updating Pytest mark and tests/workloads

Signed-off-by: Jose Santos <josantos@login1.hpcfund>
This commit is contained in:
Jose Santos
2024-02-21 12:49:32 -06:00
committed by Karl W. Schulz
parent 4f96837157
commit b018d9207f
116 changed files with 499 additions and 1 deletions
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,1329746,1329746,1048576,256,0,0,8,8,16,64,0x0,0x7ff36005ce80,49853,49853,16384,65536,13040,1680908,5862031958679664,5862046126501116,5862046126524956,5862031966293896
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,1329746,1329746,1048576,256,0,0,8,8,16,64,0x0,0x7ff36005ce80,113546,113546,16384,65536,8251,1048576,5862031966316188,5862046126616796,5862046126635516,5862031966678814
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,1329746,1329746,1048576,256,0,0,8,8,16,64,0x0,0x7ff36005ce80,47978,47978,16384,65536,8069,1048584,5862031966711406,5862046126657436,5862046126676476,5862031966894302
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 1329746 1329746 1048576 256 0 0 8 8 16 64 0x0 0x7ff36005ce80 49853 49853 16384 65536 13040 1680908 5862031958679664 5862046126501116 5862046126524956 5862031966293896
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 1329746 1329746 1048576 256 0 0 8 8 16 64 0x0 0x7ff36005ce80 113546 113546 16384 65536 8251 1048576 5862031966316188 5862046126616796 5862046126635516 5862031966678814
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 1329746 1329746 1048576 256 0 0 8 8 16 64 0x0 0x7ff36005ce80 47978 47978 16384 65536 8069 1048584 5862031966711406 5862046126657436 5862046126676476 5862031966894302
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,1328531,1328531,1048576,256,0,0,8,8,16,64,0x0,0x7f64b2038e80,0,0,0,5862026052994063,5862046126501116,5862046126524956,5862026060638081
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,1328531,1328531,1048576,256,0,0,8,8,16,64,0x0,0x7f64b2038e80,0,0,0,5862026060659161,5862046126616796,5862046126635516,5862026060957375
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,1328531,1328531,1048576,256,0,0,8,8,16,64,0x0,0x7f64b2038e80,0,0,0,5862026060985809,5862046126657436,5862046126676476,5862026061154438
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 1328531 1328531 1048576 256 0 0 8 8 16 64 0x0 0x7f64b2038e80 0 0 0 5862026052994063 5862046126501116 5862046126524956 5862026060638081
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 1328531 1328531 1048576 256 0 0 8 8 16 64 0x0 0x7f64b2038e80 0 0 0 5862026060659161 5862046126616796 5862046126635516 5862026060957375
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 1328531 1328531 1048576 256 0 0 8 8 16 64 0x0 0x7f64b2038e80 0 0 0 5862026060985809 5862046126657436 5862046126676476 5862026061154438
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,1328329,1328329,1048576,256,0,0,8,8,16,64,0x0,0x7fdff6a24e80,65536,185356,23718656,5862025131935600,5862046126501116,5862046126524956,5862025140185344
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,1328329,1328329,1048576,256,0,0,8,8,16,64,0x0,0x7fdff6a24e80,65536,188418,24213280,5862025140195654,5862046126616796,5862046126635516,5862025140512263
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,1328329,1328329,1048576,256,0,0,8,8,16,64,0x0,0x7fdff6a24e80,65536,175286,22402288,5862025140540476,5862046126657436,5862046126676476,5862025140712692
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 1328329 1328329 1048576 256 0 0 8 8 16 64 0x0 0x7fdff6a24e80 65536 185356 23718656 5862025131935600 5862046126501116 5862046126524956 5862025140185344
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 1328329 1328329 1048576 256 0 0 8 8 16 64 0x0 0x7fdff6a24e80 65536 188418 24213280 5862025140195654 5862046126616796 5862046126635516 5862025140512263
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 1328329 1328329 1048576 256 0 0 8 8 16 64 0x0 0x7fdff6a24e80 65536 175286 22402288 5862025140540476 5862046126657436 5862046126676476 5862025140712692
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,1330557,1330557,1048576,256,0,0,8,8,16,64,0x0,0x7f6ef60aae80,32768,646195,82717292,5862035909155076,5862046126501116,5862046126524956,5862035917308328
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,1330557,1330557,1048576,256,0,0,8,8,16,64,0x0,0x7f6ef60aae80,32768,679196,86941576,5862035917329729,5862046126616796,5862046126635516,5862035917590542
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,1330557,1330557,1048576,256,0,0,8,8,16,64,0x0,0x7f6ef60aae80,32768,648200,82969328,5862035917619637,5862046126657436,5862046126676476,5862035917766324
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 1330557 1330557 1048576 256 0 0 8 8 16 64 0x0 0x7f6ef60aae80 32768 646195 82717292 5862035909155076 5862046126501116 5862046126524956 5862035917308328
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 1330557 1330557 1048576 256 0 0 8 8 16 64 0x0 0x7f6ef60aae80 32768 679196 86941576 5862035917329729 5862046126616796 5862046126635516 5862035917590542
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 1330557 1330557 1048576 256 0 0 8 8 16 64 0x0 0x7f6ef60aae80 32768 648200 82969328 5862035917619637 5862046126657436 5862046126676476 5862035917766324
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,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,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,1331365,1331365,1048576,256,0,0,8,8,16,64,0x0,0x7ff38955ee80,48726,48726,15960,389816,16384,25298259,237438,0,101737392,5862039834232768,5862046126501116,5862046126524956,5862039841771177
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,1331365,1331365,1048576,256,0,0,8,8,16,64,0x0,0x7ff38955ee80,42346,42346,13239,338776,16384,25180426,231129,0,101259708,5862039841799491,5862046126616796,5862046126635516,5862039842117172
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,1331365,1331365,1048576,256,0,0,8,8,16,64,0x0,0x7ff38955ee80,43098,43098,13945,344792,16384,25427869,236168,0,102246936,5862039842156836,5862046126657436,5862046126676476,5862039842351986
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj 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 DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 1331365 1331365 1048576 256 0 0 8 8 16 64 0x0 0x7ff38955ee80 48726 48726 15960 389816 16384 25298259 237438 0 101737392 5862039834232768 5862046126501116 5862046126524956 5862039841771177
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 1331365 1331365 1048576 256 0 0 8 8 16 64 0x0 0x7ff38955ee80 42346 42346 13239 338776 16384 25180426 231129 0 101259708 5862039841799491 5862046126616796 5862046126635516 5862039842117172
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 1331365 1331365 1048576 256 0 0 8 8 16 64 0x0 0x7ff38955ee80 43098 43098 13945 344792 16384 25427869 236168 0 102246936 5862039842156836 5862046126657436 5862046126676476 5862039842351986
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
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:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
gpu:
range:
kernel:
@@ -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 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_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_EA_ATOMIC_LEVEL_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31]
gpu:
range:
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 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS_SMEM 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 SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS SQ_WAIT_ANY 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_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_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_EA_WRREQ_STALL_sum TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: 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 SQ_IFETCH TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_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_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel:
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID
0,"vecCopy(double*, double*, double*, int, int)",2
