511700.0,684.0,1368.0,1368.0,522233.0,684.0,1368.0,1368.0,538744.0,684.0,1368.0,1368.0,536736.0,703.0,1368.0,1368.0,542074.0,684.0,1368.0,1368.0,537972.0,684.0,1368.0,1368.0,559639.0,684.0,1368.0,1368.0,554338.0,684.0,1364.0,1364.0,537704.0,682.0,1364.0,1364.0,544881.0,682.0,1364.0,1364.0,547310.0,682.0,1364.0,1364.0,547079.0,701.0,1364.0,1364.0,535313.0,682.0,1364.0,1364.0,540081.0,682.0,1364.0,1364.0,552806.0,682.0,1364.0,1364.0,547481.0,682.0,1368.0,1368.0,518804.0,684.0,1368.0,1368.0,527708.0,684.0,1368.0,1368.0,532284.0,684.0,1368.0,1368.0,540842.0,684.0,1368.0,1368.0,528395.0,684.0,1368.0,1368.0,532847.0,684.0,1368.0,1368.0,545687.0,684.0,1368.0,1368.0,537912.0,742.0,1364.0,1364.0,522633.0,682.0,1364.0,1364.0,529822.0,682.0,1364.0,1364.0,539071.0,682.0,1364.0,1364.0,539757.0,701.0,1364.0,1364.0,531684.0,682.0,1364.0,1364.0,532581.0,682.0,1364.0,1364.0,548176.0,682.0,1364.0,1364.0,544569.0,682.0,1364.0,1364.0,529995.0,682.0,1364.0,1364.0,542462.0,682.0,1364.0,1364.0,540328.0,682.0,1364.0,1364.0,546443.0,682.0,1364.0,1364.0,534772.0,682.0,1364.0,1364.0,540022.0,682.0,1364.0,1364.0,548293.0,682.0,1364.0,1364.0,537971.0,740.0,1364.0,1364.0,522116.0,682.0,1364.0,1364.0,534570.0,682.0,1364.0,1364.0,525988.0,682.0,1364.0,1364.0,533200.0,682.0,1364.0,1364.0,525282.0,682.0,1364.0,1364.0,530236.0,682.0,1364.0,1364.0,539101.0,682.0,1364.0,1364.0,532376.0,740.0,1364.0,1364.0,524346.0,682.0,1364.0,1364.0,530667.0,682.0,1364.0,1364.0,540163.0,682.0,1364.0,1364.0,539296.0,701.0,1364.0,1364.0,531284.0,682.0,1364.0,1364.0,533764.0,682.0,1364.0,1364.0,548181.0,682.0,1364.0,1364.0,541978.0,682.0,1364.0,1364.0,546280.0,682.0,1364.0,1364.0,551883.0,682.0,1364.0,1364.0,546572.0,682.0,1364.0,1364.0,554393.0,701.0,1364.0,1364.0,556097.0,682.0,1364.0,1364.0,557718.0,682.0,1364.0,1364.0,563912.0,682.0,1364.0,1364.0,559049.0,682.0,1368.0,1368.0,526992.0,684.0,1368.0,1368.0,534971.0,684.0,1368.0,1368.0,541835.0,684.0,1368.0,1368.0,542685.0,684.0,1368.0,1368.0,539923.0,684.0,1368.0,1368.0,545449.0,684.0,1368.0,1368.0,557051.0,684.0,1368.0,1368.0,556856.0,742.0,1364.0,1364.0,537362.0,682.0,1364.0,1364.0,545368.0,682.0,1364.0,1364.0,552214.0,682.0,1364.0,1364.0,551742.0,682.0,1364.0,1364.0,546187.0,682.0,1364.0,1364.0,553806.0,682.0,1364.0,1364.0,561782.0,682.0,1364.0,1364.0,554829.0,740.0,1368.0,1368.0,529890.0,684.0,1368.0,1368.0,533261.0,684.0,1368.0,1368.0,536135.0,684.0,1368.0,1368.0,540424.0,703.0,1368.0,1368.0,527211.0,684.0,1368.0,1368.0,537228.0,684.0,1368.0,1368.0,548992.0,684.0,1368.0,1368.0,534877.0,684.0,64,0,6291456.0,65536.0,0.0,0.0,0.0,16384.0,0.0,0.0,0.0,0.0,16384.0,32768.0,53501.0,65602.0,12035.0,83865.0,0.0,0.0,0.0,0.0,64,0,0,1260.0,0.0,1368.0,805.0,0.0,1368.0,1261.0,0.0,1368.0,1336.0,0.0,1368.0,1342.0,0.0,1368.0,808.0,0.0,1368.0,1332.0,0.0,1368.0,971.0,0.0,1368.0,726.0,0.0,1364.0,728.0,0.0,1364.0,724.0,0.0,1364.0,726.0,0.0,1364.0,1181.0,0.0,1364.0,1184.0,0.0,1364.0,1275.0,0.0,1364.0,1247.0,0.0,1364.0,966.0,0.0,1368.0,942.0,0.0,1368.0,900.0,0.0,1368.0,885.0,0.0,1368.0,1197.0,0.0,1368.0,1174.0,0.0,1368.0,1291.0,0.0,1368.0,1268.0,0.0,1368.0,1097.0,0.0,1364.0,766.0,0.0,1364.0,1178.0,0.0,1364.0,1192.0,0.0,1364.0,1232.0,0.0,1364.0,769.0,0.0,1364.0,1209.0,0.0,1364.0,903.0,0.0,1364.0,768.0,0.0,1368.0,740.0,0.0,1368.0,754.0,0.0,1368.0,760.0,0.0,1368.0,1092.0,0.0,1368.0,1030.0,0.0,1368.0,1228.0,0.0,1368.0,1189.0,0.0,1368.0,1141.0,0.0,1364.0,905.0,0.0,1364.0,1264.0,0.0,1364.0,1253.0,0.0,1364.0,1233.0,0.0,1364.0,819.0,0.0,1364.0,1220.0,0.0,1364.0,983.0,0.0,1364.0,1026.0,0.0,1368.0,654.0,0.0,1368.0,1270.0,0.0,1368.0,1261.0,0.0,1368.0,1250.0,0.0,1368.0,664.0,0.0,1368.0,1252.0,0.0,1368.0,795.0,0.0,1368.0,904.0,0.0,1364.0,910.0,0.0,1364.0,925.0,0.0,1364.0,923.0,0.0,1364.0,1141.0,0.0,1364.0,1144.0,0.0,1364.0,1330.0,0.0,1364.0,1307.0,0.0,1364.0,708.0,0.0,1364.0,686.0,0.0,1364.0,687.0,0.0,1364.0,687.0,0.0,1364.0,1081.0,0.0,1364.0,1129.0,0.0,1364.0,1283.0,0.0,1364.0,1257.0,0.0,1364.0,1251.0,0.0,1364.0,788.0,0.0,1364.0,1334.0,0.0,1364.0,1348.0,0.0,1364.0,1331.0,0.0,1364.0,774.0,0.0,1364.0,1335.0,0.0,1364.0,951.0,0.0,1364.0,1110.0,0.0,1364.0,717.0,0.0,1364.0,1203.0,0.0,1364.0,1165.0,0.0,1364.0,1181.0,0.0,1364.0,733.0,0.0,1364.0,1242.0,0.0,1364.0,871.0,0.0,1364.0,917.0,0.0,1364.0,930.0,0.0,1364.0,937.0,0.0,1364.0,937.0,0.0,1364.0,1173.0,0.0,1364.0,1178.0,0.0,1364.0,1321.0,0.0,1364.0,1323.0,0.0,1364.0,64,0,0.0,49152.0,32768.0,65536.0,32768.0,0.0,0.0,0.0,12371.0,0.0,510.0,587052.0,78.0,0.0,0.0,0.0,66066.0,65536.0,131072.0,0.0,0.0,524288.0Line truncated
