35ef8c0707
Signed-off-by: Jose Santos <josantos@amd.com>
5.2 KiB
5.2 KiB
| 1 | Dispatch_ID | Kernel_Name | GPU_ID | Grid_Size | Workgroup_Size | LDS_Per_Workgroup | Scratch_Per_Workitem | Arch_VGPR | Accum_VGPR | SGPR | wave_size | obj | 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 | TA_FLAT_WRITE_WAVEFRONTS_sum | TA_FLAT_ATOMIC_WAVEFRONTS_sum | wave_size_1 | obj_1 | SQC_TC_DATA_WRITE_REQ | SQC_TC_DATA_ATOMIC_REQ | SQC_TC_STALL | SQC_TC_REQ | SQC_DCACHE_REQ_READ_16 | SQC_ICACHE_REQ | SQC_ICACHE_HITS | SQC_ICACHE_MISSES | wave_size_2 | obj_2 | SQ_IFETCH | SQ_LDS_BANK_CONFLICT | SQ_LDS_ADDR_CONFLICT | SQ_LDS_UNALIGNED_STALL | SQ_WAVES | SQ_WAVES_EQ_64 | SQ_WAVES_LT_64 | SQ_WAVES_LT_48 | TA_FLAT_WAVEFRONTS_sum | TA_FLAT_READ_WAVEFRONTS_sum | wave_size_3 | obj_3 | SQ_ACTIVE_INST_ANY | SQ_CYCLES | SQ_BUSY_CYCLES | SQ_BUSY_CU_CYCLES | SQ_ACTIVE_INST_VMEM | SQ_ACTIVE_INST_LDS | SQ_ACTIVE_INST_VALU | SQ_ACTIVE_INST_SCA | TA_ADDR_STALLED_BY_TC_CYCLES_sum | TA_TOTAL_WAVEFRONTS_sum | wave_size_4 | obj_4 | SQ_INSTS_VALU_CVT | SQ_INSTS_VMEM_WR | SQ_INSTS_VMEM_RD | SQ_INSTS_VMEM | SQ_INSTS_SALU | SQ_INSTS_VSKIPPED | SQ_INSTS | SQ_INSTS_VALU | GRBM_COUNT | GRBM_GUI_ACTIVE | TA_TA_BUSY_sum | TA_BUFFER_WAVEFRONTS_sum | wave_size_5 | obj_5 | SQ_INSTS_LDS | SQ_INSTS_GDS | SQ_INSTS_EXP_GDS | SQ_INSTS_BRANCH | SQ_INSTS_SENDMSG | SQ_WAVE_CYCLES | SQ_WAIT_ANY | SQ_WAIT_INST_ANY | TA_BUFFER_COALESCED_READ_CYCLES_sum | TA_BUFFER_COALESCED_WRITE_CYCLES_sum | wave_size_6 | obj_6 | SQC_DCACHE_REQ_READ_1 | SQC_DCACHE_REQ_READ_2 | SQC_DCACHE_REQ_READ_4 | wave_size_7 | obj_7 | 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 | SQ_THREAD_CYCLES_VALU | TA_ADDR_STALLED_BY_TD_CYCLES_sum | TA_DATA_STALLED_BY_TC_CYCLES_sum | wave_size_8 | obj_8 | SQ_INSTS_VALU_ADD_F64 | SQ_INSTS_VALU_MUL_F64 | SQ_INSTS_VALU_FMA_F64 | SQ_INSTS_VALU_TRANS_F64 | SQ_INSTS_VALU_INT32 | SQ_INSTS_VALU_INT64 | SQ_INSTS_SMEM | SQ_INSTS_FLAT | TA_BUFFER_ATOMIC_WAVEFRONTS_sum | TA_BUFFER_TOTAL_CYCLES_sum | wave_size_9 | obj_9 | SQ_INSTS_VALU_ADD_F16 | SQ_INSTS_VALU_MUL_F16 | SQ_INSTS_VALU_FMA_F16 | SQ_INSTS_VALU_TRANS_F16 | SQ_INSTS_VALU_ADD_F32 | SQ_INSTS_VALU_MUL_F32 | SQ_INSTS_VALU_FMA_F32 | SQ_INSTS_VALU_TRANS_F32 | TA_BUFFER_READ_WAVEFRONTS_sum | TA_BUFFER_WRITE_WAVEFRONTS_sum | wave_size_10 | obj_10 | SQ_INSTS_FLAT_LDS_ONLY | SQ_INSTS_VALU_MFMA_MOPS_I8 | SQ_INSTS_VALU_MFMA_MOPS_F16 | SQ_INSTS_VALU_MFMA_MOPS_BF16 | SQ_INSTS_VALU_MFMA_MOPS_F32 | SQ_INSTS_VALU_MFMA_MOPS_F64 | SQC_TC_INST_REQ | SQC_TC_DATA_READ_REQ | wave_size_11 | obj_11 | SQC_ICACHE_MISSES_DUPLICATE | SQC_DCACHE_INPUT_VALID_READYB | SQC_DCACHE_ATOMIC | SQC_DCACHE_REQ_READ_8 | SQC_DCACHE_REQ | SQC_DCACHE_HITS | SQC_DCACHE_MISSES | SQC_DCACHE_MISSES_DUPLICATE | wave_size_12 | obj_12 | 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 | Start_Timestamp | End_Timestamp |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | vecCopy(double*, double*, double*, int, int) | 2 | 1048576 | 256 | 0 | 0 | 8 | 0 | 16 | 64 | 0x7f7151634ec0 | 0 | 0 | 1048576 | 0 | 0 | 0 | 0 | 0 | 16384.0 | 0.0 | 64 | 0x7f61b0404ec0 | 0 | 0 | 0 | 224 | 0 | 65536 | 64209 | 56 | 64 | 0x7f84a35c4ec0 | 65536 | 0 | 0 | 0 | 16384 | 16384 | 0 | 0 | 32768.0 | 16384.0 | 64 | 0x7fa133074ec0 | 344064 | 