1,"vecCopy(double*, double*, double*, int, int)",2
2,"vecCopy(double*, double*, double*, int, int)",2
1 Dispatch_ID Kernel_Name GPU_ID
2 0 vecCopy(double*, double*, double*, int, int) 2
3 1 vecCopy(double*, double*, double*, int, int) 2
4 2 vecCopy(double*, double*, double*, int, int) 2
File diff suppressed because one or more lines are too long
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,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,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2506192,2506192,1048576,256,0,0,8,8,16,64,0x0,0x7f6d00ddce80,387944,231876,3381429,16384,24479957,144,48,0,48492,48492,3829962.0,2956311.0,7779.0,1218015.0,2028935.0,0.0,2947718.0,2636032.0,386879,241828,48492,0,48492,0,1551744.0,970309.0,0.0,0.0,5255486636623607,5255477523602709,5255477523626869,5255486644675676
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2506192,2506192,1048576,256,0,0,8,8,16,64,0x0,0x7f6d00ddce80,347176,226940,3324691,16384,24507650,0,48,0,43396,43396,3693477.0,3028337.0,5682.0,1119280.0,2040456.0,0.0,3019418.0,2707688.0,347168,236471,43396,0,43396,0,1388672.0,825503.0,0.0,0.0,5255486645190559,5255477523727189,5255477523745909,5255486645761069
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2506192,2506192,1048576,256,0,0,8,8,16,64,0x0,0x7f6d00ddce80,336256,224102,3276450,16384,24165791,0,48,0,42031,42031,3650603.0,2996298.0,6116.0,1082593.0,2000564.0,0.0,2987361.0,2675741.0,336248,233309,42031,0,42031,0,1344992.0,808442.0,0.0,0.0,5255486646287654,5255477523767029,5255477523785909,5255486646790496
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ 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 DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2506192 2506192 1048576 256 0 0 8 8 16 64 0x0 0x7f6d00ddce80 387944 231876 3381429 16384 24479957 144 48 0 48492 48492 3829962.0 2956311.0 7779.0 1218015.0 2028935.0 0.0 2947718.0 2636032.0 386879 241828 48492 0 48492 0 1551744.0 970309.0 0.0 0.0 5255486636623607 5255477523602709 5255477523626869 5255486644675676
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2506192 2506192 1048576 256 0 0 8 8 16 64 0x0 0x7f6d00ddce80 347176 226940 3324691 16384 24507650 0 48 0 43396 43396 3693477.0 3028337.0 5682.0 1119280.0 2040456.0 0.0 3019418.0 2707688.0 347168 236471 43396 0 43396 0 1388672.0 825503.0 0.0 0.0 5255486645190559 5255477523727189 5255477523745909 5255486645761069
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2506192 2506192 1048576 256 0 0 8 8 16 64 0x0 0x7f6d00ddce80 336256 224102 3276450 16384 24165791 0 48 0 42031 42031 3650603.0 2996298.0 6116.0 1082593.0 2000564.0 0.0 2987361.0 2675741.0 336248 233309 42031 0 42031 0 1344992.0 808442.0 0.0 0.0 5255486646287654 5255477523767029 5255477523785909 5255486646790496
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,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,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_COALESCABLE_WAVEFRONT_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,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2503804,2503804,1048576,256,0,0,8,8,16,64,0x0,0x7fce2c1f6e80,0,0,192,0,65536,64463,48,1328,31457,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,566,47595,1753,0,48.0,267.0,0.0,262288.0,5255475603740413,5255477523602709,5255477523626869,5255475611599657
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2503804,2503804,1048576,256,0,0,8,8,16,64,0x0,0x7fce2c1f6e80,0,0,48,0,65536,65536,0,0,31418,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,485,43362,1692,0,48.0,260.0,0.0,262144.0,5255475612116504,5255477523727189,5255477523745909,5255475612678297
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2503804,2503804,1048576,256,0,0,8,8,16,64,0x0,0x7fce2c1f6e80,0,0,48,0,65536,65536,0,0,30785,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,484,42117,1769,0,48.0,292.0,0.0,262144.0,5255475613204502,5255477523767029,5255477523785909,5255475613684550
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj 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 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_COALESCABLE_WAVEFRONT_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 DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2503804 2503804 1048576 256 0 0 8 8 16 64 0x0 0x7fce2c1f6e80 0 0 192 0 65536 64463 48 1328 31457 0.0 0.0 0.0 32768.0 0.0 0.0 0.0 32768.0 4096 16384 566 47595 1753 0 48.0 267.0 0.0 262288.0 5255475603740413 5255477523602709 5255477523626869 5255475611599657
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2503804 2503804 1048576 256 0 0 8 8 16 64 0x0 0x7fce2c1f6e80 0 0 48 0 65536 65536 0 0 31418 0.0 0.0 0.0 32768.0 0.0 0.0 0.0 32768.0 4096 16384 485 43362 1692 0 48.0 260.0 0.0 262144.0 5255475612116504 5255477523727189 5255477523745909 5255475612678297
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2503804 2503804 1048576 256 0 0 8 8 16 64 0x0 0x7fce2c1f6e80 0 0 48 0 65536 65536 0 0 30785 0.0 0.0 0.0 32768.0 0.0 0.0 0.0 32768.0 4096 16384 484 42117 1769 0 48.0 292.0 0.0 262144.0 5255475613204502 5255477523767029 5255477523785909 5255475613684550
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,TCC_EA_ATOMIC_LEVEL_sum,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2502411,2502411,1048576,256,0,0,8,8,16,64,0x0,0x7fbad2a9ee80,0.0,5255468851933661,5255477523602709,5255477523626869,5255468859346622
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2502411,2502411,1048576,256,0,0,8,8,16,64,0x0,0x7fbad2a9ee80,0.0,5255468859371759,5255477523727189,5255477523745909,5255468859732853
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2502411,2502411,1048576,256,0,0,8,8,16,64,0x0,0x7fbad2a9ee80,0.0,5255468859766997,5255477523767029,5255477523785909,5255468859987274
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj TCC_EA_ATOMIC_LEVEL_sum DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2502411 2502411 1048576 256 0 0 8 8 16 64 0x0 0x7fbad2a9ee80 0.0 5255468851933661 5255477523602709 5255477523626869 5255468859346622
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2502411 2502411 1048576 256 0 0 8 8 16 64 0x0 0x7fbad2a9ee80 0.0 5255468859371759 5255477523727189 5255477523745909 5255468859732853
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2502411 2502411 1048576 256 0 0 8 8 16 64 0x0 0x7fbad2a9ee80 0.0 5255468859766997 5255477523767029 5255477523785909 5255468859987274
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2502809,2502809,1048576,256,0,0,8,8,16,64,0x0,0x7f6beb8d6e80,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,0,48711,0,0,5255471044333015,5255477523602709,5255477523626869,5255471052065240
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2502809,2502809,1048576,256,0,0,8,8,16,64,0x0,0x7f6beb8d6e80,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,0,43055,0,0,5255471052133319,5255477523727189,5255477523745909,5255471052654826
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2502809,2502809,1048576,256,0,0,8,8,16,64,0x0,0x7f6beb8d6e80,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,0,42511,0,0,5255471052732092,5255477523767029,5255477523785909,5255471053044382
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2502809 2502809 1048576 256 0 0 8 8 16 64 0x0 0x7f6beb8d6e80 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 0 48711 0 0 5255471044333015 5255477523602709 5255477523626869 5255471052065240
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2502809 2502809 1048576 256 0 0 8 8 16 64 0x0 0x7f6beb8d6e80 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 0 43055 0 0 5255471052133319 5255477523727189 5255477523745909 5255471052654826
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2502809 2502809 1048576 256 0 0 8 8 16 64 0x0 0x7f6beb8d6e80 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 0 42511 0 0 5255471052732092 5255477523767029 5255477523785909 5255471053044382
