update workloads]

Signed-off-by: Jose Santos <josantos@amd.com>
This commit is contained in:
Jose Santos
2024-03-07 15:19:48 -06:00
committed by Karl W. Schulz
parent afea510551
commit 35ef8c0707
1472 changed files with 5798 additions and 630 deletions
@@ -1,4 +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) ",2,0,0,2869770,2869770,1048576,256,0,0,8,8,16,64,0x0,0x7eff6a3d2e80,48732,48732,16384,65536,12984,1684952,2187869534755189,2187863086843344,2187863086866864,2187869542260328
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2869770,2869770,1048576,256,0,0,8,8,16,64,0x0,0x7eff6a3d2e80,43698,43698,16384,65536,8101,1048580,2187869542283442,2187863086979504,2187863086998544,2187869542602320
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2869770,2869770,1048576,256,0,0,8,8,16,64,0x0,0x7eff6a3d2e80,42890,42890,16384,65536,8070,1048588,2187869542634450,2187863087020944,2187863087039824,2187869542818836
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,171832,171832,1048576,256,0,0,8,8,16,64,0x0,0x7f261105ce80,48069,48069,16384,65536,12763,1638700,194272922419343,194285066464535,194285066489175,194272930391948
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,171832,171832,1048576,256,0,0,8,8,16,64,0x0,0x7f261105ce80,43546,43546,16384,65536,8369,1048580,194272930413559,194285066682455,194285066701335,194272930732383
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,171832,171832,1048576,256,0,0,8,8,16,64,0x0,0x7f261105ce80,43715,43715,16384,65536,8176,1048580,194272930764153,194285066722455,194285066741335,194272930942791
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 2869770 171832 2869770 171832 1048576 256 0 0 8 8 16 64 0x0 0x7eff6a3d2e80 0x7f261105ce80 48732 48069 48732 48069 16384 65536 12984 12763 1684952 1638700 2187869534755189 194272922419343 2187863086843344 194285066464535 2187863086866864 194285066489175 2187869542260328 194272930391948
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2869770 171832 2869770 171832 1048576 256 0 0 8 8 16 64 0x0 0x7eff6a3d2e80 0x7f261105ce80 43698 43546 43698 43546 16384 65536 8101 8369 1048580 2187869542283442 194272930413559 2187863086979504 194285066682455 2187863086998544 194285066701335 2187869542602320 194272930732383
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2869770 171832 2869770 171832 1048576 256 0 0 8 8 16 64 0x0 0x7eff6a3d2e80 0x7f261105ce80 42890 43715 42890 43715 16384 65536 8070 8176 1048588 1048580 2187869542634450 194272930764153 2187863087020944 194285066722455 2187863087039824 194285066741335 2187869542818836 194272930942791
@@ -1,4 +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) ",2,0,0,2869952,2869952,1048576,256,0,0,8,8,16,64,0x0,0x7f72072bae80,0,0,0,2187869977668644,2187863086843344,2187863086866864,2187869985176257
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2869952,2869952,1048576,256,0,0,8,8,16,64,0x0,0x7f72072bae80,0,0,0,2187869985195062,2187863086979504,2187863086998544,2187869985509663
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2869952,2869952,1048576,256,0,0,8,8,16,64,0x0,0x7f72072bae80,0,0,0,2187869985538427,2187863087020944,2187863087039824,2187869985711863
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,172017,172017,1048576,256,0,0,8,8,16,64,0x0,0x7ff6bfca6e80,0,0,0,194273420605668,194285066464535,194285066489175,194273428330044
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,172017,172017,1048576,256,0,0,8,8,16,64,0x0,0x7ff6bfca6e80,0,0,0,194273428350383,194285066682455,194285066701335,194273428660279
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,172017,172017,1048576,256,0,0,8,8,16,64,0x0,0x7ff6bfca6e80,0,0,0,194273428688593,194285066722455,194285066741335,194273428860549
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 2869952 172017 2869952 172017 1048576 256 0 0 8 8 16 64 0x0 0x7f72072bae80 0x7ff6bfca6e80 0 0 0 2187869977668644 194273420605668 2187863086843344 194285066464535 2187863086866864 194285066489175 2187869985176257 194273428330044
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2869952 172017 2869952 172017 1048576 256 0 0 8 8 16 64 0x0 0x7f72072bae80 0x7ff6bfca6e80 0 0 0 2187869985195062 194273428350383 2187863086979504 194285066682455 2187863086998544 194285066701335 2187869985509663 194273428660279
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2869952 172017 2869952 172017 1048576 256 0 0 8 8 16 64 0x0 0x7f72072bae80 0x7ff6bfca6e80 0 0 0 2187869985538427 194273428688593 2187863087020944 194285066722455 2187863087039824 194285066741335 2187869985711863 194273428860549
@@ -1,4 +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) ",2,0,0,2867946,2867946,1048576,256,0,0,8,8,16,64,0x0,0x7fde64f1ae80,65536,193254,24880920,2187864659556927,2187863086843344,2187863086866864,2187864667075622
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2867946,2867946,1048576,256,0,0,8,8,16,64,0x0,0x7fde64f1ae80,65536,177776,22778168,2187864667094427,2187863086979504,2187863086998544,2187864667403628
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2867946,2867946,1048576,256,0,0,8,8,16,64,0x0,0x7fde64f1ae80,65536,177040,22689848,2187864667432131,2187863087020944,2187863087039824,2187864667600928
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,172202,172202,1048576,256,0,0,8,8,16,64,0x0,0x7f80dbc10e80,65536,198372,25466512,194273910775706,194285066464535,194285066489175,194273918668841
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,172202,172202,1048576,256,0,0,8,8,16,64,0x0,0x7f80dbc10e80,65536,178410,22861520,194273918687927,194285066682455,194285066701335,194273919011510
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,172202,172202,1048576,256,0,0,8,8,16,64,0x0,0x7f80dbc10e80,65536,178762,22853312,194273919039884,194285066722455,194285066741335,194273919232939
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 2867946 172202 2867946 172202 1048576 256 0 0 8 8 16 64 0x0 0x7fde64f1ae80 0x7f80dbc10e80 65536 193254 198372 24880920 25466512 2187864659556927 194273910775706 2187863086843344 194285066464535 2187863086866864 194285066489175 2187864667075622 194273918668841