|
||||
1,11995,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,16384.0,16384.0,10013532.0,1030746.0,278528.0,0.0,0.0,98304.0,265424.0,0.0,0.0,462816.0,122548.0,32768.0,131072.0,131072.0,131072.0,0.0,0.0,524288.0,454479.0,1824.0,64,0,0,1368.0,1368.0,655899.0,684.0,1368.0,1368.0,679324.0,684.0,1368.0,1368.0,662825.0,684.0,1368.0,1368.0,670586.0,684.0,1368.0,1368.0,625332.0,684.0,1368.0,1368.0,633770.0,684.0,1368.0,1368.0,654758.0,684.0,1368.0,1368.0,639753.0,684.0,1364.0,1364.0,560868.0,682.0,1364.0,1364.0,571509.0,682.0,1364.0,1364.0,578519.0,682.0,1364.0,1364.0,580519.0,701.0,1364.0,1364.0,574237.0,682.0,1364.0,1364.0,577889.0,682.0,1364.0,1364.0,588009.0,682.0,1364.0,1364.0,584625.0,682.0,1364.0,1364.0,559408.0,682.0,1364.0,1364.0,567187.0,682.0,1364.0,1364.0,572395.0,682.0,1364.0,1364.0,572620.0,701.0,1364.0,1364.0,572457.0,682.0,1364.0,1364.0,575149.0,682.0,1364.0,1364.0,589747.0,682.0,1364.0,1364.0,585305.0,682.0,1364.0,1364.0,637370.0,682.0,1364.0,1364.0,657376.0,682.0,1364.0,1364.0,642937.0,682.0,1364.0,1364.0,652291.0,682.0,1364.0,1364.0,627166.0,682.0,1364.0,1364.0,645299.0,682.0,1364.0,1364.0,642152.0,682.0,1364.0,1364.0,627627.0,682.0,1364.0,1364.0,586142.0,682.0,1364.0,1364.0,603228.0,682.0,1364.0,1364.0,615673.0,682.0,1364.0,1364.0,619655.0,701.0,1364.0,1364.0,613988.0,682.0,1364.0,1364.0,628893.0,682.0,1364.0,1364.0,635292.0,682.0,1364.0,1364.0,633325.0,682.0,1364.0,1364.0,573445.0,682.0,1364.0,1364.0,589202.0,682.0,1364.0,1364.0,596227.0,682.0,1364.0,1364.0,598789.0,682.0,1364.0,1364.0,579316.0,682.0,1364.0,1364.0,582510.0,682.0,1364.0,1364.0,589929.0,682.0,1364.0,1364.0,584585.0,682.0,1368.0,1368.0,605995.0,684.0,1368.0,1368.0,620807.0,684.0,1368.0,1368.0,623761.0,684.0,1368.0,1368.0,632338.0,684.0,1368.0,1368.0,616628.0,684.0,1368.0,1368.0,620023.0,684.0,1368.0,1368.0,630596.0,684.0,1368.0,1368.0,622199.0,684.0,1364.0,1364.0,594633.0,682.0,1364.0,1364.0,608727.0,682.0,1364.0,1364.0,607747.0,682.0,1364.0,1364.0,609994.0,701.0,1364.0,1364.0,630570.0,682.0,1364.0,1364.0,631967.0,682.0,1364.0,1364.0,630426.0,682.0,1364.0,1364.0,635321.0,682.0,1368.0,1368.0,581195.0,684.0,1368.0,1368.0,594854.0,684.0,1368.0,1368.0,596794.0,684.0,1368.0,1368.0,605206.0,703.0,1368.0,1368.0,585585.0,684.0,1368.0,1368.0,594412.0,684.0,1368.0,1368.0,595696.0,684.0,1368.0,1368.0,593195.0,684.0,1364.0,1364.0,577615.0,682.0,1364.0,1364.0,593693.0,682.0,1364.0,1364.0,603376.0,682.0,1364.0,1364.0,594761.0,682.0,1364.0,1364.0,578522.0,682.0,1364.0,1364.0,588172.0,682.0,1364.0,1364.0,603815.0,682.0,1364.0,1364.0,597555.0,682.0,1364.0,1364.0,554205.0,682.0,1364.0,1364.0,562099.0,682.0,1364.0,1364.0,565704.0,682.0,1364.0,1364.0,564309.0,682.0,1364.0,1364.0,561031.0,682.0,1364.0,1364.0,565141.0,682.0,1364.0,1364.0,581908.0,682.0,1364.0,1364.0,579165.0,682.0,1368.0,1368.0,579237.0,684.0,1368.0,1368.0,584847.0,684.0,1368.0,1368.0,589765.0,684.0,1368.0,1368.0,597558.0,703.0,1368.0,1368.0,582643.0,684.0,1368.0,1368.0,601473.0,684.0,1368.0,1368.0,594095.0,684.0,1368.0,1368.0,590203.0,684.0,64,0,6291456.0,65536.0,0.0,0.0,0.0,16384.0,0.0,0.0,0.0,0.0,16384.0,32768.0,52716.0,65627.0,12820.0,97804.0,0.0,0.0,0.0,0.0,64,0,0,903.0,0.0,1364.0,900.0,0.0,1364.0,841.0,0.0,1364.0,827.0,0.0,1364.0,902.0,0.0,1364.0,906.0,0.0,1364.0,933.0,0.0,1364.0,886.0,0.0,1364.0,1448.0,0.0,1368.0,1510.0,0.0,1368.0,1427.0,0.0,1368.0,1468.0,0.0,1368.0,1332.0,0.0,1368.0,1323.0,0.0,1368.0,1432.0,0.0,1368.0,1404.0,0.0,1368.0,1279.0,0.0,1368.0,1340.0,0.0,1368.0,1223.0,0.0,1368.0,1181.0,0.0,1368.0,1168.0,0.0,1368.0,1209.0,0.0,1368.0,1350.0,0.0,1368.0,1306.0,0.0,1368.0,1122.0,0.0,1364.0,1131.0,0.0,1364.0,936.0,0.0,1364.0,1118.0,0.0,1364.0,1262.0,0.0,1364.0,1251.0,0.0,1364.0,1333.0,0.0,1364.0,1197.0,0.0,1364.0,1218.0,0.0,1364.0,1219.0,0.0,1364.0,1243.0,0.0,1364.0,1164.0,0.0,1364.0,1180.0,0.0,1364.0,1153.0,0.0,1364.0,1235.0,0.0,1364.0,1153.0,0.0,1364.0,1210.0,0.0,1368.0,1219.0,0.0,1368.0,1199.0,0.0,1368.0,1247.0