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2502609,2502609,1048576,256,0,0,8,8,16,64,0x0,0x7f12c929ee80,4096,0,1630,0,4096,0,1318,0,4099,0,1107,0,4096,0,668,0,4096,0,850,0,4187,0,1462,0,4096,0,2185,0,4096,0,96,0,4096,0,937,0,4096,0,1065,0,4144,0,2608,0,4096,0,1315,0,4097,0,379,0,4096,0,2310,0,4096,0,1631,0,4096,0,18,0,4096,0,1714,0,4096,0,1709,0,4096,0,2055,0,4096,0,1403,0,4096,0,430,0,4096,0,1888,0,4096,0,429,0,4096,0,798,0,4096,0,206,0,4096,0,1680,0,4096,0,723,0,4096,0,596,0,4096,0,269,0,4096,0,1847,0,4144,0,1351,0,4096,0,5627,0,5255469945486487,5255477523602709,5255477523626869,5255469953250101
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2502609,2502609,1048576,256,0,0,8,8,16,64,0x0,0x7f12c929ee80,4096,0,24,0,4096,0,3641,0,4096,0,6674,0,4096,0,1381,0,4097,0,55,0,4188,0,116,0,4096,0,3627,0,4096,0,1530,0,4096,0,134,0,4096,0,33,0,4144,0,1747,0,4097,0,2094,0,4097,0,1110,0,4096,0,459,0,4096,0,2537,0,4096,0,71,0,4096,0,1573,0,4096,0,3596,0,4096,0,7691,0,4099,0,760,0,4096,0,158,0,4096,0,990,0,4096,0,1453,0,4097,0,2110,0,4096,0,0,0,4096,0,5352,0,4096,0,875,0,4096,0,56,0,4096,0,0,0,4096,0,0,0,4144,0,86,0,4096,0,249,0,5255469953316807,5255477523727189,5255477523745909,5255469953869372
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2502609,2502609,1048576,256,0,0,8,8,16,64,0x0,0x7f12c929ee80,4096,0,7377,0,4096,0,523,0,4096,0,90,0,4096,0,850,0,4097,0,0,0,4171,0,3051,0,4096,0,936,0,4096,0,1156,0,4096,0,0,0,4096,0,0,0,4144,0,0,0,4097,0,976,0,4097,0,299,0,4096,0,669,0,4096,0,393,0,4096,0,433,0,4096,0,1504,0,4096,0,96,0,4096,0,156,0,4099,0,948,0,4096,0,0,0,4096,0,1299,0,4096,0,744,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4144,0,0,0,4096,0,0,0,5255469953947330,5255477523767029,5255477523785909,5255469954345823
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2502609 2502609 1048576 256 0 0 8 8 16 64 0x0 0x7f12c929ee80 4096 0 1630 0 4096 0 1318 0 4099 0 1107 0 4096 0 668 0 4096 0 850 0 4187 0 1462 0 4096 0 2185 0 4096 0 96 0 4096 0 937 0 4096 0 1065 0 4144 0 2608 0 4096 0 1315 0 4097 0 379 0 4096 0 2310 0 4096 0 1631 0 4096 0 18 0 4096 0 1714 0 4096 0 1709 0 4096 0 2055 0 4096 0 1403 0 4096 0 430 0 4096 0 1888 0 4096 0 429 0 4096 0 798 0 4096 0 206 0 4096 0 1680 0 4096 0 723 0 4096 0 596 0 4096 0 269 0 4096 0 1847 0 4144 0 1351 0 4096 0 5627 0 5255469945486487 5255477523602709 5255477523626869 5255469953250101
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2502609 2502609 1048576 256 0 0 8 8 16 64 0x0 0x7f12c929ee80 4096 0 24 0 4096 0 3641 0 4096 0 6674 0 4096 0 1381 0 4097 0 55 0 4188 0 116 0 4096 0 3627 0 4096 0 1530 0 4096 0 134 0 4096 0 33 0 4144 0 1747 0 4097 0 2094 0 4097 0 1110 0 4096 0 459 0 4096 0 2537 0 4096 0 71 0 4096 0 1573 0 4096 0 3596 0 4096 0 7691 0 4099 0 760 0 4096 0 158 0 4096 0 990 0 4096 0 1453 0 4097 0 2110 0 4096 0 0 0 4096 0 5352 0 4096 0 875 0 4096 0 56 0 4096 0 0 0 4096 0 0 0 4144 0 86 0 4096 0 249 0 5255469953316807 5255477523727189 5255477523745909 5255469953869372
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2502609 2502609 1048576 256 0 0 8 8 16 64 0x0 0x7f12c929ee80 4096 0 7377 0 4096 0 523 0 4096 0 90 0 4096 0 850 0 4097 0 0 0 4171 0 3051 0 4096 0 936 0 4096 0 1156 0 4096 0 0 0 4096 0 0 0 4144 0 0 0 4097 0 976 0 4097 0 299 0 4096 0 669 0 4096 0 393 0 4096 0 433 0 4096 0 1504 0 4096 0 96 0 4096 0 156 0 4099 0 948 0 4096 0 0 0 4096 0 1299 0 4096 0 744 0 4097 0 0 0 4096 0 0 0 4096 0 0 0 4096 0 0 0 4096 0 0 0 4096 0 0 0 4096 0 0 0 4144 0 0 0 4096 0 0 0 5255469953947330 5255477523767029 5255477523785909 5255469954345823
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2505195,2505195,1048576,256,0,0,8,8,16,64,0x0,0x7f6897764e80,0,4199967,4096,4096,0,3787845,4096,4096,0,3798826,4096,4096,0,3965707,4096,4096,0,4265502,4096,4096,0,3224875,4096,4096,0,3269732,4096,4096,0,4759519,4096,4096,0,3408748,4096,4096,0,3746181,4096,4096,0,4995994,4096,4096,0,4398527,4096,4096,0,4982045,4096,4096,0,4420582,4096,4096,0,3395586,4096,4096,0,3635501,4096,4096,0,4605479,4096,4096,0,4290013,4096,4096,0,5471570,4096,4096,0,3380308,4096,4096,0,2923558,4096,4096,0,4757409,4096,4096,0,4256877,4096,4096,0,3610068,4096,4096,0,3482292,4096,4096,0,4179240,4096,4096,0,3325666,4096,4096,0,4431641,4096,4096,0,3673996,4096,4096,0,3443525,4096,4096,0,5083134,4096,4096,0,3373160,4096,4096,5255482056061761,5255477523602709,5255477523626869,5255482063909393
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2505195,2505195,1048576,256,0,0,8,8,16,64,0x0,0x7f6897764e80,0,3945625,2720,2720,0,3637482,2698,2698,0,4160693,2728,2728,0,4267811,2700,2700,0,3988071,2669,2669,0,3381390,2740,2740,0,3869233,2724,2724,0,3821182,2678,2678,0,3595625,2699,2699,0,3964716,2696,2696,0,3735386,2718,2718,0,3810793,2732,2732,0,3903194,2708,2708,0,3457876,2696,2696,0,4311564,2712,2712,0,4873632,2710,2710,0,3099974,2674,2674,0,3699894,2734,2734,0,3717282,2720,2720,0,3980427,2740,2740,0,3296021,2684,2684,0,3293713,2753,2753,0,4565345,2708,2708,0,4438297,2692,2692,0,3736186,2673,2673,0,3842887,2718,2718,0,3861515,2722,2722,0,3487951,2722,2722,0,3451360,2690,2690,0,3260900,2702,2702,0,3906882,2714,2714,0,3761768,2726,2726,5255482063977883,5255477523727189,5255477523745909,5255482064534395
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2505195,2505195,1048576,256,0,0,8,8,16,64,0x0,0x7f6897764e80,0,3357033,2742,2742,0,3308360,2726,2726,0,3700260,2706,2706,0,3322244,2737,2737,0,3278681,2720,2720,0,3289291,2717,2717,0,4165032,2761,2761,0,3678049,2710,2710,0,2970411,2724,2724,0,3792083,2714,2714,0,3586427,2744,2744,0,4332538,2726,2726,0,3001487,2688,2688,0,3570121,2746,2746,0,3444118,2728,2728,0,4920101,2743,2743,0,3133024,2702,2702,0,3663592,2756,2756,0,3335035,2697,2697,0,4043109,2776,2776,0,3006236,2740,2740,0,4114151,2753,2753,0,4080535,2714,2714,0,3398524,2715,2715,0,2857780,2702,2702,0,3653575,2734,2734,0,3194397,2742,2742,0,3675930,2749,2749,0,2918960,2720,2720,0,3868721,2756,2756,0,3416089,2728,2728,0,3559499,2764,2764,5255482064611581,5255477523767029,5255477523785909,5255482065000797
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2505195 2505195 1048576 256 0 0 8 8 16 64 0x0 0x7f6897764e80 0 4199967 4096 4096 0 3787845 4096 4096 0 3798826 4096 4096 0 3965707 4096 4096 0 4265502 4096 4096 0 3224875 4096 4096 0 3269732 4096 4096 0 4759519 4096 4096 0 3408748 4096 4096 0 3746181 4096 4096 0 4995994 4096 4096 0 4398527 4096 4096 0 4982045 4096 4096 0 4420582 4096 4096 0 3395586 4096 4096 0 3635501 4096 4096 0 4605479 4096 4096 0 4290013 4096 4096 0 5471570 4096 4096 0 3380308 4096 4096 0 2923558 4096 4096 0 4757409 4096 4096 0 4256877 4096 4096 0 3610068 4096 4096 0 3482292 4096 4096 0 4179240 4096 4096 0 3325666 4096 4096 0 4431641 4096 4096 0 3673996 4096 4096 0 3443525 4096 4096 0 5083134 4096 4096 0 3373160 4096 4096 5255482056061761 5255477523602709 5255477523626869 5255482063909393
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2505195 2505195 1048576 256 0 0 8 8 16 64 0x0 0x7f6897764e80 0 3945625 2720 2720 0 3637482 2698 2698 0 4160693 2728 2728 0 4267811 2700 2700 0 3988071 2669 2669 0 3381390 2740 2740 0 3869233 2724 2724 0 3821182 2678 2678 0 3595625 2699 2699 0 3964716 2696 2696 0 3735386 2718 2718 0 3810793 2732 2732 0 3903194 2708 2708 0 3457876 2696 2696 0 4311564 2712 2712 0 4873632 2710 2710 0 3099974 2674 2674 0 3699894 2734 2734 0 3717282 2720 2720 0 3980427 2740 2740 0 3296021 2684 2684 0 3293713 2753 2753 0 4565345 2708 2708 0 4438297 2692 2692 0 3736186 2673 2673 0 3842887 2718 2718 0 3861515 2722 2722 0 3487951 2722 2722 0 3451360 2690 2690 0 3260900 2702 2702 0 3906882 2714 2714 0 3761768 2726 2726 5255482063977883 5255477523727189 5255477523745909 5255482064534395
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2505195 2505195 1048576 256 0 0 8 8 16 64 0x0 0x7f6897764e80 0 3357033 2742 2742 0 3308360 2726 2726 0 3700260 2706 2706 0 3322244 2737 2737 0 3278681 2720 2720 0 3289291 2717 2717 0 4165032 2761 2761 0 3678049 2710 2710 0 2970411 2724 2724 0 3792083 2714 2714 0 3586427 2744 2744 0 4332538 2726 2726 0 3001487 2688 2688 0 3570121 2746 2746 0 3444118 2728 2728 0 4920101 2743 2743 0 3133024 2702 2702 0 3663592 2756 2756 0 3335035 2697 2697 0 4043109 2776 2776 0 3006236 2740 2740 0 4114151 2753 2753 0 4080535 2714 2714 0 3398524 2715 2715 0 2857780 2702 2702 0 3653575 2734 2734 0 3194397 2742 2742 0 3675930 2749 2749 0 2918960 2720 2720 0 3868721 2756 2756 0 3416089 2728 2728 0 3559499 2764 2764 5255482064611581 5255477523767029 5255477523785909 5255482065000797