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2867946 172202 2867946 172202 1048576 256 0 0 8 8 16 64 0x0 0x7fde64f1ae80 0x7f80dbc10e80 65536 177776 178410 22778168 22861520 2187864667094427 194273918687927 2187863086979504 194285066682455 2187863086998544 194285066701335 2187864667403628 194273919011510
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2867946 172202 2867946 172202 1048576 256 0 0 8 8 16 64 0x0 0x7fde64f1ae80 0x7f80dbc10e80 65536 177040 178762 22689848 22853312 2187864667432131 194273919039884 2187863087020944 194285066722455 2187863087039824 194285066741335 2187864667600928 194273919232939
@@ -1,4 +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) ",2,0,0,2870680,2870680,1048576,256,0,0,8,8,16,64,0x0,0x7f9a920b2e80,32768,646946,82808524,2187872008481374,2187863086843344,2187863086866864,2187872016007002
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2870680,2870680,1048576,256,0,0,8,8,16,64,0x0,0x7f9a920b2e80,32768,665028,85108136,2187872016024845,2187863086979504,2187863086998544,2187872016349314
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2870680,2870680,1048576,256,0,0,8,8,16,64,0x0,0x7f9a920b2e80,32768,662924,84848200,2187872016378269,2187863087020944,2187863087039824,2187872016554119
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,172388,172388,1048576,256,0,0,8,8,16,64,0x0,0x7f91b7fd6e80,32768,645046,82562784,194274390775457,194285066464535,194285066489175,194274398576077
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,172388,172388,1048576,256,0,0,8,8,16,64,0x0,0x7f91b7fd6e80,32768,656009,83967432,194274398595203,194285066682455,194285066701335,194274398895572
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,172388,172388,1048576,256,0,0,8,8,16,64,0x0,0x7f91b7fd6e80,32768,654851,83819532,194274398924006,194285066722455,194285066741335,194274399099017
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 2870680 172388 2870680 172388 1048576 256 0 0 8 8 16 64 0x0 0x7f9a920b2e80 0x7f91b7fd6e80 32768 646946 645046 82808524 82562784 2187872008481374 194274390775457 2187863086843344 194285066464535 2187863086866864 194285066489175 2187872016007002 194274398576077
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2870680 172388 2870680 172388 1048576 256 0 0 8 8 16 64 0x0 0x7f9a920b2e80 0x7f91b7fd6e80 32768 665028 656009 85108136 83967432 2187872016024845 194274398595203 2187863086979504 194285066682455 2187863086998544 194285066701335 2187872016349314 194274398895572
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2870680 172388 2870680 172388 1048576 256 0 0 8 8 16 64 0x0 0x7f9a920b2e80 0x7f91b7fd6e80 32768 662924 654851 84848200 83819532 2187872016378269 194274398924006 2187863087020944 194285066722455 2187863087039824 194285066741335 2187872016554119 194274399099017
@@ -1,4 +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) ",2,0,0,2870862,2870862,1048576,256,0,0,8,8,16,64,0x0,0x7febf83ace80,49355,49355,18227,394848,16384,25114743,232859,0,100948108,2187872453712459,2187863086843344,2187863086866864,2187872461243888
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2870862,2870862,1048576,256,0,0,8,8,16,64,0x0,0x7febf83ace80,44034,44034,15357,352280,16384,24796619,227952,0,99683264,2187872461273072,2187863086979504,2187863086998544,2187872461597281
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2870862,2870862,1048576,256,0,0,8,8,16,64,0x0,0x7febf83ace80,44730,44730,15579,357848,16384,24297029,232090,0,97687376,2187872461636034,2187863087020944,2187863087039824,2187872461826611
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,172574,172574,1048576,256,0,0,8,8,16,64,0x0,0x7f63ef9aae80,48374,48374,16676,387000,16384,25449189,235661,0,102288864,194274879224637,194285066464535,194285066489175,194274887852072
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,172574,172574,1048576,256,0,0,8,8,16,64,0x0,0x7f63ef9aae80,42333,42333,13500,338672,16384,24694478,228632,0,99275804,194274887882279,194285066682455,194285066701335,194274888171918
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,172574,172574,1048576,256,0,0,8,8,16,64,0x0,0x7f63ef9aae80,42877,42877,13541,343024,16384,24621688,230950,0,98996648,194274888210190,194285066722455,194285066741335,194274888401232
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 2870862 172574 2870862 172574 1048576 256 0 0 8 8 16 64 0x0 0x7febf83ace80 0x7f63ef9aae80 49355 48374 49355 48374 18227 16676 394848 387000 16384 25114743 25449189 232859 235661 0 100948108 102288864 2187872453712459 194274879224637 2187863086843344 194285066464535 2187863086866864 194285066489175 2187872461243888 194274887852072
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2870862 172574 2870862 172574 1048576 256 0 0 8 8 16 64 0x0 0x7febf83ace80 0x7f63ef9aae80 44034 42333 44034 42333 15357 13500 352280 338672 16384 24796619 24694478 227952 228632 0 99683264 99275804 2187872461273072 194274887882279 2187863086979504 194285066682455 2187863086998544 194285066701335 2187872461597281 194274888171918
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2870862 172574 2870862 172574 1048576 256 0 0 8 8 16 64 0x0 0x7febf83ace80 0x7f63ef9aae80 44730 42877 44730 42877 15579 13541 357848 343024 16384 24297029 24621688 232090 230950 0 97687376 98996648 2187872461636034 194274888210190 2187863087020944 194285066722455 2187863087039824 194285066741335 2187872461826611 194274888401232
File diff suppressed because one or more lines are too long
@@ -1,2 +1,2 @@
workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
device_filter,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:46:13 2024 (CST),1,t006-003.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,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1
device_filter,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:08:57 PM (CST),2,t008-007.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,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1
