35ef8c0707
Signed-off-by: Jose Santos <josantos@amd.com>
4.1 KiB
4.1 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_SAVED | SQ_INSTS_SMEM_NORM | SQC_TC_INST_REQ | SQC_TC_DATA_READ_REQ | SQC_TC_DATA_WRITE_REQ | SQC_TC_DATA_ATOMIC_REQ | SQC_TC_STALL | SQC_TC_REQ | TA_FLAT_WAVEFRONTS_sum | TA_FLAT_READ_WAVEFRONTS_sum | wave_size_1 | obj_1 | SQ_CYCLES | SQ_BUSY_CYCLES | SQ_BUSY_CU_CYCLES | SQ_WAVES | SQ_WAVE_CYCLES | SQ_INSTS_VMEM_WR | SQ_INSTS_VMEM_RD | SQ_INSTS_VMEM | GRBM_COUNT | GRBM_GUI_ACTIVE | TA_TA_BUSY_sum | TA_BUFFER_WAVEFRONTS_sum | wave_size_2 | obj_2 | SQ_INSTS_SALU | SQ_INSTS_VSKIPPED | SQ_INSTS_SMEM | SQ_INSTS_FLAT | SQ_INSTS_LDS | SQ_INSTS_GDS | SQ_INSTS_EXP_GDS | SQ_INSTS_BRANCH | TA_BUFFER_READ_WAVEFRONTS_sum | TA_BUFFER_WRITE_WAVEFRONTS_sum | wave_size_3 | obj_3 | SQ_ACTIVE_INST_VALU | 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 | TA_BUFFER_COALESCED_READ_CYCLES_sum | TA_BUFFER_COALESCED_WRITE_CYCLES_sum | wave_size_4 | obj_4 | SQ_WAVES_LT_48 | 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 | TA_ADDR_STALLED_BY_TD_CYCLES_sum | TA_DATA_STALLED_BY_TC_CYCLES_sum | wave_size_5 | obj_5 | SQ_INST_CYCLES_SALU | 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 | TA_ADDR_STALLED_BY_TC_CYCLES_sum | TA_TOTAL_WAVEFRONTS_sum | wave_size_6 | obj_6 | SQC_DCACHE_REQ | SQC_DCACHE_HITS | SQC_DCACHE_MISSES | SQC_DCACHE_MISSES_DUPLICATE | SQC_DCACHE_REQ_READ_1 | SQC_DCACHE_REQ_READ_2 | SQC_DCACHE_REQ_READ_4 | wave_size_7 | obj_7 | SQC_DCACHE_REQ_READ_16 | SQC_ICACHE_REQ | SQC_ICACHE_HITS | SQC_ICACHE_MISSES | SQC_ICACHE_MISSES_DUPLICATE | SQC_DCACHE_INPUT_VALID_READYB | SQC_DCACHE_ATOMIC | SQC_DCACHE_REQ_READ_8 | TA_FLAT_WRITE_WAVEFRONTS_sum | TA_FLAT_ATOMIC_WAVEFRONTS_sum | wave_size_8 | obj_8 | SQ_INSTS_SENDMSG | SQ_INSTS | SQ_WAIT_ANY | SQ_WAIT_INST_ANY | SQ_ACTIVE_INST_ANY | SQ_INSTS_VALU | SQ_ACTIVE_INST_VMEM | SQ_ACTIVE_INST_LDS | TA_BUFFER_ATOMIC_WAVEFRONTS_sum | TA_BUFFER_TOTAL_CYCLES_sum | Start_Timestamp | End_Timestamp |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | vecCopy(double*, double*, double*, int, int) | 2 | 1048576 | 256 | 0 | 0 | 8 | 8 | 16 | 64 | 0x7f57df22ce80 | 0 | 131072 | 144 | 48 | 0 | 0 | 0 | 192 | 32768.0 | 16384.0 | 64 | 0x7f578ac6ce80 | 384208 | 233514 | 3414819 | 16384 | 25361297 | 16384 | 16384 | 32768 | 48025 | 48025 | 2054029.0 | 0.0 | 64 | 0x7f152ac70e80 | 49152 | 0 | 65536 | 32768 | 0 | 0 | 0 | 16384 | 0.0 | 0.0 | 64 | 