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2505789,2505789,1048576,256,0,0,8,8,16,64,0x0,0x7f2464ff8e80,1362,0,0,1772749,2395,0,0,1915772,1708,0,0,1760583,1168,0,0,1774277,1921,0,0,1806044,2164,0,0,1922614,1585,0,0,1760526,1766,0,0,1841640,1175,0,0,1688581,3901,0,0,2055028,653,0,0,1665457,1728,0,0,1868750,692,0,0,1696121,6580,0,0,2265636,920,0,0,1748105,981,0,0,1712684,1547,0,0,1713275,1727,0,0,1761652,2644,0,0,1990127,3217,0,0,1968023,1163,0,0,1690656,3936,0,0,2055541,694,0,0,1738340,6885,0,0,2349657,2774,0,0,2003554,3232,0,0,2009370,1018,0,0,1778080,1799,0,0,1767463,1379,0,0,1712616,4321,0,0,2092130,1002,0,0,1796998,1905,0,0,1948391,5255484890454743,5255477523602709,5255477523626869,5255484898237743
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2505789,2505789,1048576,256,0,0,8,8,16,64,0x0,0x7f2464ff8e80,2825,0,0,1610320,2010,0,0,1453374,1976,0,0,1346409,5186,0,0,1766161,3192,0,0,1578145,668,0,0,1254082,1695,0,0,1442969,979,0,0,1298836,1648,0,0,1452923,1321,0,0,1367727,2775,0,0,1633999,651,0,0,1275994,5896,0,0,1852989,401,0,0,1129189,1422,0,0,1552545,1809,0,0,1512768,2878,0,0,1564059,15,0,0,1043562,5103,0,0,1807824,3203,0,0,1553366,3388,0,0,1605487,483,0,0,1187053,3305,0,0,1636655,2288,0,0,1425865,1464,0,0,1334573,826,0,0,1227040,1966,0,0,1481582,2399,0,0,1553371,2381,0,0,1522777,3921,0,0,1584294,6864,0,0,1899464,2317,0,0,1475340,5255484898307365,5255477523727189,5255477523745909,5255484898846344
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2505789,2505789,1048576,256,0,0,8,8,16,64,0x0,0x7f2464ff8e80,1658,0,0,1357005,815,0,0,1251707,806,0,0,1296471,8106,0,0,1971684,1010,0,0,1286227,2323,0,0,1506255,1671,0,0,1402325,732,0,0,1304578,976,0,0,1306722,418,0,0,1217583,995,0,0,1261259,194,0,0,1294151,1558,0,0,1261404,1021,0,0,1366638,3737,0,0,1663534,3082,0,0,1498572,555,0,0,1222219,983,0,0,1305704,806,0,0,1167812,1497,0,0,1300276,1751,0,0,1388434,4339,0,0,1710562,3905,0,0,1629757,6485,0,0,1797143,1565,0,0,1273292,711,0,0,1228676,1260,0,0,1411654,6337,0,0,1862579,1367,0,0,1302549,6269,0,0,1795652,1694,0,0,1375304,2504,0,0,1459175,5255484898923841,5255477523767029,5255477523785909,5255484899266228
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2505789 2505789 1048576 256 0 0 8 8 16 64 0x0 0x7f2464ff8e80 1362 0 0 1772749 2395 0 0 1915772 1708 0 0 1760583 1168 0 0 1774277 1921 0 0 1806044 2164 0 0 1922614 1585 0 0 1760526 1766 0 0 1841640 1175 0 0 1688581 3901 0 0 2055028 653 0 0 1665457 1728 0 0 1868750 692 0 0 1696121 6580 0 0 2265636 920 0 0 1748105 981 0 0 1712684 1547 0 0 1713275 1727 0 0 1761652 2644 0 0 1990127 3217 0 0 1968023 1163 0 0 1690656 3936 0 0 2055541 694 0 0 1738340 6885 0 0 2349657 2774 0 0 2003554 3232 0 0 2009370 1018 0 0 1778080 1799 0 0 1767463 1379 0 0 1712616 4321 0 0 2092130 1002 0 0 1796998 1905 0 0 1948391 5255484890454743 5255477523602709 5255477523626869 5255484898237743
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2505789 2505789 1048576 256 0 0 8 8 16 64 0x0 0x7f2464ff8e80 2825 0 0 1610320 2010 0 0 1453374 1976 0 0 1346409 5186 0 0 1766161 3192 0 0 1578145 668 0 0 1254082 1695 0 0 1442969 979 0 0 1298836 1648 0 0 1452923 1321 0 0 1367727 2775 0 0 1633999 651 0 0 1275994 5896 0 0 1852989 401 0 0 1129189 1422 0 0 1552545 1809 0 0 1512768 2878 0 0 1564059 15 0 0 1043562 5103 0 0 1807824 3203 0 0 1553366 3388 0 0 1605487 483 0 0 1187053 3305 0 0 1636655 2288 0 0 1425865 1464 0 0 1334573 826 0 0 1227040 1966 0 0 1481582 2399 0 0 1553371 2381 0 0 1522777 3921 0 0 1584294 6864 0 0 1899464 2317 0 0 1475340 5255484898307365 5255477523727189 5255477523745909 5255484898846344
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2505789 2505789 1048576 256 0 0 8 8 16 64 0x0 0x7f2464ff8e80 1658 0 0 1357005 815 0 0 1251707 806 0 0 1296471 8106 0 0 1971684 1010 0 0 1286227 2323 0 0 1506255 1671 0 0 1402325 732 0 0 1304578 976 0 0 1306722 418 0 0 1217583 995 0 0 1261259 194 0 0 1294151 1558 0 0 1261404 1021 0 0 1366638 3737 0 0 1663534 3082 0 0 1498572 555 0 0 1222219 983 0 0 1305704 806 0 0 1167812 1497 0 0 1300276 1751 0 0 1388434 4339 0 0 1710562 3905 0 0 1629757 6485 0 0 1797143 1565 0 0 1273292 711 0 0 1228676 1260 0 0 1411654 6337 0 0 1862579 1367 0 0 1302549 6269 0 0 1795652 1694 0 0 1375304 2504 0 0 1459175 5255484898923841 5255477523767029 5255477523785909 5255484899266228
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2503605,2503605,1048576,256,0,0,8,8,16,64,0x0,0x7fb0a8d5ce80,47,8193,4144,8240,0,8430,4334,8430,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8208,4112,8208,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,5255474735075905,5255477523602709,5255477523626869,5255474742830210
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2503605,2503605,1048576,256,0,0,8,8,16,64,0x0,0x7fb0a8d5ce80,47,8193,4144,8240,0,8432,4336,8432,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8195,4099,8195,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8241,4145,8241,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8238,4142,8238,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,5255474742899311,5255477523727189,5255477523745909,5255474743409356
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2503605,2503605,1048576,256,0,0,8,8,16,64,0x0,0x7fb0a8d5ce80,47,8193,4144,8240,0,8432,4336,8432,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8195,4099,8195,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8241,4145,8241,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8242,4146,8242,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,5255474743486331,5255477523767029,5255477523785909,5255474743827256
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2503605 2503605 1048576 256 0 0 8 8 16 64 0x0 0x7fb0a8d5ce80 47 8193 4144 8240 0 8430 4334 8430 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 141 8195 4240 8336 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8240 4144 8240 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8208 4112 8208 0 8192 4096 8192 0 8192 4096 8192 0 8240 4144 8240 0 8192 4096 8192 5255474735075905 5255477523602709 5255477523626869 5255474742830210
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2503605 2503605 1048576 256 0 0 8 8 16 64 0x0 0x7fb0a8d5ce80 47 8193 4144 8240 0 8432 4336 8432 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8193 4097 8193 0 8195 4099 8195 0 8192 4096 8192 0 8192 4096 8192 0 8193 4097 8193 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8241 4145 8241 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8238 4142 8238 0 8192 4096 8192 0 8192 4096 8192 0 8240 4144 8240 0 8192 4096 8192 5255474742899311 5255477523727189 5255477523745909 5255474743409356
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2503605 2503605 1048576 256 0 0 8 8 16 64 0x0 0x7fb0a8d5ce80 47 8193 4144 8240 0 8432 4336 8432 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8193 4097 8193 0 8195 4099 8195 0 8192 4096 8192 0 8192 4096 8192 0 8193 4097 8193 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8241 4145 8241 0 8192 4096 8192 0 8192 4096 8192 0 8192 4096 8192 0 8242 4146 8242 0 8192 4096 8192 0 8192 4096 8192 0 8240 4144 8240 0 8192 4096 8192 5255474743486331 5255477523767029 5255477523785909 5255474743827256
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2504007,2504007,1048576,256,0,0,8,8,16,64,0x0,0x7f57fe5e8e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,5255476648728339,5255477523602709,5255477523626869,5255476656514154
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2504007,2504007,1048576,256,0,0,8,8,16,64,0x0,0x7f57fe5e8e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,5255476656566463,5255477523727189,5255477523745909,5255476657042643
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2504007,2504007,1048576,256,0,0,8,8,16,64,0x0,0x7f57fe5e8e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,5255476657106815,5255477523767029,5255477523785909,5255476657435246
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2504007 2504007 1048576 256 0 0 8 8 16 64 0x0 0x7f57fe5e8e80 8192 0 4096 8192 0 4096 8336 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 5255476648728339 5255477523602709 5255477523626869 5255476656514154