1 workload_name command ip_blocks timestamp version hostname cpu_model sbios linux_distro linux_kernel_version amd_gpu_kernel_version cpu_memory gpu_memory rocm_version vbios compute_partition memory_partition gpu_model gpu_arch gpu_l1 gpu_l2 cu_per_gpu simd_per_cu se_per_gpu wave_size workgroup_max_size max_waves_per_cu max_sclk max_mclk cur_sclk cur_mclk total_l2_chan lds_banks_per_cu sqc_per_gpu pipes_per_gpu hbm_bw num_xcd
2 device_filter ./tests/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF Fri Mar 1 16:46:13 2024 (CST) Thu 07 Mar 2024 01:08:57 PM (CST) 1 2 t006-003.hpcfund t008-007.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 527651240 527651100 5.7.1-98 6.0.2-115 113-D3431401-100 NA NA MI100 gfx908 16 8192 120 4 8 64 1024 40 1502 1200 1502 1200 32 32 64 4 1228.8 1
@@ -1,4 +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) [clone .kd]",2,0,0,2867400,2867400,1048576,256,0,0,8,8,16,64,0x0,0x7f1016c04e80,2187863086818021,2187863086843344,2187863086866864,2187863086880578
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2867400,2867400,1048576,256,0,0,8,8,16,64,0x0,0x7f1016c04e80,2187863086879366,2187863086979504,2187863086998544,2187863086999782
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2867400,2867400,1048576,256,0,0,8,8,16,64,0x0,0x7f1016c04e80,2187863087011163,2187863087020944,2187863087039824,2187863087040899
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,175921,175921,1048576,256,0,0,8,8,16,64,0x0,0x7ff832f9ae80,194285066439120,194285066464535,194285066489175,194285066502310
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,175921,175921,1048576,256,0,0,8,8,16,64,0x0,0x7ff832f9ae80,194285066502350,194285066682455,194285066701335,194285066702839
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,175921,175921,1048576,256,0,0,8,8,16,64,0x0,0x7ff832f9ae80,194285066713930,194285066722455,194285066741335,194285066742634
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) [clone .kd] 2 0 0 2867400 175921 2867400 175921 1048576 256 0 0 8 8 16 64 0x0 0x7f1016c04e80 0x7ff832f9ae80 2187863086818021 194285066439120 2187863086843344 194285066464535 2187863086866864 194285066489175 2187863086880578 194285066502310
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 2867400 175921 2867400 175921 1048576 256 0 0 8 8 16 64 0x0 0x7f1016c04e80 0x7ff832f9ae80 2187863086879366 194285066502350 2187863086979504 194285066682455 2187863086998544 194285066701335 2187863086999782 194285066702839
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 2867400 175921 2867400 175921 1048576 256 0 0 8 8 16 64 0x0 0x7f1016c04e80 0x7ff832f9ae80 2187863087011163 194285066713930 2187863087020944 194285066722455 2187863087039824 194285066741335 2187863087040899 194285066742634
@@ -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) ",2,0,0,330344,330344,1048576,256,0,0,8,0,16,64,0x0,0x7fe6cf348ec0,27379,27379,16384,65536,13546,1530804,199109067732799,199121780771567,199121780791247,199109083780798
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,330344,330344,1048576,256,0,0,8,0,16,64,0x0,0x7fe6cf348ec0,40641,40641,16384,65536,9422,1048620,199109083800004,199121780810127,199121780825807,199109084104139
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,330344,330344,1048576,256,0,0,8,0,16,64,0x0,0x7fe6cf348ec0,40214,40214,16384,65536,9321,1048756,199109084143764,199121780890127,199121780906607,199109084308516
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 330344 330344 1048576 256 0 0 8 0 16 64 0x0 0x7fe6cf348ec0 27379 27379 16384 65536 13546 1530804 199109067732799 199121780771567 199121780791247 199109083780798
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 330344 330344 1048576 256 0 0 8 0 16 64 0x0 0x7fe6cf348ec0 40641 40641 16384 65536 9422 1048620 199109083800004 199121780810127 199121780825807 199109084104139
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 330344 330344 1048576 256 0 0 8 0 16 64 0x0 0x7fe6cf348ec0 40214 40214 16384 65536 9321 1048756 199109084143764 199121780890127 199121780906607 199109084308516
@@ -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) ",2,0,0,330545,330545,1048576,256,0,0,8,0,16,64,0x0,0x7f3c42f94ec0,0,0,0,199109550821338,199121780771567,199121780791247,199109566789335
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,330545,330545,1048576,256,0,0,8,0,16,64,0x0,0x7f3c42f94ec0,0,0,0,199109566805174,199121780810127,199121780825807,199109567096836
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,330545,330545,1048576,256,0,0,8,0,16,64,0x0,0x7f3c42f94ec0,0,0,0,199109567123557,199121780890127,199121780906607,199109567286696
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 330545 330545 1048576 256 0 0 8 0 16 64 0x0 0x7f3c42f94ec0 0 0 0 199109550821338 199121780771567 199121780791247 199109566789335
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 330545 330545 1048576 256 0 0 8 0 16 64 0x0 0x7f3c42f94ec0 0 0 0 199109566805174 199121780810127 199121780825807 199109567096836
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 330545 330545 1048576 256 0 0 8 0 16 64 0x0 0x7f3c42f94ec0 0 0 0 199109567123557 199121780890127 199121780906607 199109567286696
@@ -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) ",2,0,0,330728,330728,1048576,256,0,0,8,0,16,64,0x0,0x7fc8f8a6cec0,65536,211460,23579520,199110030597901,199121780771567,199121780791247,199110046727484
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,330728,330728,1048576,256,0,0,8,0,16,64,0x0,0x7fc8f8a6cec0,65536,254912,28465096,199110046748423,199121780810127,199121780825807,199110047009096
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,330728,330728,1048576,256,0,0,8,0,16,64,0x0,0x7fc8f8a6cec0,65536,258838,28871464,199110047035506,199121780890127,199121780906607,199110047184308
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 330728 330728 1048576 256 0 0 8 0 16 64 0x0 0x7fc8f8a6cec0 65536 211460 23579520 199110030597901 199121780771567 199121780791247 199110046727484