,0.0,1368.0,1344.0,0.0,1368.0,1334.0,0.0,1368.0,1244.0,0.0,1368.0,1161.0,0.0,1368.0,1028.0,0.0,1364.0,1133.0,0.0,1364.0,1113.0,0.0,1364.0,1117.0,0.0,1364.0,1182.0,0.0,1364.0,1169.0,0.0,1364.0,1106.0,0.0,1364.0,1037.0,0.0,1364.0,1006.0,0.0,1364.0,1022.0,0.0,1364.0,1119.0,0.0,1364.0,1009.0,0.0,1364.0,892.0,0.0,1364.0,880.0,0.0,1364.0,1026.0,0.0,1364.0,1005.0,0.0,1364.0,1166.0,0.0,1364.0,1280.0,0.0,1364.0,1261.0,0.0,1364.0,1046.0,0.0,1364.0,1226.0,0.0,1364.0,1141.0,0.0,1364.0,1216.0,0.0,1364.0,1172.0,0.0,1364.0,1072.0,0.0,1364.0,1096.0,0.0,1364.0,1201.0,0.0,1364.0,1176.0,0.0,1364.0,1179.0,0.0,1364.0,1169.0,0.0,1364.0,1127.0,0.0,1364.0,1121.0,0.0,1364.0,1410.0,0.0,1368.0,1404.0,0.0,1368.0,1436.0,0.0,1368.0,1424.0,0.0,1368.0,1391.0,0.0,1368.0,1389.0,0.0,1368.0,1459.0,0.0,1368.0,1391.0,0.0,1368.0,837.0,0.0,1364.0,927.0,0.0,1364.0,913.0,0.0,1364.0,853.0,0.0,1364.0,922.0,0.0,1364.0,905.0,0.0,1364.0,887.0,0.0,1364.0,880.0,0.0,1364.0,64,0,0.0,49152.0,32768.0,65536.0,32768.0,0.0,0.0,0.0,8103.0,0.0,7646.0,555127.0,863.0,0.0,0.0,0.0,65740.0,65536.0,1Line truncated
|
||||
2,11995,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,16384.0,16384.0,9962715.0,975001.0,278528.0,0.0,0.0,98304.0,258378.0,0.0,0.0,441191.0,122110.0,32768.0,131072.0,131072.0,131072.0,0.0,0.0,524288.0,453394.0,1824.0,64,0,0,1364.0,1364.0,581549.0,682.0,1364.0,1364.0,593007.0,682.0,1364.0,1364.0,590215.0,682.0,1364.0,1364.0,598929.0,682.0,1364.0,1364.0,599286.0,682.0,1364.0,1364.0,598507.0,682.0,1364.0,1364.0,615814.0,682.0,1364.0,1364.0,606287.0,682.0,1364.0,1364.0,551160.0,682.0,1364.0,1364.0,558908.0,682.0,1364.0,1364.0,567221.0,682.0,1364.0,1364.0,563140.0,701.0,1364.0,1364.0,564185.0,682.0,1364.0,1364.0,569173.0,682.0,1364.0,1364.0,575742.0,682.0,1364.0,1364.0,573763.0,682.0,1364.0,1364.0,581888.0,682.0,1364.0,1364.0,590935.0,682.0,1364.0,1364.0,592923.0,682.0,1364.0,1364.0,594306.0,701.0,1364.0,1364.0,593370.0,682.0,1364.0,1364.0,599186.0,682.0,1364.0,1364.0,609180.0,682.0,1364.0,1364.0,611798.0,682.0,1364.0,1364.0,552699.0,682.0,1364.0,1364.0,562568.0,682.0,1364.0,1364.0,562887.0,682.0,1364.0,1364.0,569041.0,682.0,1364.0,1364.0,560641.0,682.0,1364.0,1364.0,566382.0,682.0,1364.0,1364.0,573252.0,682.0,1364.0,1364.0,567403.0,682.0,1364.0,1364.0,572973.0,682.0,1364.0,1364.0,575627.0,682.0,1364.0,1364.0,610483.0,682.0,1364.0,1364.0,611201.0,701.0,1364.0,1364.0,588891.0,682.0,1364.0,1364.0,592120.0,682.0,1364.0,1364.0,613191.0,682.0,1364.0,1364.0,615509.0,682.0,1368.0,1368.0,604664.0,684.0,1368.0,1368.0,619847.0,684.0,1368.0,1368.0,622870.0,684.0,1368.0,1368.0,628577.0,684.0,1368.0,1368.0,606383.0,684.0,1368.0,1368.0,634607.0,684.0,1368.0,1368.0,640866.0,684.0,1368.0,1368.0,626136.0,684.0,1364.0,1364.0,595644.0,682.0,1364.0,1364.0,615993.0,682.0,1364.0,1364.0,615306.0,682.0,1364.0,1364.0,610915.0,682.0,1364.0,1364.0,599437.0,682.0,1364.0,1364.0,613835.0,682.0,1364.0,1364.0,626925.0,682.0,1364.0,1364.0,612861.0,682.0,1368.0,1368.0,604436.0,684.0,1368.0,1368.0,605582.0,684.0,1368.0,1368.0,640114.0,684.0,1368.0,1368.0,628983.0,703.0,1368.0,1368.0,608648.0,684.0,1368.0,1368.0,610690.0,684.0,1368.0,1368.0,630804.0,684.0,1368.0,1368.0,624050.0,684.0,1368.0,1368.0,590629.0,684.0,1368.0,1368.0,599443.0,684.0,1368.0,1368.0,604793.0,684.0,1368.0,1368.0,608788.0,703.0,1368.0,1368.0,592446.0,684.0,1368.0,1368.0,607418.0,684.0,1368.0,1368.0,606684.0,684.0,1368.0,1368.0,602122.0,684.0,1364.0,1364.0,558268.0,682.0,1364.0,1364.0,566166.0,682.0,1364.0,1364.0,576751.0,682.0,1364.0,1364.0,570488.0,682.0,1364.0,1364.0,574877.0,682.0,1364.0,1364.0,577336.0,682.0,1364.0,1364.0,582760.0,682.0,1364.0,1364.0,576283.0,682.0,1368.0,1368.0,578259.0,684.0,1368.0,1368.0,585985.0,684.0,1368.0,1368.0,596204.0,684.0,1368.0,1368.0,594385.0,684.0,1368.0,1368.0,592923.0,684.0,1368.0,1368.0,598755.0,684.0,1368.0,1368.0,604588.0,684.0,1368.0,1368.0,600474.0,684.0,1364.0,1364.0,553196.0,682.0,1364.0,1364.0,568263.0,682.0,1364.0,1364.0,583454.0,682.0,1364.0,1364.0,573116.0,701.0,1364.0,1364.0,561679.0,682.0,1364.0,1364.0,569663.0,682.0,1364.0,1364.0,575468.0,682.0,1364.0,1364.0,571044.0,682.0,64,0,6291456.0,65536.0,0.0,0.0,0.0,16384.0,0.0,0.0,0.0,0.0,16384.0,32768.0,52759.0,65615.0,12777.0,97552.0,0.0,0.0,0.0,0.0,64,