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2504007 2504007 1048576 256 0 0 8 8 16 64 0x0 0x7f57fe5e8e80 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 5255476656566463 5255477523727189 5255477523745909 5255476657042643
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2504007 2504007 1048576 256 0 0 8 8 16 64 0x0 0x7f57fe5e8e80 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 8192 0 4096 5255476657106815 5255477523767029 5255477523785909 5255476657435246
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,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,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,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2505393,2505393,1048576,256,0,0,8,8,16,64,0x0,0x7fb5c31cee80,127456,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12010,28394,9387,588,0,47301,262662.0,0.0,188.0,262474.0,5255482940426522,5255477523602709,5255477523626869,5255482948272190
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2505393,2505393,1048576,256,0,0,8,8,16,64,0x0,0x7fb5c31cee80,184963,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12316,28700,8604,3914,0,41168,262501.0,0.0,47.0,262454.0,5255482948787796,5255477523727189,5255477523745909,5255482949284144
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2505393,2505393,1048576,256,0,0,8,8,16,64,0x0,0x7fb5c31cee80,185097,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13067,29451,8454,3873,0,40781,262491.0,0.0,47.0,262444.0,5255482949810239,5255477523767029,5255477523785909,5255482950320134
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj 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 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 DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2505393 2505393 1048576 256 0 0 8 8 16 64 0x0 0x7fb5c31cee80 127456 0 0 65536 64048 48 1440 32768 2097152.0 2097152.0 1048576.0 1048576.0 0.0 0.0 0.0 16384.0 12010 28394 9387 588 0 47301 262662.0 0.0 188.0 262474.0 5255482940426522 5255477523602709 5255477523626869 5255482948272190
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2505393 2505393 1048576 256 0 0 8 8 16 64 0x0 0x7fb5c31cee80 184963 0 0 65536 64048 48 1440 32768 2097152.0 2097152.0 1048576.0 1048576.0 0.0 0.0 0.0 16384.0 12316 28700 8604 3914 0 41168 262501.0 0.0 47.0 262454.0 5255482948787796 5255477523727189 5255477523745909 5255482949284144
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2505393 2505393 1048576 256 0 0 8 8 16 64 0x0 0x7fb5c31cee80 185097 0 0 65536 64048 48 1440 32768 2097152.0 2097152.0 1048576.0 1048576.0 0.0 0.0 0.0 16384.0 13067 29451 8454 3873 0 40781 262491.0 0.0 47.0 262444.0 5255482949810239 5255477523767029 5255477523785909 5255482950320134
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,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,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,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2502213,2502213,1048576,256,0,0,8,8,16,64,0x0,0x7faac8ab8e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47440,0,131523.0,131072.0,0.0,131104.0,5255467984134331,5255477523602709,5255477523626869,5255467992118683
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2502213,2502213,1048576,256,0,0,8,8,16,64,0x0,0x7faac8ab8e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2982,39242,0,131375.0,131072.0,0.0,86801.0,5255467992528158,5255477523727189,5255477523745909,5255467993009969
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2502213,2502213,1048576,256,0,0,8,8,16,64,0x0,0x7faac8ab8e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2740,38903,0,131366.0,131072.0,0.0,86478.0,5255467993387223,5255477523767029,5255477523785909,5255467993869645
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS_SMEM 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 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 DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2502213 2502213 1048576 256 0 0 8 8 16 64 0x0 0x7faac8ab8e80 32768 0 16384 16384 32768 49152 0 65536 0.0 0.0 120.0 524288.0 0.0 0.0 0 0 913 47440 0 131523.0 131072.0 0.0 131104.0 5255467984134331 5255477523602709 5255477523626869 5255467992118683
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2502213 2502213 1048576 256 0 0 8 8 16 64 0x0 0x7faac8ab8e80 32768 0 16384 16384 32768 49152 0 65536 0.0 0.0 120.0 524288.0 0.0 0.0 0 0 2982 39242 0 131375.0 131072.0 0.0 86801.0 5255467992528158 5255477523727189 5255477523745909 5255467993009969
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2502213 2502213 1048576 256 0 0 8 8 16 64 0x0 0x7faac8ab8e80 32768 0 16384 16384 32768 49152 0 65536 0.0 0.0 120.0 524288.0 0.0 0.0 0 0 2740 38903 0 131366.0 131072.0 0.0 86478.0 5255467993387223 5255477523767029 5255477523785909 5255467993869645
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,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_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2504799,2504799,1048576,256,0,0,8,8,16,64,0x0,0x7fe944a7ae80,32768,0,0,0,16384,16384,393216,22818566,960.0,513929.0,0.0,524288.0,973160.0,32768.0,0,0,0,15853,131072.0,131072.0,0.0,131072.0,5255480092131817,5255477523602709,5255477523626869,5255480100121388
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2504799,2504799,1048576,256,0,0,8,8,16,64,0x0,0x7fe944a7ae80,32768,0,0,0,16384,16384,393216,22796945,960.0,513920.0,0.0,524288.0,1052429.0,32768.0,0,0,0,14374,86427.0,86427.0,0.0,86427.0,5255480100530732,5255477523727189,5255477523745909,5255480101042641
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2504799,2504799,1048576,256,0,0,8,8,16,64,0x0,0x7fe944a7ae80,32768,0,0,0,16384,16384,393216,23050498,960.0,513854.0,0.0,524288.0,1032802.0,32768.0,0,0,0,14514,86574.0,86574.0,0.0,86574.0,5255480101397161,5255477523767029,5255477523785909,5255480101867741
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS SQ_WAIT_ANY 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_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2504799 2504799 1048576 256 0 0 8 8 16 64 0x0 0x7fe944a7ae80 32768 0 0 0 16384 16384 393216 22818566 960.0 513929.0 0.0 524288.0 973160.0 32768.0 0 0 0 15853 131072.0 131072.0 0.0 131072.0 5255480092131817 5255477523602709 5255477523626869 5255480100121388
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2504799 2504799 1048576 256 0 0 8 8 16 64 0x0 0x7fe944a7ae80 32768 0 0 0 16384 16384 393216 22796945 960.0 513920.0 0.0 524288.0 1052429.0 32768.0 0 0 0 14374 86427.0 86427.0 0.0 86427.0 5255480100530732 5255477523727189 5255477523745909 5255480101042641
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2504799 2504799 1048576 256 0 0 8 8 16 64 0x0 0x7fe944a7ae80 32768 0 0 0 16384 16384 393216 23050498 960.0 513854.0 0.0 524288.0 1032802.0 32768.0 0 0 0 14514 86574.0 86574.0 0.0 86574.0 5255480101397161 5255477523767029 5255477523785909 5255480101867741
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_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_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2504601,2504601,1048576,256,0,0,8,8,16,64,0x0,0x7fb93167ce80,2401097,360448,163840,0,0,180224,114688,0,63183910.0,178360826.0,73472986.0,131072.0,0.0,579128.0,0,0,26510,160674.0,0.0,0.0,160674.0,5255479238979177,5255477523602709,5255477523626869,5255479246825677
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2504601,2504601,1048576,256,0,0,8,8,16,64,0x0,0x7fb93167ce80,1749558,360448,163840,0,0,180224,114688,0,63804267.0,174389289.0,81563486.0,131072.0,0.0,1015017.0,0,0,28364,26297.0,0.0,0.0,26297.0,5255479247235002,5255477523727189,5255477523745909,5255479247715600
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2504601,2504601,1048576,256,0,0,8,8,16,64,0x0,0x7fb93167ce80,2266773,360448,163840,0,0,180224,114688,0,62333348.0,167139174.0,70212142.0,131072.0,0.0,502949.0,0,0,26360,150530.0,0.0,0.0,150530.0,5255479248061204,5255477523767029,5255477523785909,5255479248515834
