35ef8c0707
Signed-off-by: Jose Santos <josantos@amd.com>
4.8 KiB
4.8 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 | wave_size_1 | obj_1 | SQC_DCACHE_REQ_READ_1 | SQC_DCACHE_REQ_READ_2 | SQC_DCACHE_REQ_READ_4 | 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 | wave_size_3 | obj_3 | 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_4 | obj_4 | 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 | CPC_CPC_TCIU_BUSY | CPC_CPC_TCIU_IDLE | wave_size_5 | obj_5 | 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_6 | obj_6 | 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 | CPC_CPC_STAT_STALL | CPC_UTCL1_STALL_ON_TRANSLATION | wave_size_7 | obj_7 | 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_8 | obj_8 | 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 | CPC_CPC_UTCL2IU_BUSY | CPC_CPC_UTCL2IU_IDLE | wave_size_9 | obj_9 | 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 | CPC_CPC_UTCL2IU_STALL | CPC_ME1_BUSY_FOR_PACKET_DECODE | wave_size_10 | obj_10 | 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 | CPC_ME1_DC0_SPI_BUSY | wave_size_11 | obj_11 | 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 | wave_size_12 | obj_12 | 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 | CPC_CPC_STAT_BUSY | CPC_CPC_STAT_IDLE | Start_Timestamp | End_Timestamp |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | vecCopy(double*, double*, double*, int, int) | 2 | 1048576 | 256 | 0 | 0 | 8 | 0 | 16 | 64 | 0x7f5c00d38ec0 | 0 | 0 | 1048576 | 0 | 0 | 0 | 0 | 0 | 64 | 0x7f969f5b8ec0 | 32768 | 32768 | 0 | 64 | 0x7f4f8e064ec0 | 65536 | 0 | 0 | 0 | 16384 | 16384 | 0 | 0 | 64 | 0x7f8b5522cec0 | 1309 | 118813 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 64 | 0x7f01b1a78ec0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 352 | 26713 | 64 | 0x7fd799508ec0 | 0 | 0 | 0 | 0 | 0 | 0 | 168 | 56 | 64 | 0x7f2fd4028ec0 | 0 | 0 | 0 | 0 | 114688 | 0 | 65536 | 32768 | 6975 | 545 | 64 | 0x7f92067f8ec0 | 0 | 0 | 0 | 224 | 0 | 65536 | 64281 | 56 | 64 | 0x7f07c3da4ec0 | 0 | 0 | 0 | 16384 | 16384 | 10962787 | 9750506 | 868217 | 819 | 27095 | 64 | 0x7f1dfa30cec0 | 344064 | 222320 | 129677 | 1638076 | 0 | 0 | 163840 | 114688 | 0 | 10897 | 64 | 0x7f2afe650ec0 | 0 | 32768 | 32768 | 16384 | 16384 | 65536 | 49152 | 10485760 | 14976 | 64 | 0x7fe928480ec0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 64 | 0x7f2dd787cec0 | 0 | 16384 | 16384 | 32768 | 49152 | 0 | 393216 | 163840 | 28084 | 28084 | 28084 | 0 | 199354805603573 | 199354805623573 |
| 3 | 1 | vecCopy(double*, double*, double*, int, int) | 2 | 1048576 | 256 | 0 | 0 | 8 | 0 | 16 | 64 | 0x7f5c00d38ec0 | 0 | 0 | 1048576 | 0 | 0 | 0 | 0 | 0 | 64 | 0x7f969f5b8ec0 | 32768 | 32768 | 0 | 64 | 0x7f4f8e064ec0 | 65536 | 0 | 0 | 0 | 16384 | 16384 | 0 | 0 | 64 | 0x7f8b5522cec0 | 0 | 184208 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 64 | 0x7f01b1a78ec0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 302 | 40076 | 64 | 0x7fd799508ec0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 56 | 64 | 0x7f2fd4028ec0 | 0 | 0 | 0 | 0 | 114688 | 0 | 65536 | 32768 | 9493 | 3123 | 64 | 0x7f92067f8ec0 | 0 | 0 | 0 | 56 | 0 | 65536 | 65536 | 0 | 64 | 0x7f07c3da4ec0 | 0 | 0 | 0 | 16384 | 16384 | 20187209 | 18709486 | 1133659 | 3400 | 39163 | 64 | 0x7f1dfa30cec0 | 344064 | 335088 | 226311 | 2849726 | 0 | 0 | 163840 | 114688 | 0 | 13257 | 64 | 0x7f2afe650ec0 | 0 | 32768 | 32768 | 16384 | 16384 | 65536 | 49152 | 10485760 | 25389 | 64 | 0x7fe928480ec0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 64 | 0x7f2dd787cec0 | 0 | 16384 | 16384 | 32768 | 49152 | 0 | 393216 | 163840 | 43103 | 43103 | 43103 | 0 | 199354805693333 | 199354805709493 |
| 4 | 2 | vecCopy(double*, double*, double*, int, int) | 2 | 1048576 | 256 | 0 | 0 | 8 | 0 | 16 | 64 | 0x7f5c00d38ec0 | 0 | 0 | 1048576 | 0 | 0 | 0 | 0 | 0 | 64 | 0x7f969f5b8ec0 | 32768 | 32768 | 0 | 64 | 0x7f4f8e064ec0 | 65536 | 0 | 0 | 0 | 16384 | 16384 | 0 | 0 | 64 | 0x7f8b5522cec0 | 0 | 186988 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 64 | 0x7f01b1a78ec0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 302 | 40301 | 64 | 0x7fd799508ec0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 56 | 64 | 0x7f2fd4028ec0 | 0 | 0 | 0 | 0 | 114688 | 0 | 65536 | 32768 | 9501 | 3093 | 64 | 0x7f92067f8ec0 | 0 | 0 | 0 | 56 | 0 | 65536 | 65536 | 0 | 64 | 0x7f07c3da4ec0 | 0 | 0 | 0 | 16384 | 16384 | 19566197 | 18340038 | 882095 | 3396 | 38395 | 64 | 0x7f1dfa30cec0 | 344064 | 329504 | 221551 | 2765990 | 0 | 0 | 163840 | 114688 | 0 | 13935 | 64 | 0x7f2afe650ec0 | 0 | 32768 | 32768 | 16384 | 16384 | 65536 | 49152 | 10485760 | 25246 | 64 | 0x7fe928480ec0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 64 | 0x7f2dd787cec0 | 0 | 16384 | 16384 | 32768 | 49152 | 0 | 393216 | 163840 | 43655 | 43655 | 43655 | 0 | 199354805729173 | 199354805744853 |