0x7fb03f932e80 | 180224 | 114688 | 0 | 32768 | 32768 | 16384 | 16384 | 65536 | 0.0 | 0.0 | 64 | 0x7fecd7b64e80 | 0 | 0 | 0 | 1048576 | 0 | 0 | 0 | 0 | 0.0 | 580352.0 | 64 | 0x7f53aa404e80 | 49152 | 11534336 | 65536 | 0 | 0 | 0 | 16384 | 0 | 931521.0 | 32768.0 | 64 | 0x7ff4bf300e80 | 65536 | 64048 | 48 | 1440 | 32768 | 32768 | 0 | 64 | 0x7f0c6b402e80 | 0 | 65536 | 64480 | 48 | 1358 | 185497 | 0 | 0 | 16384.0 | 0.0 | 64 | 0x7fd299446e80 | 16384 | 393216 | 22671296 | 1650806 | 360448 | 163840 | 0 | 0 | 0.0 | 0.0 | 194093425213997 | 194093425237997 |
| 3 | 1 | vecCopy(double*, double*, double*, int, int) | 2 | 1048576 | 256 | 0 | 0 | 8 | 8 | 16 | 64 | 0x7f57df22ce80 | 0 | 131072 | 0 | 48 | 0 | 0 | 0 | 48 | 32768.0 | 16384.0 | 64 | 0x7f578ac6ce80 | 341200 | 231657 | 3384515 | 16384 | 25334508 | 16384 | 16384 | 32768 | 42649 | 42649 | 2136241.0 | 0.0 | 64 | 0x7f152ac70e80 | 49152 | 0 | 65536 | 32768 | 0 | 0 | 0 | 16384 | 0.0 | 0.0 | 64 | 0x7fb03f932e80 | 180224 | 114688 | 0 | 32768 | 32768 | 16384 | 16384 | 65536 | 0.0 | 0.0 | 64 | 0x7fecd7b64e80 | 0 | 0 | 0 | 1048576 | 0 | 0 | 0 | 0 | 0.0 | 615386.0 | 64 | 0x7f53aa404e80 | 49152 | 11534336 | 65536 | 0 | 0 | 0 | 16384 | 0 | 1137406.0 | 32768.0 | 64 | 0x7ff4bf300e80 | 65536 | 64048 | 48 | 1440 | 32768 | 32768 | 0 | 64 | 0x7f0c6b402e80 | 0 | 65536 | 65536 | 0 | 0 | 190996 | 0 | 0 | 16384.0 | 0.0 | 64 | 0x7fd299446e80 | 16384 | 393216 | 23016849 | 1129850 | 360448 | 163840 | 0 | 0 | 0.0 | 0.0 | 194093425324077 | 194093425343117 |
| 4 | 2 | vecCopy(double*, double*, double*, int, int) | 2 | 1048576 | 256 | 0 | 0 | 8 | 8 | 16 | 64 | 0x7f57df22ce80 | 0 | 131072 | 0 | 48 | 0 | 0 | 0 | 48 | 32768.0 | 16384.0 | 64 | 0x7f578ac6ce80 | 349200 | 233179 | 3382702 | 16384 | 24402589 | 16384 | 16384 | 32768 | 43649 | 43649 | 2132975.0 | 0.0 | 64 | 0x7f152ac70e80 | 49152 | 0 | 65536 | 32768 | 0 | 0 | 0 | 16384 | 0.0 | 0.0 | 64 | 0x7fb03f932e80 | 180224 | 114688 | 0 | 32768 | 32768 | 16384 | 16384 | 65536 | 0.0 | 0.0 | 64 | 0x7fecd7b64e80 | 0 | 0 | 0 | 1048576 | 0 | 0 | 0 | 0 | 0.0 | 626002.0 | 64 | 0x7f53aa404e80 | 49152 | 11534336 | 65536 | 0 | 0 | 0 | 16384 | 0 | 960706.0 | 32768.0 | 64 | 0x7ff4bf300e80 | 65536 | 64048 | 48 | 1440 | 32768 | 32768 | 0 | 64 | 0x7f0c6b402e80 | 0 | 65536 | 65536 | 0 | 0 | 190685 | 0 | 0 | 16384.0 | 0.0 | 64 | 0x7fd299446e80 | 16384 | 393216 | 22578421 | 1415558 | 360448 | 163840 | 0 | 0 | 0.0 | 0.0 | 194093425365197 | 194093425384237 |