0,0,1122.0,0.0,1364.0,1150.0,0.0,1364.0,1169.0,0.0,1364.0,1164.0,0.0,1364.0,1280.0,0.0,1364.0,1248.0,0.0,1364.0,1375.0,0.0,1364.0,1308.0,0.0,1364.0,1252.0,0.0,1368.0,1098.0,0.0,1368.0,1162.0,0.0,1368.0,1097.0,0.0,1368.0,1123.0,0.0,1368.0,1058.0,0.0,1368.0,1232.0,0.0,1368.0,1187.0,0.0,1368.0,1178.0,0.0,1364.0,1165.0,0.0,1364.0,1208.0,0.0,1364.0,1190.0,0.0,1364.0,1170.0,0.0,1364.0,1165.0,0.0,1364.0,1227.0,0.0,1364.0,1203.0,0.0,1364.0,1329.0,0.0,1368.0,1292.0,0.0,1368.0,1277.0,0.0,1368.0,1326.0,0.0,1368.0,1348.0,0.0,1368.0,1322.0,0.0,1368.0,1340.0,0.0,1368.0,1254.0,0.0,1368.0,886.0,0.0,1364.0,1051.0,0.0,1364.0,1056.0,0.0,1364.0,1042.0,0.0,1364.0,954.0,0.0,1364.0,930.0,0.0,1364.0,980.0,0.0,1364.0,963.0,0.0,1364.0,1032.0,0.0,1364.0,1033.0,0.0,1364.0,1050.0,0.0,1364.0,1057.0,0.0,1364.0,1077.0,0.0,1364.0,1061.0,0.0,1364.0,1122.0,0.0,1364.0,1041.0,0.0,1364.0,981.0,0.0,1364.0,960.0,0.0,1364.0,959.0,0.0,1364.0,830.0,0.0,1364.0,1055.0,0.0,1364.0,1033.0,0.0,1364.0,1058.0,0.0,1364.0,974.0,0.0,1364.0,1147.0,0.0,1364.0,1103.0,0.0,1364.0,1130.0,0.0,1364.0,907.0,0.0,1364.0,1064.0,0.0,1364.0,1055.0,0.0,1364.0,1003.0,0.0,1364.0,1117.0,0.0,1364.0,977.0,0.0,1364.0,937.0,0.0,1364.0,1109.0,0.0,1364.0,990.0,0.0,1364.0,944.0,0.0,1364.0,933.0,0.0,1364.0,1080.0,0.0,1364.0,1058.0,0.0,1364.0,1547.0,0.0,1368.0,1553.0,0.0,1368.0,1512.0,0.0,1368.0,1516.0,0.0,1368.0,1504.0,0.0,1368.0,1490.0,0.0,1368.0,1555.0,0.0,1368.0,1499.0,0.0,1368.0,930.0,0.0,1364.0,941.0,0.0,1364.0,950.0,0.0,1364.0,914.0,0.0,1364.0,1067.0,0.0,1364.0,1059.0,0.0,1364.0,1012.0,0.0,1364.0,942.0,0.0,1364.0,1379.0,0.0,1368.0,1392.0,0.0,1368.0,1446.0,0.0,1368.0,1386.0,0.0,1368.0,1291.0,0.0,1368.0,1279.0,0.0,1368.0,1423.0,0.0,1368.0,1401.0,0.0,1368.0,64,0,0.0,49152.0,32768.0,65536.0,32768.0,0.0,0.0,0.0,8213.0,0.0,7599.0,609220.0,0.0,0.0,0.0,0.0,65728.0,65536.0,131072.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
|
||||
dispatch_2,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Wed 29 May 2024 01:36:08 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
|
||||
1,11995,1,146305,146305,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370067592,73646370075364,0
|
||||
3,11995,1,146305,146305,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370113222,73646370119351,0
|
||||
2,11995,1,146305,146305,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",73646370091949,73646370098199,0
|
||||
|
@@ -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
|
||||
0,60633,1,964651,964651,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250185980750,716250185996629,0,445034.0,445034.0,16384.0,65536.0,35311.0,2824232.0
|
||||
1,60633,1,964651,964651,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250186019509,716250186033267,0,409556.0,409556.0,16384.0,65536.0,12992.0,1048576.0
|
||||
2,60633,1,964651,964651,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250186053586,716250186067426,0,369883.0,369883.0,16384.0,65536.0,13128.0,1048576.0
|
||||
|
@@ -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
|
||||
0,60633,1,964663,964663,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250185980750,716250185996629,0,0.0,0.0,0.0
|
||||
1,60633,1,964663,964663,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250186019509,716250186033267,0,0.0,0.0,0.0
|
||||
2,60633,1,964663,964663,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250186053586,716250186067426,0,0.0,0.0,0.0
|
||||
|
@@ -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
|
||||
0,60633,1,964675,964675,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250185980750,716250185996629,0,65536.0,3944090.0,315488968.0
|
||||
1,60633,1,964675,964675,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250186019509,716250186033267,0,65536.0,3617558.0,289330136.0
|
||||
2,60633,1,964675,964675,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250186053586,716250186067426,0,65536.0,3495734.0,279597328.0
|
||||
|
@@ -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
|
||||
0,60633,1,964687,964687,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250185980750,716250185996629,0,32768.0,510457.0,40831868.0
|
||||
1,60633,1,964687,964687,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250186019509,716250186033267,0,32768.0,382581.0,30601624.0