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 330728 330728 1048576 256 0 0 8 0 16 64 0x0 0x7fc8f8a6cec0 65536 254912 28465096 199110046748423 199121780810127 199121780825807 199110047009096
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 330728 330728 1048576 256 0 0 8 0 16 64 0x0 0x7fc8f8a6cec0 65536 258838 28871464 199110047035506 199121780890127 199121780906607 199110047184308
@@ -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) ",2,0,0,330929,330929,1048576,256,0,0,8,0,16,64,0x0,0x7fd12bbd8ec0,32768,288902,32346476,199110514009110,199121780771567,199121780791247,199110529778261
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,330929,330929,1048576,256,0,0,8,0,16,64,0x0,0x7fd12bbd8ec0,32768,593947,66524552,199110529795433,199121780810127,199121780825807,199110530092144
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,330929,330929,1048576,256,0,0,8,0,16,64,0x0,0x7fd12bbd8ec0,32768,602236,67452520,199110530118254,199121780890127,199121780906607,199110530290219
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 330929 330929 1048576 256 0 0 8 0 16 64 0x0 0x7fd12bbd8ec0 32768 288902 32346476 199110514009110 199121780771567 199121780791247 199110529778261
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 330929 330929 1048576 256 0 0 8 0 16 64 0x0 0x7fd12bbd8ec0 32768 593947 66524552 199110529795433 199121780810127 199121780825807 199110530092144
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 330929 330929 1048576 256 0 0 8 0 16 64 0x0 0x7fd12bbd8ec0 32768 602236 67452520 199110530118254 199121780890127 199121780906607 199110530290219
@@ -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) ",2,0,0,331115,331115,1048576,256,0,0,8,0,16,64,0x0,0x7f16a9730ec0,27492,27492,10876,219944,16384,10773590,127834,0,43600528,199110993347043,199121780771567,199121780791247,199111009505921
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,331115,331115,1048576,256,0,0,8,0,16,64,0x0,0x7f16a9730ec0,41046,41046,13175,328376,16384,19783221,224811,0,79611516,199111009533263,199121780810127,199121780825807,199111009819264
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,331115,331115,1048576,256,0,0,8,0,16,64,0x0,0x7f16a9730ec0,40621,40621,11924,324976,16384,19553416,225262,0,78707700,199111009854681,199121780890127,199121780906607,199111010019924
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 331115 331115 1048576 256 0 0 8 0 16 64 0x0 0x7f16a9730ec0 27492 27492 10876 219944 16384 10773590 127834 0 43600528 199110993347043 199121780771567 199121780791247 199111009505921
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 331115 331115 1048576 256 0 0 8 0 16 64 0x0 0x7f16a9730ec0 41046 41046 13175 328376 16384 19783221 224811 0 79611516 199111009533263 199121780810127 199121780825807 199111009819264
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 331115 331115 1048576 256 0 0 8 0 16 64 0x0 0x7f16a9730ec0 40621 40621 11924 324976 16384 19553416 225262 0 78707700 199111009854681 199121780890127 199121780906607 199111010019924
@@ -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_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU 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_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 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_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 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 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_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG 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_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES 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:
File diff suppressed because one or more lines are too long
@@ -0,0 +1,2 @@
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
0,1388.6548,1388.108,1389.2015,5015.9297,5012.8184,5019.041,9223.8145,9223.0537,9224.5752,18052.502,18051.623,18053.381,20935.658,20875.303,20996.014,20266.73,20266.039,20267.422,170456.62,170450.44,170462.81,164889.83,164885.14,164894.52,41426.273,41425.676,41426.871,41480.551,41480.051,41481.051,166346.09,165855.02,166837.17
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 1388.6548 1388.108 1389.2015 5015.9297 5012.8184 5019.041 9223.8145 9223.0537 9224.5752 18052.502 18051.623 18053.381 20935.658 20875.303 20996.014 20266.73 20266.039 20267.422 170456.62 170450.44 170462.81 164889.83 164885.14 164894.52 41426.273 41425.676 41426.871 41480.551 41480.051 41481.051 166346.09 165855.02 166837.17
@@ -0,0 +1,2 @@
workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
device_filter,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:29:36 PM (CST),2,t007-002.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,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1
1 workload_name command ip_blocks timestamp version hostname cpu_model sbios linux_distro linux_kernel_version amd_gpu_kernel_version cpu_memory gpu_memory rocm_version vbios compute_partition memory_partition gpu_model gpu_arch gpu_l1 gpu_l2 cu_per_gpu simd_per_cu se_per_gpu wave_size workgroup_max_size max_waves_per_cu max_sclk max_mclk cur_sclk cur_mclk total_l2_chan lds_banks_per_cu sqc_per_gpu pipes_per_gpu hbm_bw num_xcd
2 device_filter ./sample/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline Thu 07 Mar 2024 02:29:36 PM (CST) 2 t007-002.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 527650760 6.0.2-115 113-D67301-059 NA NA MI200 gfx90a 16 8192 104 4 8 64 1024 32 1700 1600 1700 1600 32 32 56 4 1638.4 1
@@ -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) [clone .kd]",2,0,0,334902,334902,1048576,256,0,0,8,0,16,64,0x0,0x7fc789a84ec0,199121780746738,199121780771567,199121780791247,199121780807012
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,334902,334902,1048576,256,0,0,8,0,16,64,0x0,0x7fc789a84ec0,199121780801932,199121780810127,199121780825807,199121780887234