226464 | 134756 | 1702621 | 0 | 0 | 163840 | 114688 | 259449.0 | 32768.0 | 64 | 0x7ff1a5bd8ec0 | 0 | 16384 | 16384 | 32768 | 49152 | 0 | 393216 | 163840 | 27784 | 27784 | 1038475.0 | 0.0 | 64 | 0x7fb51c518ec0 | 0 | 0 | 0 | 16384 | 16384 | 10612853 | 9512844 | 755945 | 0.0 | 0.0 | 64 | 0x7fdf34ae4ec0 | 32768 | 32768 | 0 | 64 | 0x7f4c20ba8ec0 | 0 | 32768 | 32768 | 16384 | 16384 | 65536 | 49152 | 10485760 | 0.0 | 225616.0 | 64 | 0x7f0416f28ec0 | 0 | 0 | 0 | 0 | 114688 | 0 | 65536 | 32768 | 0.0 | 0.0 | 64 | 0x7fdd9bf3cec0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 64 | 0x7f0a3d084ec0 | 0 | 0 | 0 | 0 | 0 | 0 | 168 | 56 | 64 | 0x7fb675a04ec0 | 1308 | 119573 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 64 | 0x7f142814cec0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 197636385194490 | 197636385214970 |
| 3 | 1 | vecCopy(double*, double*, double*, int, int) | 2 | 1048576 | 256 | 0 | 0 | 8 | 0 | 16 | 64 | 0x7f7151634ec0 | 0 | 0 | 1048576 | 0 | 0 | 0 | 0 | 0 | 16384.0 | 0.0 | 64 | 0x7f61b0404ec0 | 0 | 0 | 0 | 56 | 0 | 65536 | 65536 | 0 | 64 | 0x7f84a35c4ec0 | 65536 | 0 | 0 | 0 | 16384 | 16384 | 0 | 0 | 32768.0 | 16384.0 | 64 | 0x7fa133074ec0 | 344064 | 299936 | 206150 | 2558989 | 0 | 0 | 163840 | 114688 | 446443.0 | 32768.0 | 64 | 0x7ff1a5bd8ec0 | 0 | 16384 | 16384 | 32768 | 49152 | 0 | 393216 | 163840 | 38484 | 38484 | 1736112.0 | 0.0 | 64 | 0x7fb51c518ec0 | 0 | 0 | 0 | 16384 | 16384 | 17686698 | 17104122 | 238512 | 0.0 | 0.0 | 64 | 0x7fdf34ae4ec0 | 32768 | 32768 | 0 | 64 | 0x7f4c20ba8ec0 | 0 | 32768 | 32768 | 16384 | 16384 | 65536 | 49152 | 10485760 | 0.0 | 470988.0 | 64 | 0x7f0416f28ec0 | 0 | 0 | 0 | 0 | 114688 | 0 | 65536 | 32768 | 0.0 | 0.0 | 64 | 0x7fdd9bf3cec0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 64 | 0x7f0a3d084ec0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 56 | 64 | 0x7fb675a04ec0 | 0 | 192083 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 64 | 0x7f142814cec0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 197636385234650 | 197636385250330 |
| 4 | 2 | vecCopy(double*, double*, double*, int, int) | 2 | 1048576 | 256 | 0 | 0 | 8 | 0 | 16 | 64 | 0x7f7151634ec0 | 0 | 0 | 1048576 | 0 | 0 | 0 | 0 | 0 | 16384.0 | 0.0 | 64 | 0x7f61b0404ec0 | 0 | 0 | 0 | 56 | 0 | 65536 | 65536 | 0 | 64 | 0x7f84a35c4ec0 | 65536 | 0 | 0 | 0 | 16384 | 16384 | 0 | 0 | 32768.0 | 16384.0 | 64 | 0x7fa133074ec0 | 344064 | 337144 | 231351 | 2886370 | 0 | 0 | 163840 | 114688 | 625844.0 | 32768.0 | 64 | 0x7ff1a5bd8ec0 | 0 | 16384 | 16384 | 32768 | 49152 | 0 | 393216 | 163840 | 40532 | 40532 | 1638787.0 | 0.0 | 64 | 0x7fb51c518ec0 | 0 | 0 | 0 | 16384 | 16384 | 19861626 | 18505828 | 1011734 | 0.0 | 0.0 | 64 | 0x7fdf34ae4ec0 | 32768 | 32768 | 0 | 64 | 0x7f4c20ba8ec0 | 0 | 32768 | 32768 | 16384 | 16384 | 65536 | 49152 | 10485760 | 0.0 | 492901.0 | 64 | 0x7f0416f28ec0 | 0 | 0 | 0 | 0 | 114688 | 0 | 65536 | 32768 | 0.0 | 0.0 | 64 | 0x7fdd9bf3cec0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 64 | 0x7f0a3d084ec0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 56 | 64 | 0x7fb675a04ec0 | 0 | 190677 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 64 | 0x7f142814cec0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 197636385313530 | 197636385329850 |