|
||||
2,60633,1,964687,964687,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250186053586,716250186067426,0,32768.0,348139.0,27857520.0
|
||||
|
@@ -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
|
||||
0,60633,1,964700,964700,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250185980750,716250185996629,0,577249.0,577249.0,316007.0,2308996.0,16384.0,34957599.0,562816.0,0.0,140189340.0
|
||||
1,60633,1,964700,964700,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250186019509,716250186033267,0,415641.0,415641.0,244236.0,1662564.0,16384.0,29686735.0,481490.0,0.0,119099552.0
|
||||
2,60633,1,964700,964700,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250186053586,716250186067426,0,357965.0,357965.0,189759.0,1431860.0,16384.0,29243119.0,479688.0,0.0,117325408.0
|
||||
|
@@ -0,0 +1,230 @@
|
||||
Omniperf version: 2.0.0
|
||||
Profiler choice: rocprofv2
|
||||
Path: /home/colramos/omniperf/tests/workloads/dispatch_2/MI300X_A1
|
||||
Target: MI300X_A1
|
||||
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
|
||||
Kernel Selection: None
|
||||
Dispatch Selection: ['1']
|
||||
Hardware Blocks: All
|
||||
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
Collecting Performance Counters
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_ACCUM_PREV_HIRES
|
||||
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|-> [/opt/rocm/bin/rocprofv2] vcopy testing on GCD 0
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the CPU
|
||||
|-> [/opt/rocm/bin/rocprofv2] Finished allocating vectors on the GPU
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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/dispatch_2/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
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_ICACHE_HITS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_ICACHE_MISSES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_ICACHE_MISSES_DUPLICATE
|
||||
|-> [/opt/rocm/bin/rocprofv2] Enabling Counter Collection
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_HITS
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_MISSES
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQC_DCACHE_MISSES_DUPLICATE
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_CYCLE[1]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_EA0_RDREQ_32B[1]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_READ[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_REQ[1]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_TOO_MANY_EA_WRREQS_STALL[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_WRITE[1]
|
||||
|-> [/opt/rocm/bin/rocprofv2] - TCC_TAG_STALL[2]
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_TRANS_F32
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_ADD_F64
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_VALU_MUL_F64
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|-> [/opt/rocm/bin/rocprofv2] - SQ_INSTS_LDS
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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/dispatch_2/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
|
||||
|
||||
[profiling] Current input file: tests/workloads/dispatch_2/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: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_ATOMIC[0] TCC_BUBBLE[0] TCC_CYCLE[0] TCC_EA0_ATOMIC[0] TCC_ATOMIC[1] TCC_BUBBLE[1] TCC_CYCLE[1] TCC_EA0_ATOMIC[1] TCC_ATOMIC[2] TCC_BUBBLE[2] TCC_CYCLE[2] TCC_EA0_ATOMIC[2] TCC_ATOMIC[3] TCC_BUBBLE[3] TCC_CYCLE[3] TCC_EA0_ATOMIC[3] TCC_ATOMIC[4] TCC_BUBBLE[4] TCC_CYCLE[4] TCC_EA0_ATOMIC[4] TCC_ATOMIC[5] TCC_BUBBLE[5] TCC_CYCLE[5] TCC_EA0_ATOMIC[5] TCC_ATOMIC[6] TCC_BUBBLE[6] TCC_CYCLE[6] TCC_EA0_ATOMIC[6] TCC_ATOMIC[7] TCC_BUBBLE[7] TCC_CYCLE[7] TCC_EA0_ATOMIC[7] TCC_ATOMIC[8] TCC_BUBBLE[8] TCC_CYCLE[8] TCC_EA0_ATOMIC[8] TCC_ATOMIC[9] TCC_BUBBLE[9] TCC_CYCLE[9] TCC_EA0_ATOMIC[9] TCC_ATOMIC[10] TCC_BUBBLE[10] TCC_CYCLE[10] TCC_EA0_ATOMIC[10] TCC_ATOMIC[11] TCC_BUBBLE[11] TCC_CYCLE[11] TCC_EA0_ATOMIC[11] TCC_ATOMIC[12] TCC_BUBBLE[12] TCC_CYCLE[12] TCC_EA0_ATOMIC[12] TCC_ATOMIC[13] TCC_BUBBLE[13] TCC_CYCLE[13] TCC_EA0_ATOMIC[13] TCC_ATOMIC[14] TCC_BUBBLE[14] TCC_CYCLE[14] TCC_EA0_ATOMIC[14] TCC_ATOMIC[15] TCC_BUBBLE[15] TCC_CYCLE[15] TCC_EA0_ATOMIC[15]