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,334902,334902,1048576,256,0,0,8,0,16,64,0x0,0x7fc789a84ec0,199121780836327,199121780890127,199121780906607,199121780907502
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) [clone .kd] 2 0 0 334902 334902 1048576 256 0 0 8 0 16 64 0x0 0x7fc789a84ec0 199121780746738 199121780771567 199121780791247 199121780807012
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 334902 334902 1048576 256 0 0 8 0 16 64 0x0 0x7fc789a84ec0 199121780801932 199121780810127 199121780825807 199121780887234
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 334902 334902 1048576 256 0 0 8 0 16 64 0x0 0x7fc789a84ec0 199121780836327 199121780890127 199121780906607 199121780907502
@@ -1,4 +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) ",2,0,0,2858631,2858631,1048576,256,0,0,8,8,16,64,0x0,0x7f306d022e80,48693,48693,16384,65536,14587,1861268,2187837651454006,2187843682406959,2187843682431279,2187837659153650
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2858631,2858631,1048576,256,0,0,8,8,16,64,0x0,0x7f306d022e80,43450,43450,16384,65536,8185,1048576,2187837659175581,2187843682524719,2187843682543599,2187837659498637
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2858631,2858631,1048576,256,0,0,8,8,16,64,0x0,0x7f306d022e80,42429,42429,16384,65536,8118,1048580,2187837659530768,2187843682565519,2187843682585039,2187837659713381
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,163106,163106,1048576,256,0,0,8,8,16,64,0x0,0x7fd0d59ece80,47824,47824,16384,65536,14415,1841604,194245701996654,194257894802798,194257894826478,194245709757699
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,163106,163106,1048576,256,0,0,8,8,16,64,0x0,0x7fd0d59ece80,42607,42607,16384,65536,8172,1048580,194245709780272,194257894909678,194257894929198,194245710148639
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,163106,163106,1048576,256,0,0,8,8,16,64,0x0,0x7fd0d59ece80,42359,42359,16384,65536,8301,1048580,194245710180850,194257894949838,194257894968558,194245710367043
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 2858631 163106 2858631 163106 1048576 256 0 0 8 8 16 64 0x0 0x7f306d022e80 0x7fd0d59ece80 48693 47824 48693 47824 16384 65536 14587 14415 1861268 1841604 2187837651454006 194245701996654 2187843682406959 194257894802798 2187843682431279 194257894826478 2187837659153650 194245709757699
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2858631 163106 2858631 163106 1048576 256 0 0 8 8 16 64 0x0 0x7f306d022e80 0x7fd0d59ece80 43450 42607 43450 42607 16384 65536 8185 8172 1048576 1048580 2187837659175581 194245709780272 2187843682524719 194257894909678 2187843682543599 194257894929198 2187837659498637 194245710148639
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2858631 163106 2858631 163106 1048576 256 0 0 8 8 16 64 0x0 0x7f306d022e80 0x7fd0d59ece80 42429 42359 42429 42359 16384 65536 8118 8301 1048580 2187837659530768 194245710180850 2187843682565519 194257894949838 2187843682585039 194257894968558 2187837659713381 194245710367043
@@ -1,4 +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) ",2,0,0,2862637,2862637,1048576,256,0,0,8,8,16,64,0x0,0x7f5be8850e80,0,0,0,2187848852549207,2187843682406959,2187843682431279,2187848859975488
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2862637,2862637,1048576,256,0,0,8,8,16,64,0x0,0x7f5be8850e80,0,0,0,2187848859994684,2187843682524719,2187843682543599,2187848860303414
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2862637,2862637,1048576,256,0,0,8,8,16,64,0x0,0x7f5be8850e80,0,0,0,2187848860332038,2187843682565519,2187843682585039,2187848860506154
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,163295,163295,1048576,256,0,0,8,8,16,64,0x0,0x7f1c0fd10e80,0,0,0,194246201989340,194257894802798,194257894826478,194246209682066
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,163295,163295,1048576,256,0,0,8,8,16,64,0x0,0x7f1c0fd10e80,0,0,0,194246209701843,194257894909678,194257894929198,194246209982224
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,163295,163295,1048576,256,0,0,8,8,16,64,0x0,0x7f1c0fd10e80,0,0,0,194246210010568,194257894949838,194257894968558,194246210167986
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 2862637 163295 2862637 163295 1048576 256 0 0 8 8 16 64 0x0 0x7f5be8850e80 0x7f1c0fd10e80 0 0 0 2187848852549207 194246201989340 2187843682406959 194257894802798 2187843682431279 194257894826478 2187848859975488 194246209682066
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2862637 163295 2862637 163295 1048576 256 0 0 8 8 16 64 0x0 0x7f5be8850e80 0x7f1c0fd10e80 0 0 0 2187848859994684 194246209701843 2187843682524719 194257894909678 2187843682543599 194257894929198 2187848860303414 194246209982224
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2862637 163295 2862637 163295 1048576 256 0 0 8 8 16 64 0x0 0x7f5be8850e80 0x7f1c0fd10e80 0 0 0 2187848860332038 194246210010568 2187843682565519 194257894949838 2187843682585039 194257894968558 2187848860506154 194246210167986
@@ -1,4 +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) ",2,0,0,2861181,2861181,1048576,256,0,0,8,8,16,64,0x0,0x7f4afbf56e80,65536,210560,26916328,2187844811633072,2187843682406959,2187843682431279,2187844819158530
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2861181,2861181,1048576,256,0,0,8,8,16,64,0x0,0x7f4afbf56e80,65536,180192,23099952,2187844819178597,2187843682524719,2187843682543599,2187844819476596
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2861181,2861181,1048576,256,0,0,8,8,16,64,0x0,0x7f4afbf56e80,65536,192032,24611128,2187844819505521,2187843682565519,2187843682585039,2187844819677133
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,163481,163481,1048576,256,0,0,8,8,16,64,0x0,0x7f41294aee80,65536,202308,25952544,194246693370130,194257894802798,194257894826478,194246701328779
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,163481,163481,1048576,256,0,0,8,8,16,64,0x0,0x7f41294aee80,65536,182670,23344896,194246701348828,194257894909678,194257894929198,194246701641622