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_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_EA_WRREQ_STALL_sum TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2504601 2504601 1048576 256 0 0 8 8 16 64 0x0 0x7fb93167ce80 2401097 360448 163840 0 0 180224 114688 0 63183910.0 178360826.0 73472986.0 131072.0 0.0 579128.0 0 0 26510 160674.0 0.0 0.0 160674.0 5255479238979177 5255477523602709 5255477523626869 5255479246825677
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2504601 2504601 1048576 256 0 0 8 8 16 64 0x0 0x7fb93167ce80 1749558 360448 163840 0 0 180224 114688 0 63804267.0 174389289.0 81563486.0 131072.0 0.0 1015017.0 0 0 28364 26297.0 0.0 0.0 26297.0 5255479247235002 5255477523727189 5255477523745909 5255479247715600
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2504601 2504601 1048576 256 0 0 8 8 16 64 0x0 0x7fb93167ce80 2266773 360448 163840 0 0 180224 114688 0 62333348.0 167139174.0 70212142.0 131072.0 0.0 502949.0 0 0 26360 150530.0 0.0 0.0 150530.0 5255479248061204 5255477523767029 5255477523785909 5255479248515834
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,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,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_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_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2503206,2503206,1048576,256,0,0,8,8,16,64,0x0,0x7f5165bcee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131403.0,0.0,654.0,131402.0,5255472779999302,5255477523602709,5255477523626869,5255472787872554
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2503206,2503206,1048576,256,0,0,8,8,16,64,0x0,0x7f5165bcee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131405.0,0.0,664.0,131404.0,5255472788280485,5255477523727189,5255477523745909,5255472788735096
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2503206,2503206,1048576,256,0,0,8,8,16,64,0x0,0x7f5165bcee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131385.0,0.0,624.0,131384.0,5255472789121446,5255477523767029,5255477523785909,5255472789564955
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj 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 SQ_IFETCH TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_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_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2503206 2503206 1048576 256 0 0 8 8 16 64 0x0 0x7f5165bcee80 32768 32768 16384 16384 65536 49152 11534336 65536 131072.0 0.0 0.0 0.0 32768.0 16384.0 0 0 131403.0 0.0 654.0 131402.0 5255472779999302 5255477523602709 5255477523626869 5255472787872554
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2503206 2503206 1048576 256 0 0 8 8 16 64 0x0 0x7f5165bcee80 32768 32768 16384 16384 65536 49152 11534336 65536 131072.0 0.0 0.0 0.0 32768.0 16384.0 0 0 131405.0 0.0 664.0 131404.0 5255472788280485 5255477523727189 5255477523745909 5255472788735096
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2503206 2503206 1048576 256 0 0 8 8 16 64 0x0 0x7f5165bcee80 32768 32768 16384 16384 65536 49152 11534336 65536 131072.0 0.0 0.0 0.0 32768.0 16384.0 0 0 131385.0 0.0 624.0 131384.0 5255472789121446 5255477523767029 5255477523785909 5255472789564955
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2503406,2503406,1048576,256,0,0,8,8,16,64,0x0,0x7fe43a3dce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,28555.0,123147.0,5255473651421229,5255477523602709,5255477523626869,5255473659148252
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2503406,2503406,1048576,256,0,0,8,8,16,64,0x0,0x7fe43a3dce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,24406.0,117740.0,5255473659556374,5255477523727189,5255477523745909,5255473660045560
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2503406,2503406,1048576,256,0,0,8,8,16,64,0x0,0x7fe43a3dce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,30143.0,117619.0,5255473660464542,5255477523767029,5255477523785909,5255473660902821
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2503406 2503406 1048576 256 0 0 8 8 16 64 0x0 0x7fe43a3dce80 0 0 0 16384 0 0 0 0 0.0 0.0 0.0 0.0 16384.0 0.0 0 81920 0.0 0.0 28555.0 123147.0 5255473651421229 5255477523602709 5255477523626869 5255473659148252
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2503406 2503406 1048576 256 0 0 8 8 16 64 0x0 0x7fe43a3dce80 0 0 0 16384 0 0 0 0 0.0 0.0 0.0 0.0 16384.0 0.0 0 81920 0.0 0.0 24406.0 117740.0 5255473659556374 5255477523727189 5255477523745909 5255473660045560
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2503406 2503406 1048576 256 0 0 8 8 16 64 0x0 0x7fe43a3dce80 0 0 0 16384 0 0 0 0 0.0 0.0 0.0 0.0 16384.0 0.0 0 81920 0.0 0.0 30143.0 117619.0 5255473660464542 5255477523767029 5255477523785909 5255473660902821
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2504403,2504403,1048576,256,0,0,8,8,16,64,0x0,0x7f90e3670e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86376.0,44696.0,131112.0,0.0,5255478374482041,5255477523602709,5255477523626869,5255478382738647
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2504403,2504403,1048576,256,0,0,8,8,16,64,0x0,0x7f90e3670e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86650.0,0.0,131110.0,0.0,5255478383039316,5255477523727189,5255477523745909,5255478383517560
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2504403,2504403,1048576,256,0,0,8,8,16,64,0x0,0x7f90e3670e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86608.0,0.0,131112.0,0.0,5255478383710425,5255477523767029,5255477523785909,5255478384197656
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2504403 2504403 1048576 256 0 0 8 8 16 64 0x0 0x7f90e3670e80 1048576 0 0 0 0 0 131072 0.0 0.0 0.0 0.0 16384 0 86376.0 44696.0 131112.0 0.0 5255478374482041 5255477523602709 5255477523626869 5255478382738647
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2504403 2504403 1048576 256 0 0 8 8 16 64 0x0 0x7f90e3670e80 1048576 0 0 0 0 0 131072 0.0 0.0 0.0 0.0 16384 0 86650.0 0.0 131110.0 0.0 5255478383039316 5255477523727189 5255477523745909 5255478383517560
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2504403 2504403 1048576 256 0 0 8 8 16 64 0x0 0x7f90e3670e80 1048576 0 0 0 0 0 131072 0.0 0.0 0.0 0.0 16384 0 86608.0 0.0 131112.0 0.0 5255478383710425 5255477523767029 5255477523785909 5255478384197656
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2503007,2503007,1048576,256,0,0,8,8,16,64,0x0,0x7fc2645dae80,131072.0,131072.0,0.0,2634051.0,0.0,0.0,101035301.0,60679800.0,5255471915112862,5255477523602709,5255477523626869,5255471922855878
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2503007,2503007,1048576,256,0,0,8,8,16,64,0x0,0x7fc2645dae80,131072.0,131072.0,0.0,2636684.0,0.0,0.0,132074784.0,48137103.0,5255471923130227,5255477523727189,5255477523745909,5255471923536144
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2503007,2503007,1048576,256,0,0,8,8,16,64,0x0,0x7fc2645dae80,131072.0,131072.0,0.0,2615156.0,0.0,0.0,108332268.0,49336132.0,5255471923718419,5255477523767029,5255477523785909,5255471924155456
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2503007 2503007 1048576 256 0 0 8 8 16 64 0x0 0x7fc2645dae80 131072.0 131072.0 0.0 2634051.0 0.0 0.0 101035301.0 60679800.0 5255471915112862 5255477523602709 5255477523626869 5255471922855878
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2503007 2503007 1048576 256 0 0 8 8 16 64 0x0 0x7fc2645dae80 131072.0 131072.0 0.0 2636684.0 0.0 0.0 132074784.0 48137103.0 5255471923130227 5255477523727189 5255477523745909 5255471923536144
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2503007 2503007 1048576 256 0 0 8 8 16 64 0x0 0x7fc2645dae80 131072.0 131072.0 0.0 2615156.0 0.0 0.0 108332268.0 49336132.0 5255471923718419 5255477523767029 5255477523785909 5255471924155456
+2
View File
@@ -0,0 +1,2 @@
workload_name,command,host_name,host_cpu,sbios,host_distro,host_kernel,host_rocmver,date,gpu_soc,vbios,numSE,numCU,numSIMD,waveSize,maxWavesPerCU,maxWorkgroupSize,L1,L2,sclk,mclk,cur_sclk,cur_mclk,L2Banks,totalL2Banks,LDSBanks,name,numSQC,numPipes,hbmBW,compute_partition,memory_partition,ip_blocks
app_1,./tests/vcopy -n 1048576 -b 256 -i 3,t004-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,5.7.1-98,Wed Feb 14 11:44:01 2024 (CST),gfx908,113-D3431401-100,8,120,4,64,40,1024,16,8192,1502,1200,1502,1200,32,32,32,MI100,30,4,1200,,,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