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_EA0_ATOMIC_LEVEL[0] TCC_EA0_RDREQ[0] TCC_EA0_RDREQ_32B[0] TCC_EA0_RDREQ_LEVEL[0] TCC_EA0_ATOMIC_LEVEL[1] TCC_EA0_RDREQ[1] TCC_EA0_RDREQ_32B[1] TCC_EA0_RDREQ_LEVEL[1] TCC_EA0_ATOMIC_LEVEL[2] TCC_EA0_RDREQ[2] TCC_EA0_RDREQ_32B[2] TCC_EA0_RDREQ_LEVEL[2] TCC_EA0_ATOMIC_LEVEL[3] TCC_EA0_RDREQ[3] TCC_EA0_RDREQ_32B[3] TCC_EA0_RDREQ_LEVEL[3] TCC_EA0_ATOMIC_LEVEL[4] TCC_EA0_RDREQ[4] TCC_EA0_RDREQ_32B[4] TCC_EA0_RDREQ_LEVEL[4] TCC_EA0_ATOMIC_LEVEL[5] TCC_EA0_RDREQ[5] TCC_EA0_RDREQ_32B[5] TCC_EA0_RDREQ_LEVEL[5] TCC_EA0_ATOMIC_LEVEL[6] TCC_EA0_RDREQ[6] TCC_EA0_RDREQ_32B[6] TCC_EA0_RDREQ_LEVEL[6] TCC_EA0_ATOMIC_LEVEL[7] TCC_EA0_RDREQ[7] TCC_EA0_RDREQ_32B[7] TCC_EA0_RDREQ_LEVEL[7] TCC_EA0_ATOMIC_LEVEL[8] TCC_EA0_RDREQ[8] TCC_EA0_RDREQ_32B[8] TCC_EA0_RDREQ_LEVEL[8] TCC_EA0_ATOMIC_LEVEL[9] TCC_EA0_RDREQ[9] TCC_EA0_RDREQ_32B[9] TCC_EA0_RDREQ_LEVEL[9] TCC_EA0_ATOMIC_LEVEL[10] TCC_EA0_RDREQ[10] TCC_EA0_RDREQ_32B[10] TCC_EA0_RDREQ_LEVEL[10] TCC_EA0_ATOMIC_LEVEL[11] TCC_EA0_RDREQ[11] TCC_EA0_RDREQ_32B[11] TCC_EA0_RDREQ_LEVEL[11] TCC_EA0_ATOMIC_LEVEL[12] TCC_EA0_RDREQ[12] TCC_EA0_RDREQ_32B[12] TCC_EA0_RDREQ_LEVEL[12] TCC_EA0_ATOMIC_LEVEL[13] TCC_EA0_RDREQ[13] TCC_EA0_RDREQ_32B[13] TCC_EA0_RDREQ_LEVEL[13] TCC_EA0_ATOMIC_LEVEL[14] TCC_EA0_RDREQ[14] TCC_EA0_RDREQ_32B[14] TCC_EA0_RDREQ_LEVEL[14] TCC_EA0_ATOMIC_LEVEL[15] TCC_EA0_RDREQ[15] TCC_EA0_RDREQ_32B[15] TCC_EA0_RDREQ_LEVEL[15]
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_EA0_WRREQ[0] TCC_EA0_WRREQ_64B[0] TCC_EA0_WRREQ_LEVEL[0] TCC_HIT[0] TCC_EA0_WRREQ[1] TCC_EA0_WRREQ_64B[1] TCC_EA0_WRREQ_LEVEL[1] TCC_HIT[1] TCC_EA0_WRREQ[2] TCC_EA0_WRREQ_64B[2] TCC_EA0_WRREQ_LEVEL[2] TCC_HIT[2] TCC_EA0_WRREQ[3] TCC_EA0_WRREQ_64B[3] TCC_EA0_WRREQ_LEVEL[3] TCC_HIT[3] TCC_EA0_WRREQ[4] TCC_EA0_WRREQ_64B[4] TCC_EA0_WRREQ_LEVEL[4] TCC_HIT[4] TCC_EA0_WRREQ[5] TCC_EA0_WRREQ_64B[5] TCC_EA0_WRREQ_LEVEL[5] TCC_HIT[5] TCC_EA0_WRREQ[6] TCC_EA0_WRREQ_64B[6] TCC_EA0_WRREQ_LEVEL[6] TCC_HIT[6] TCC_EA0_WRREQ[7] TCC_EA0_WRREQ_64B[7] TCC_EA0_WRREQ_LEVEL[7] TCC_HIT[7] TCC_EA0_WRREQ[8] TCC_EA0_WRREQ_64B[8] TCC_EA0_WRREQ_LEVEL[8] TCC_HIT[8] TCC_EA0_WRREQ[9] TCC_EA0_WRREQ_64B[9] TCC_EA0_WRREQ_LEVEL[9] TCC_HIT[9] TCC_EA0_WRREQ[10] TCC_EA0_WRREQ_64B[10] TCC_EA0_WRREQ_LEVEL[10] TCC_HIT[10] TCC_EA0_WRREQ[11] TCC_EA0_WRREQ_64B[11] TCC_EA0_WRREQ_LEVEL[11] TCC_HIT[11] TCC_EA0_WRREQ[12] TCC_EA0_WRREQ_64B[12] TCC_EA0_WRREQ_LEVEL[12] TCC_HIT[12] TCC_EA0_WRREQ[13] TCC_EA0_WRREQ_64B[13] TCC_EA0_WRREQ_LEVEL[13] TCC_HIT[13] TCC_EA0_WRREQ[14] TCC_EA0_WRREQ_64B[14] TCC_EA0_WRREQ_LEVEL[14] TCC_HIT[14] TCC_EA0_WRREQ[15] TCC_EA0_WRREQ_64B[15] TCC_EA0_WRREQ_LEVEL[15] TCC_HIT[15]
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_RW_REQ[0] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_RW_REQ[1] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_RW_REQ[2] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_RW_REQ[3] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_RW_REQ[4] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_RW_REQ[5] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_RW_REQ[6] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_RW_REQ[7] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_RW_REQ[8] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_RW_REQ[9] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_RW_REQ[10] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_RW_REQ[11] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_RW_REQ[12] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_RW_REQ[13] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_RW_REQ[14] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_RW_REQ[15]