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,163481,163481,1048576,256,0,0,8,8,16,64,0x0,0x7f41294aee80,65536,181360,23270400,194246701670366,194257894949838,194257894968558,194246701840689
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 2861181 163481 2861181 163481 1048576 256 0 0 8 8 16 64 0x0 0x7f4afbf56e80 0x7f41294aee80 65536 210560 202308 26916328 25952544 2187844811633072 194246693370130 2187843682406959 194257894802798 2187843682431279 194257894826478 2187844819158530 194246701328779
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2861181 163481 2861181 163481 1048576 256 0 0 8 8 16 64 0x0 0x7f4afbf56e80 0x7f41294aee80 65536 180192 182670 23099952 23344896 2187844819178597 194246701348828 2187843682524719 194257894909678 2187843682543599 194257894929198 2187844819476596 194246701641622
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2861181 163481 2861181 163481 1048576 256 0 0 8 8 16 64 0x0 0x7f4afbf56e80 0x7f41294aee80 65536 192032 181360 24611128 23270400 2187844819505521 194246701670366 2187843682565519 194257894949838 2187843682585039 194257894968558 2187844819677133 194246701840689
@@ -1,4 +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) ",2,0,0,2859725,2859725,1048576,256,0,0,8,8,16,64,0x0,0x7f77365b0e80,32768,648628,83041940,2187840584839972,2187843682406959,2187843682431279,2187840592444006
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2859725,2859725,1048576,256,0,0,8,8,16,64,0x0,0x7f77365b0e80,32768,665455,85189652,2187840592464465,2187843682524719,2187843682543599,2187840592804623
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2859725,2859725,1048576,256,0,0,8,8,16,64,0x0,0x7f77365b0e80,32768,630264,80689312,2187840592833738,2187843682565519,2187843682585039,2187840593022011
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,163664,163664,1048576,256,0,0,8,8,16,64,0x0,0x7f0703804e80,32768,645357,82598164,194247183554014,194257894802798,194257894826478,194247191243955
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,163664,163664,1048576,256,0,0,8,8,16,64,0x0,0x7f0703804e80,32768,670028,85765020,194247191265515,194257894909678,194257894929198,194247191518214
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,163664,163664,1048576,256,0,0,8,8,16,64,0x0,0x7f0703804e80,32768,644220,82464252,194247191549022,194257894949838,194257894968558,194247191732850
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 2859725 163664 2859725 163664 1048576 256 0 0 8 8 16 64 0x0 0x7f77365b0e80 0x7f0703804e80 32768 648628 645357 83041940 82598164 2187840584839972 194247183554014 2187843682406959 194257894802798 2187843682431279 194257894826478 2187840592444006 194247191243955
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2859725 163664 2859725 163664 1048576 256 0 0 8 8 16 64 0x0 0x7f77365b0e80 0x7f0703804e80 32768 665455 670028 85189652 85765020 2187840592464465 194247191265515 2187843682524719 194257894909678 2187843682543599 194257894929198 2187840592804623 194247191518214
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2859725 163664 2859725 163664 1048576 256 0 0 8 8 16 64 0x0 0x7f77365b0e80 0x7f0703804e80 32768 630264 644220 80689312 82464252 2187840592833738 194247191549022 2187843682565519 194257894949838 2187843682585039 194257894968558 2187840593022011 194247191732850
@@ -1,4 +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) ",2,0,0,2861545,2861545,1048576,256,0,0,8,8,16,64,0x0,0x7f66b3458e80,49547,49547,16868,396384,16384,26740947,242792,0,107460160,2187845706739501,2187843682406959,2187843682431279,2187845714403057
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2861545,2861545,1048576,256,0,0,8,8,16,64,0x0,0x7f66b3458e80,43543,43543,13929,348352,16384,25132807,235648,0,101028984,2187845714431621,2187843682524719,2187843682543599,2187845714748586
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2861545,2861545,1048576,256,0,0,8,8,16,64,0x0,0x7f66b3458e80,43359,43359,14054,346880,16384,24431177,229443,0,98220436,2187845714786918,2187843682565519,2187843682585039,2187845714981864
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,163849,163849,1048576,256,0,0,8,8,16,64,0x0,0x7f24c9b52e80,48152,48152,17278,385224,16384,24999057,233984,0,100494368,194247678463586,194257894802798,194257894826478,194247686158065
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,163849,163849,1048576,256,0,0,8,8,16,64,0x0,0x7f24c9b52e80,42999,42999,13485,344000,16384,25054375,233600,0,100720288,194247686185978,194257894909678,194257894929198,194247686516484
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,163849,163849,1048576,256,0,0,8,8,16,64,0x0,0x7f24c9b52e80,43151,43151,13780,345216,16384,23923902,232092,0,96192684,194247686554565,194257894949838,194257894968558,194247686738744
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 2861545 163849 2861545 163849 1048576 256 0 0 8 8 16 64 0x0 0x7f66b3458e80 0x7f24c9b52e80 49547 48152 49547 48152 16868 17278 396384 385224 16384 26740947 24999057 242792 233984 0 107460160 100494368 2187845706739501 194247678463586 2187843682406959 194257894802798 2187843682431279 194257894826478 2187845714403057 194247686158065
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2861545 163849 2861545 163849 1048576 256 0 0 8 8 16 64 0x0 0x7f66b3458e80 0x7f24c9b52e80 43543 42999 43543 42999 13929 13485 348352 344000 16384 25132807 25054375 235648 233600 0 101028984 100720288 2187845714431621 194247686185978 2187843682524719 194257894909678 2187843682543599 194257894929198 2187845714748586 194247686516484
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2861545 163849 2861545 163849 1048576 256 0 0 8 8 16 64 0x0 0x7f66b3458e80 0x7f24c9b52e80 43359 43151 43359 43151 14054 13780 346880 345216 16384 24431177 23923902 229443 232092 0 98220436 96192684 2187845714786918 194247686554565 2187843682565519 194257894949838 2187843682585039 194257894968558 2187845714981864 194247686738744