1 workload_name command host_name host_cpu sbios host_distro host_kernel host_rocmver date gpu_soc vbios numSE numCU numSIMD waveSize maxWavesPerCU maxWorkgroupSize L1 L2 sclk mclk cur_sclk cur_mclk L2Banks totalL2Banks LDSBanks name numSQC numPipes hbmBW compute_partition memory_partition ip_blocks
2 app_1 ./tests/vcopy -n 1048576 -b 256 -i 3 t004-002.hpcfund AMD EPYC 7V13 64-Core Processor American Megatrends Inc.0602 Rocky Linux 9.1 (Blue Onyx) 5.14.0-162.18.1.el9_1.x86_64 5.7.1-98 Wed Feb 14 11:44:01 2024 (CST) gfx908 113-D3431401-100 8 120 4 64 40 1024 16 8192 1502 1200 1502 1200 32 32 32 MI100 30 4 1200 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,1332584,1332584,1048576,256,0,0,8,8,16,64,0x0,0x7f9fcce86e80,5862046126473749,5862046126501116,5862046126524956,5862046126538100
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,1332584,1332584,1048576,256,0,0,8,8,16,64,0x0,0x7f9fcce86e80,5862046126537579,5862046126616796,5862046126635516,5862046126636526
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,1332584,1332584,1048576,256,0,0,8,8,16,64,0x0,0x7f9fcce86e80,5862046126648188,5862046126657436,5862046126676476,5862046126677664
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 1332584 1332584 1048576 256 0 0 8 8 16 64 0x0 0x7f9fcce86e80 5862046126473749 5862046126501116 5862046126524956 5862046126538100
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 1332584 1332584 1048576 256 0 0 8 8 16 64 0x0 0x7f9fcce86e80 5862046126537579 5862046126616796 5862046126635516 5862046126636526
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 1332584 1332584 1048576 256 0 0 8 8 16 64 0x0 0x7f9fcce86e80 5862046126648188 5862046126657436 5862046126676476 5862046126677664
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2695647,2695647,1048576,256,0,0,8,0,16,64,0x0,0x7f8e6993cec0,27987,27987,16384,65536,13259,1512196,2423827663335467,2423816758936208,2423816758956208,2423827678821236
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2695647,2695647,1048576,256,0,0,8,0,16,64,0x0,0x7f8e6993cec0,41409,41409,16384,65536,9342,1048640,2423827678841204,2423816758974928,2423816758990448,2423827679167481
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2695647,2695647,1048576,256,0,0,8,0,16,64,0x0,0x7f8e6993cec0,42107,42107,16384,65536,9319,1048704,2423827679204520,2423816759063728,2423816759080688,2423827679384871
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2695647 2695647 1048576 256 0 0 8 0 16 64 0x0 0x7f8e6993cec0 27987 27987 16384 65536 13259 1512196 2423827663335467 2423816758936208 2423816758956208 2423827678821236
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2695647 2695647 1048576 256 0 0 8 0 16 64 0x0 0x7f8e6993cec0 41409 41409 16384 65536 9342 1048640 2423827678841204 2423816758974928 2423816758990448 2423827679167481
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2695647 2695647 1048576 256 0 0 8 0 16 64 0x0 0x7f8e6993cec0 42107 42107 16384 65536 9319 1048704 2423827679204520 2423816759063728 2423816759080688 2423827679384871
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2690991,2690991,1048576,256,0,0,8,0,16,64,0x0,0x7fbcd5864ec0,0,0,0,2423803831466254,2423816758936208,2423816758956208,2423803847254015
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2690991,2690991,1048576,256,0,0,8,0,16,64,0x0,0x7fbcd5864ec0,0,0,0,2423803847273952,2423816758974928,2423816758990448,2423803847594598
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2690991,2690991,1048576,256,0,0,8,0,16,64,0x0,0x7fbcd5864ec0,0,0,0,2423803847620387,2423816759063728,2423816759080688,2423803847781652
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2690991 2690991 1048576 256 0 0 8 0 16 64 0x0 0x7fbcd5864ec0 0 0 0 2423803831466254 2423816758936208 2423816758956208 2423803847254015
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2690991 2690991 1048576 256 0 0 8 0 16 64 0x0 0x7fbcd5864ec0 0 0 0 2423803847273952 2423816758974928 2423816758990448 2423803847594598
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2690991 2690991 1048576 256 0 0 8 0 16 64 0x0 0x7fbcd5864ec0 0 0 0 2423803847620387 2423816759063728 2423816759080688 2423803847781652
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2695445,2695445,1048576,256,0,0,8,0,16,64,0x0,0x7facdf810ec0,65536,199108,22345568,2423826707526640,2423816758936208,2423816758956208,2423826723521191
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2695445,2695445,1048576,256,0,0,8,0,16,64,0x0,0x7facdf810ec0,65536,279492,31248008,2423826723547862,2423816758974928,2423816758990448,2423826723876613
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2695445,2695445,1048576,256,0,0,8,0,16,64,0x0,0x7facdf810ec0,65536,297828,33376048,2423826723903344,2423816759063728,2423816759080688,2423826724073595
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2695445 2695445 1048576 256 0 0 8 0 16 64 0x0 0x7facdf810ec0 65536 199108 22345568 2423826707526640 2423816758936208 2423816758956208 2423826723521191
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2695445 2695445 1048576 256 0 0 8 0 16 64 0x0 0x7facdf810ec0 65536 279492 31248008 2423826723547862 2423816758974928 2423816758990448 2423826723876613
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2695445 2695445 1048576 256 0 0 8 0 16 64 0x0 0x7facdf810ec0 65536 297828 33376048 2423826723903344 2423816759063728 2423816759080688 2423826724073595
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2691397,2691397,1048576,256,0,0,8,0,16,64,0x0,0x7f2c3aac8ec0,32768,299874,33590924,2423805825500971,2423816758936208,2423816758956208,2423805841017168
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2691397,2691397,1048576,256,0,0,8,0,16,64,0x0,0x7f2c3aac8ec0,32768,590892,66171900,2423805841024021,2423816758974928,2423816758990448,2423805841366077
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2691397,2691397,1048576,256,0,0,8,0,16,64,0x0,0x7f2c3aac8ec0,32768,587630,65806776,2423805841393178,2423816759063728,2423816759080688,2423805841573549
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2691397 2691397 1048576 256 0 0 8 0 16 64 0x0 0x7f2c3aac8ec0 32768 299874 33590924 2423805825500971 2423816758936208 2423816758956208 2423805841017168
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2691397 2691397 1048576 256 0 0 8 0 16 64 0x0 0x7f2c3aac8ec0 32768 590892 66171900 2423805841024021 2423816758974928 2423816758990448 2423805841366077
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2691397 2691397 1048576 256 0 0 8 0 16 64 0x0 0x7f2c3aac8ec0 32768 587630 65806776 2423805841393178 2423816759063728 2423816759080688 2423805841573549
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,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,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2692813,2692813,1048576,256,0,0,8,0,16,64,0x0,0x7efeaac8cec0,27886,27886,10990,223096,16384,11169429,131145,0,45174824,2423813660512481,2423816758936208,2423816758956208,2423813676161599
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2692813,2692813,1048576,256,0,0,8,0,16,64,0x0,0x7efeaac8cec0,42468,42468,14278,339752,16384,20055323,227652,0,80702288,2423813676188640,2423816758974928,2423816758990448,2423813676510959
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2692813,2692813,1048576,256,0,0,8,0,16,64,0x0,0x7efeaac8cec0,41526,41526,13353,332216,16384,19715179,224611,0,79334060,2423813676546005,2423816759063728,2423816759080688,2423813676718491
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj 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 DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2692813 2692813 1048576 256 0 0 8 0 16 64 0x0 0x7efeaac8cec0 27886 27886 10990 223096 16384 11169429 131145 0 45174824 2423813660512481 2423816758936208 2423816758956208 2423813676161599
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2692813 2692813 1048576 256 0 0 8 0 16 64 0x0 0x7efeaac8cec0 42468 42468 14278 339752 16384 20055323 227652 0 80702288 2423813676188640 2423816758974928 2423816758990448 2423813676510959