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_TAG_STALL[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_TAG_STALL[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_TAG_STALL[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_TAG_STALL[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_TAG_STALL[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_TAG_STALL[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_TAG_STALL[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_TAG_STALL[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_TAG_STALL[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_TAG_STALL[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_TAG_STALL[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_TAG_STALL[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_TAG_STALL[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_TAG_STALL[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_TAG_STALL[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_TAG_STALL[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15]
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA0_WRREQ_sum TCC_EA0_WRREQ_64B_sum TCC_EA0_WR_UNCACHED_32B_sum TCC_EA0_WRREQ_DRAM_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCC_READ_REQ_sum TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA0_RDREQ_sum TCC_EA0_RDREQ_32B_sum TCC_BUBBLE_sum TCC_EA0_RD_UNCACHED_32B_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_NC_READ_REQ_sum TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA0_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_UC_WRITE_REQ_sum TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA0_ATOMIC_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_CC_ATOMIC_REQ_sum TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA0_RDREQ_LEVEL_sum TCC_EA0_WRREQ_LEVEL_sum TCC_EA0_ATOMIC_LEVEL_sum TCC_EA0_WRREQ_STALL_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ TCP_PENDING_STALL_CYCLES_sum
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc:
|
||||
|
||||
gpu:
|
||||
range: 1
|
||||
kernel:
|
||||
@@ -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)",0,2977390.0,0.0,0.0,65536.0,60576.0,160.0,4800.0,32768.0,64,0,0,0.0,512.0,48058.0,0.0,0.0,512.0,48058.0,0.0,0.0,512.0,48058.0,0.0,0.0,512.0,48058.0,0.0,0.0,512.0,48058.0,0.0,0.0,512.0,48058.0,0.0,0.0,512.0,48058.0,0.0,0.0,512.0,48058.0,0.0,0.0,512.0,48058.0,0.0,0.0,512.0,48058.0,0.0,0.0,512.0,48058.0,0.0,0.0,512.0,48058.0,0.0,0.0,512.0,48058.0,0.0,0.0,512.0,48058.0,0.0,0.0,512.0,48058.0,0.0,0.0,512.0,48058.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,46332.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,58215.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,70518.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,88380.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,95791.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,98908.0,0.0,0.0,512.0,107980.0,0.0,0.0,512.0,107980.0,0.0,0.0,512.0,107980.0,0.0,0.0,512.0,107980.0,0.0,0.0,512.0,107980.0,0.0,0.0,512.0,107980.0,0.0,0.0,512.0,107980.0,0.0,0.0,512.0,107980.0,0.0,0.0,512.0,107980.0,0.0,0.0,512.0,107980.0,0.0,0.0,512.0,107980.0,0.0,0.0,512.0,107980.0,0.0,0.0,512.0,107980.0,0.0,0.0,512.0,107980.0,0.0,0.0,512.0,107980.0,0.0,0.0,512.0,107980.0,0.0,64,0,0.0,0.0,1048576.0,0.0,0.0,0.0,0.0,0.0,0.0,32768.0,0.0,16384.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,64,0,131072.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,16384.0,0.0,0.0,88784719.0,45555558.0,80607.0,0.0,0.0,65536.0,131072.0,64,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,119713.0,29906.0,2103775.0,696.0,0.0,463487.0,0.0,0.0,66160.0,131310.0,197470.0,0.0,2097152.0,1048576.0,1048576.0,2097152.0,0.0,16384.0,64,0,0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,592.0,1616.0,1616.0,1024.0,512.0,1536.0,1536.0,1027.0,515.0,1539.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,592.0,1616.0,1616.0,1024.0,512.0,1536.0,1536.0,1028.0,516.0,1540.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,592.0,1616.0,1616.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,592.0,1616.0,1616.0,1024.0,512.0,1536.0,1536.0,1027.0,515.0,1539.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024Line truncated
|
||||