@@ -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
@@ -1,2 +1,2 @@
workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
device_inv_int,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:45:48 2024 (CST),1,t006-003.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,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1
device_inv_int,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:08:30 PM (CST),2,t008-007.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,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1
1 workload_name command ip_blocks timestamp version hostname cpu_model sbios linux_distro linux_kernel_version amd_gpu_kernel_version cpu_memory gpu_memory rocm_version vbios compute_partition memory_partition gpu_model gpu_arch gpu_l1 gpu_l2 cu_per_gpu simd_per_cu se_per_gpu wave_size workgroup_max_size max_waves_per_cu max_sclk max_mclk cur_sclk cur_mclk total_l2_chan lds_banks_per_cu sqc_per_gpu pipes_per_gpu hbm_bw num_xcd
2 device_inv_int ./tests/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF Fri Mar 1 16:45:48 2024 (CST) Thu 07 Mar 2024 01:08:30 PM (CST) 1 2 t006-003.hpcfund t008-007.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 527651240 527651100 5.7.1-98 6.0.2-115 113-D3431401-100 NA NA MI100 gfx908 16 8192 120 4 8 64 1024 40 1502 1200 1502 1200 32 32 64 4 1228.8 1
@@ -1,4 +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) [clone .kd]",2,0,0,2860817,2860817,1048576,256,0,0,8,8,16,64,0x0,0x7fd32b2cce80,2187843682380846,2187843682406959,2187843682431279,2187843682443404
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2860817,2860817,1048576,256,0,0,8,8,16,64,0x0,0x7fd32b2cce80,2187843682444325,2187843682524719,2187843682543599,2187843682544844
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2860817,2860817,1048576,256,0,0,8,8,16,64,0x0,0x7fd32b2cce80,2187843682556025,2187843682565519,2187843682585039,2187843682586092
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,167187,167187,1048576,256,0,0,8,8,16,64,0x0,0x7f75a08c8e80,194257894775994,194257894802798,194257894826478,194257894838072
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,167187,167187,1048576,256,0,0,8,8,16,64,0x0,0x7f75a08c8e80,194257894839254,194257894909678,194257894929198,194257894930367
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,167187,167187,1048576,256,0,0,8,8,16,64,0x0,0x7f75a08c8e80,194257894941187,194257894949838,194257894968558,194257894969812
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) [clone .kd] 2 0 0 2860817 167187 2860817 167187 1048576 256 0 0 8 8 16 64 0x0 0x7fd32b2cce80 0x7f75a08c8e80 2187843682380846 194257894775994 2187843682406959 194257894802798 2187843682431279 194257894826478 2187843682443404 194257894838072
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 2860817 167187 2860817 167187 1048576 256 0 0 8 8 16 64 0x0 0x7fd32b2cce80 0x7f75a08c8e80 2187843682444325 194257894839254 2187843682524719 194257894909678 2187843682543599 194257894929198 2187843682544844 194257894930367
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 2860817 167187 2860817 167187 1048576 256 0 0 8 8 16 64 0x0 0x7fd32b2cce80 0x7f75a08c8e80 2187843682556025 194257894941187 2187843682565519 194257894949838 2187843682585039 194257894968558 2187843682586092 194257894969812
@@ -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) ",2,0,0,320367,320367,1048576,256,0,0,8,0,16,64,0x0,0x7fc46ea24ec0,27912,27912,16384,65536,13514,1516880,198989177854165,199001894935363,199001894955843,198989193725590
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,320367,320367,1048576,256,0,0,8,0,16,64,0x0,0x7fc46ea24ec0,41103,41103,16384,65536,9163,1048712,198989193746269,199001895045923,199001895062403,198989194045705
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,320367,320367,1048576,256,0,0,8,0,16,64,0x0,0x7fc46ea24ec0,42248,42248,16384,65536,9321,1048688,198989194074961,199001895083363,199001895098883,198989194247106
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 320367 320367 1048576 256 0 0 8 0 16 64 0x0 0x7fc46ea24ec0 27912 27912 16384 65536 13514 1516880 198989177854165 199001894935363 199001894955843 198989193725590
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 320367 320367 1048576 256 0 0 8 0 16 64 0x0 0x7fc46ea24ec0 41103 41103 16384 65536 9163 1048712 198989193746269 199001895045923 199001895062403 198989194045705
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 320367 320367 1048576 256 0 0 8 0 16 64 0x0 0x7fc46ea24ec0 42248 42248 16384 65536 9321 1048688 198989194074961 199001895083363 199001895098883 198989194247106
@@ -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) ",2,0,0,320552,320552,1048576,256,0,0,8,0,16,64,0x0,0x7fd2d0168ec0,0,0,0,198989659429121,199001894935363,199001894955843,198989675029403
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,320552,320552,1048576,256,0,0,8,0,16,64,0x0,0x7fd2d0168ec0,0,0,0,198989675045944,199001895045923,199001895062403,198989675468113
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,320552,320552,1048576,256,0,0,8,0,16,64,0x0,0x7fd2d0168ec0,0,0,0,198989675494523,199001895083363,199001895098883,198989675627705
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 320552 320552 1048576 256 0 0 8 0 16 64 0x0 0x7fd2d0168ec0 0 0 0 198989659429121 199001894935363 199001894955843 198989675029403
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 320552 320552 1048576 256 0 0 8 0 16 64 0x0 0x7fd2d0168ec0 0 0 0 198989675045944 199001895045923 199001895062403 198989675468113
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 320552 320552 1048576 256 0 0 8 0 16 64 0x0 0x7fd2d0168ec0 0 0 0 198989675494523 199001895083363 199001895098883 198989675627705
@@ -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) ",2,0,0,320753,320753,1048576,256,0,0,8,0,16,64,0x0,0x7f4cb8e90ec0,65536,170884,19184888,198990137856562,199001894935363,199001894955843,198990153574507