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2692813 2692813 1048576 256 0 0 8 0 16 64 0x0 0x7efeaac8cec0 41526 41526 13353 332216 16384 19715179 224611 0 79334060 2423813676546005 2423816759063728 2423816759080688 2423813676718491
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
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:
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:
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:
kernel:
@@ -0,0 +1,5 @@
pmc: 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
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: 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
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31]
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31]
gpu:
range:
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:
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:
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_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum
gpu:
range:
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_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_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_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum
gpu:
range:
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_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_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_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum
gpu:
range:
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_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_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_EA_ATOMIC_sum
gpu:
range:
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_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: 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 TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel:
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID
0,"vecCopy(double*, double*, double*, int, int)",2
1,"vecCopy(double*, double*, double*, int, int)",2
2,"vecCopy(double*, double*, double*, int, int)",2
1 Dispatch_ID Kernel_Name GPU_ID
2 0 vecCopy(double*, double*, double*, int, int) 2
3 1 vecCopy(double*, double*, double*, int, int) 2
4 2 vecCopy(double*, double*, double*, int, int) 2
File diff suppressed because one or more lines are too long
+5
View File
@@ -0,0 +1,5 @@
device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh
0,1389.2573,1388.7148,1389.7998,5028.8901,5025.7681,5032.0122,9236.2383,9235.5488,9236.9277,17609.27,17606.766,17611.773,21018.107,20957.701,21078.514,20440.506,20439.146,20441.865,170492.3,170487.67,170496.92,164888.08,164883.73,164892.42,41448.984,41448.043,41449.926,41427.156,41426.016,41428.297,166462.45,165973.48,166951.42
1,1388.6865,1388.1116,1389.2615,5043.5737,5041.3315,5045.8159,9269.6289,9269.0537,9270.2041,17701.557,17696.309,17706.805,20996.717,20800.053,21193.381,20510.537,20509.943,20511.131,170937.3,170933.94,170940.66,165438.28,165434.06,165442.5,41577.234,41576.676,41577.793,41548.996,41546.246,41551.746,167192.28,167189.86,167194.7
2,1388.6455,1388.0868,1389.2042,5031.8101,5029.8232,5033.7969,9247.6719,9247.1436,9248.2002,17836.916,17827.848,17845.984,21070.893,21070.477,21071.309,20462.385,20461.734,20463.035,170666.73,170661.8,170671.67,165136.25,165131.95,165140.55,41499.688,41498.645,41500.73,41479.488,41478.453,41480.523,166663.62,166079.67,167247.58
3,1388.3237,1387.6769,1388.9706,5042.8608,5041.9971,5043.7246,9237.6855,9237.2197,9238.1514,17895.852,17888.172,17903.531,21056.562,21056.182,21056.943,20440.436,20439.594,20441.277,170615.14,170611.98,170618.3,164958.52,164953.75,164963.28,41457.891,41457.164,41458.617,41306.961,41053.715,41560.207,166802.38,166799.5,166805.25
1 device HBMBw HBMBwLow hbmBwHigh L2Bw L2BwLow L2BwHigh L1Bw L1BwLow L1BwHigh LDSBw LDSBwLow LDSBwHigh FP32Flops FP32FlopsLow FP32FlopsHigh FP64Flops FP64FlopsLow FP64FlopsHigh MFMABF16Flops MFMABF16FlopsLow MFMABF16FlopsHigh MFMAF16Flops MFMAF16FlopsLow MFMAF16FlopsHigh MFMAF32Flops MFMAF32FlopsLow MFMAF32FlopsHigh MFMAF64Flops MFMAF64FlopsLow MFMAF64FlopsHigh MFMAI8Ops MFMAFI8OpsLow MFMAI8OpsHigh
2 0 1389.2573 1388.7148 1389.7998 5028.8901 5025.7681 5032.0122 9236.2383 9235.5488 9236.9277 17609.27 17606.766 17611.773 21018.107 20957.701 21078.514 20440.506 20439.146 20441.865 170492.3 170487.67 170496.92 164888.08 164883.73 164892.42 41448.984 41448.043 41449.926 41427.156 41426.016 41428.297 166462.45 165973.48 166951.42
3 1 1388.6865 1388.1116 1389.2615 5043.5737 5041.3315 5045.8159 9269.6289 9269.0537 9270.2041 17701.557 17696.309 17706.805 20996.717 20800.053 21193.381 20510.537 20509.943 20511.131 170937.3 170933.94 170940.66 165438.28 165434.06 165442.5 41577.234 41576.676 41577.793 41548.996 41546.246 41551.746 167192.28 167189.86 167194.7
4 2 1388.6455 1388.0868 1389.2042 5031.8101 5029.8232 5033.7969 9247.6719 9247.1436 9248.2002 17836.916 17827.848 17845.984 21070.893 21070.477 21071.309 20462.385 20461.734 20463.035 170666.73 170661.8 170671.67 165136.25 165131.95 165140.55 41499.688 41498.645 41500.73 41479.488 41478.453 41480.523 166663.62 166079.67 167247.58
5 3 1388.3237 1387.6769 1388.9706 5042.8608 5041.9971 5043.7246 9237.6855 9237.2197 9238.1514 17895.852 17888.172 17903.531 21056.562 21056.182 21056.943 20440.436 20439.594 20441.277 170615.14 170611.98 170618.3 164958.52 164953.75 164963.28 41457.891 41457.164 41458.617 41306.961 41053.715 41560.207 166802.38 166799.5 166805.25
+2
View File
@@ -0,0 +1,2 @@
workload_name,command,host_name,host_cpu,sbios,host_distro,host_kernel,host_rocmver,date,gpu_soc,vbios,numSE,numCU,numSIMD,waveSize,maxWavesPerCU,maxWorkgroupSize,L1,L2,sclk,mclk,cur_sclk,cur_mclk,L2Banks,totalL2Banks,LDSBanks,name,numSQC,numPipes,hbmBW,compute_partition,memory_partition,ip_blocks
app_1,./sample/vcopy -n 1048576 -b 256 -i 3,t004-004.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,5.7.1-98,Fri Feb 16 14:36:58 2024 (CST),gfx90a,113-D67301-059,8,104,4,64,32,1024,16,8192,1700,1200,1700,1200,32,32,32,MI200,56,4,1200,,,roofline|SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
1 workload_name command host_name host_cpu sbios host_distro host_kernel host_rocmver date gpu_soc vbios numSE numCU numSIMD waveSize maxWavesPerCU maxWorkgroupSize L1 L2 sclk mclk cur_sclk cur_mclk L2Banks totalL2Banks LDSBanks name numSQC numPipes hbmBW compute_partition memory_partition ip_blocks
2 app_1 ./sample/vcopy -n 1048576 -b 256 -i 3 t004-004.hpcfund AMD EPYC 7V13 64-Core Processor American Megatrends Inc.0602 Rocky Linux 9.1 (Blue Onyx) 5.14.0-162.18.1.el9_1.x86_64 5.7.1-98 Fri Feb 16 14:36:58 2024 (CST) gfx90a 113-D67301-059 8 104 4 64 32 1024 16 8192 1700 1200 1700 1200 32 32 32 MI200 56 4 1200 roofline|SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
@@ -0,0 +1,4 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"vecCopy(double*, double*, double*, int, int)",2,0,0,2693421,2693421,1048576,256,0,0,8,0,16,64,0x0,0x7f7cf8518ec0,2423816758910852,2423816758936208,2423816758956208,2423816758969663
1,"vecCopy(double*, double*, double*, int, int)",2,0,2,2693421,2693421,1048576,256,0,0,8,0,16,64,0x0,0x7f7cf8518ec0,2423816758967389,2423816758974928,2423816758990448,2423816759061657
2,"vecCopy(double*, double*, double*, int, int)",2,0,4,2693421,2693421,1048576,256,0,0,8,0,16,64,0x0,0x7f7cf8518ec0,2423816759001022,2423816759063728,2423816759080688,2423816759081835
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid Grid_Size Workgroup_Size LDS_Per_Workgroup Scratch_Per_Workitem Arch_VGPR Accum_VGPR SGPR wave_size sig obj DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 vecCopy(double*, double*, double*, int, int) 2 0 0 2693421 2693421 1048576 256 0 0 8 0 16 64 0x0 0x7f7cf8518ec0 2423816758910852 2423816758936208 2423816758956208 2423816758969663
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2693421 2693421 1048576 256 0 0 8 0 16 64 0x0 0x7f7cf8518ec0 2423816758967389 2423816758974928 2423816758990448 2423816759061657
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2693421 2693421 1048576 256 0 0 8 0 16 64 0x0 0x7f7cf8518ec0 2423816759001022 2423816759063728 2423816759080688 2423816759081835