1,60633,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,2848691.0,0.0,0.0,65536.0,60576.0,160.0,4800.0,32768.0,64,0,0,0.0,512.0,42485.0,0.0,0.0,512.0,42485.0,0.0,0.0,512.0,42485.0,0.0,0.0,512.0,42485.0,0.0,0.0,512.0,42485.0,0.0,0.0,512.0,42485.0,0.0,0.0,512.0,42485.0,0.0,0.0,512.0,42485.0,0.0,0.0,512.0,42485.0,0.0,0.0,512.0,42485.0,0.0,0.0,512.0,42485.0,0.0,0.0,512.0,42485.0,0.0,0.0,512.0,42485.0,0.0,0.0,512.0,42485.0,0.0,0.0,512.0,42485.0,0.0,0.0,512.0,42485.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,32759.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,53918.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,61145.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,73159.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,81406.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,83453.0,0.0,0.0,512.0,91731.0,0.0,0.0,512.0,91731.0,0.0,0.0,512.0,91731.0,0.0,0.0,512.0,91731.0,0.0,0.0,512.0,91731.0,0.0,0.0,512.0,91731.0,0.0,0.0,512.0,91731.0,0.0,0.0,512.0,91731.0,0.0,0.0,512.0,91731.0,0.0,0.0,512.0,91731.0,0.0,0.0,512.0,91731.0,0.0,0.0,512.0,91731.0,0.0,0.0,512.0,91731.0,0.0,0.0,512.0,91731.0,0.0,0.0,512.0,91731.0,0.0,0.0,512.0,91731.0,0.0,64,0,0.0,0.0,1048576.0,0.0,0.0,0.0,0.0,0.0,0.0,32768.0,0.0,16384.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,64,0,131072.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,16384.0,0.0,0.0,46028365.0,63675461.0,220868.0,0.0,0.0,65536.0,131072.0,64,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,48276.0,28869.0,2423468.0,10525.0,0.0,309450.0,0.0,0.0,65536.0,131319.0,196855.0,0.0,2097152.0,1048576.0,1048576.0,2097152.0,0.0,16384.0,64,0,0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,515.0,1539.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1027.0,515.0,1539.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1026.0,514.0,1538.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1027.0,515.0,1539.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.Line truncated
|
||||
2,60633,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",0,3024458.0,0.0,0.0,65536.0,60576.0,160.0,4800.0,32768.0,64,0,0,0.0,512.0,42189.0,0.0,0.0,512.0,42189.0,0.0,0.0,512.0,42189.0,0.0,0.0,512.0,42189.0,0.0,0.0,512.0,42189.0,0.0,0.0,512.0,42189.0,0.0,0.0,512.0,42189.0,0.0,0.0,512.0,42189.0,0.0,0.0,512.0,42189.0,0.0,0.0,512.0,42189.0,0.0,0.0,512.0,42189.0,0.0,0.0,512.0,42189.0,0.0,0.0,512.0,42189.0,0.0,0.0,512.0,42189.0,0.0,0.0,512.0,42189.0,0.0,0.0,512.0,42189.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,36027.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,56301.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,62904.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,77519.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85418.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,85553.0,0.0,0.0,512.0,94244.0,0.0,0.0,512.0,94244.0,0.0,0.0,512.0,94244.0,0.0,0.0,512.0,94244.0,0.0,0.0,512.0,94244.0,0.0,0.0,512.0,94244.0,0.0,0.0,512.0,94244.0,0.0,0.0,512.0,94244.0,0.0,0.0,512.0,94244.0,0.0,0.0,512.0,94244.0,0.0,0.0,512.0,94244.0,0.0,0.0,512.0,94244.0,0.0,0.0,512.0,94244.0,0.0,0.0,512.0,94244.0,0.0,0.0,512.0,94244.0,0.0,0.0,512.0,94244.0,0.0,64,0,0.0,0.0,1048576.0,0.0,0.0,0.0,0.0,0.0,0.0,32768.0,0.0,16384.0,0.0,0.0,25.0,0.0,0.0,0.0,0.0,0.0,64,0,131072.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,16384.0,0.0,0.0,40162747.0,48276212.0,99646.0,0.0,0.0,65536.0,131072.0,64,0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,43504.0,26817.0,1999347.0,9497.0,0.0,275004.0,0.0,0.0,65536.0,131323.0,196859.0,0.0,2097152.0,1048576.0,1048576.0,2097152.0,0.0,16384.0,64,0,0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1027.0,515.0,1539.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1028.0,516.0,1540.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1025.0,513.0,1537.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1024.0,512.0,1536.0,1536.0,1026.0,514.0,1538.0,1536.0,1024.0,512.0,1536.0,1536.0,1044.0,532.0,1556.0,1536.0,1024.0,512.0,1536.0Line 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
|
||||
dispatch_2,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Wed 29 May 2024 12:00:59 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
|
||||
1,60633,1,964929,964929,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250185980750,716250185996629,0
|
||||
2,60633,1,964929,964929,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250186019509,716250186033267,0
|
||||
3,60633,1,964929,964929,1048576,256,0,0,4,4,16,64,"vecCopy(double*, double*, double*, int, int) (.kd)",716250186053586,716250186067426,0
|
||||
|
Reference in new issue
Bloquear um usuário