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,320753,320753,1048576,256,0,0,8,0,16,64,0x0,0x7f4cb8e90ec0,65536,270394,30243744,198990153590808,199001895045923,199001895062403,198990153897729
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,320753,320753,1048576,256,0,0,8,0,16,64,0x0,0x7f4cb8e90ec0,65536,259860,29229728,198990153924269,199001895083363,199001895098883,198990154075054
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 320753 320753 1048576 256 0 0 8 0 16 64 0x0 0x7f4cb8e90ec0 65536 170884 19184888 198990137856562 199001894935363 199001894955843 198990153574507
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 320753 320753 1048576 256 0 0 8 0 16 64 0x0 0x7f4cb8e90ec0 65536 270394 30243744 198990153590808 199001895045923 199001895062403 198990153897729
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 320753 320753 1048576 256 0 0 8 0 16 64 0x0 0x7f4cb8e90ec0 65536 259860 29229728 198990153924269 199001895083363 199001895098883 198990154075054
@@ -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) ",2,0,0,320954,320954,1048576,256,0,0,8,0,16,64,0x0,0x7f40f4f68ec0,32768,278475,31173412,198990619125670,199001894935363,199001894955843,198990634836722
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,320954,320954,1048576,256,0,0,8,0,16,64,0x0,0x7f40f4f68ec0,32768,559977,62717076,198990634856980,199001895045923,199001895062403,198990635121510
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,320954,320954,1048576,256,0,0,8,0,16,64,0x0,0x7f40f4f68ec0,32768,569028,63722036,198990635147840,199001895083363,199001895098883,198990635324454
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 320954 320954 1048576 256 0 0 8 0 16 64 0x0 0x7f40f4f68ec0 32768 278475 31173412 198990619125670 199001894935363 199001894955843 198990634836722
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 320954 320954 1048576 256 0 0 8 0 16 64 0x0 0x7f40f4f68ec0 32768 559977 62717076 198990634856980 199001895045923 199001895062403 198990635121510
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 320954 320954 1048576 256 0 0 8 0 16 64 0x0 0x7f40f4f68ec0 32768 569028 63722036 198990635147840 199001895083363 199001895098883 198990635324454
@@ -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) ",2,0,0,321157,321157,1048576,256,0,0,8,0,16,64,0x0,0x7f6e1b100ec0,29013,29013,11176,232112,16384,11736679,138268,0,47442548,198991099206579,199001894935363,199001894955843,198991115265029
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,321157,321157,1048576,256,0,0,8,0,16,64,0x0,0x7f6e1b100ec0,40851,40851,13491,326816,16384,18989824,219727,0,76441744,198991115292040,199001895045923,199001895062403,198991115577520
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,321157,321157,1048576,256,0,0,8,0,16,64,0x0,0x7f6e1b100ec0,41371,41371,13947,330976,16384,19441122,223986,0,78257552,198991115612746,199001895083363,199001895098883,198991115779131
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 321157 321157 1048576 256 0 0 8 0 16 64 0x0 0x7f6e1b100ec0 29013 29013 11176 232112 16384 11736679 138268 0 47442548 198991099206579 199001894935363 199001894955843 198991115265029
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 321157 321157 1048576 256 0 0 8 0 16 64 0x0 0x7f6e1b100ec0 40851 40851 13491 326816 16384 18989824 219727 0 76441744 198991115292040 199001895045923 199001895062403 198991115577520
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 321157 321157 1048576 256 0 0 8 0 16 64 0x0 0x7f6e1b100ec0 41371 41371 13947 330976 16384 19441122 223986 0 78257552 198991115612746 199001895083363 199001895098883 198991115779131
@@ -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_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU 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_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 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_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 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 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_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG 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_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES 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:
File diff suppressed because one or more lines are too long
@@ -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
0,1388.4407,1387.9556,1388.9258,5012.3818,5009.4272,5015.3364,9220.9736,9220.4082,9221.5391,18048.867,18047.982,18049.752,20929.025,20868.734,20989.316,20262.105,20261.408,20262.803,170368.28,170364.62,170371.94,164833.34,164829.61,164837.08,41411.355,41410.75,41411.961,41471.086,41470.277,41471.895,166320.92,165829.64,166812.2
1,1388.9957,1388.3947,1389.5968,5027.0874,5024.9897,5029.1851,9231.418,9230.6963,9232.1396,18088.484,18084.846,18092.123,20968.271,20901.262,21035.281,20286.959,20286.332,20287.586,170792.02,170786.41,170797.62,165064.95,165061.06,165068.84,41475.48,41474.453,41476.508,41528.645,41527.684,41529.605,166824.89,166821.84,166827.94
2,1388.7762,1388.223,1389.3295,5033.8354,5031.5078,5036.1631,9260.0098,9259.3555,9260.6641,18109.824,18108.805,18110.844,21048.404,21047.924,21048.885,20354.592,20354.098,20355.086,171145.12,171140.94,171149.31,165515.59,165511.66,165519.53,41583.41,41582.383,41584.438,41643.316,41641.996,41644.637,166962.69,166359.5,167565.88
3,1389.2411,1388.7584,1389.7238,5030.2002,5028.9575,5031.4429,9239.7422,9239.1396,9240.3447,18027.953,18024.689,18031.217,21032.553,21032.098,21033.008,20313.242,20312.57,20313.914,171017.05,171013.84,171020.25,165231.08,165227.28,165234.88,41521.387,41520.555,41522.219,41580.211,41579.453,41580.969,167016.34,167014.17,167018.52
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 1388.4407 1387.9556 1388.9258 5012.3818 5009.4272 5015.3364 9220.9736 9220.4082 9221.5391 18048.867 18047.982 18049.752 20929.025 20868.734 20989.316 20262.105 20261.408 20262.803 170368.28 170364.62 170371.94 164833.34 164829.61 164837.08 41411.355 41410.75 41411.961 41471.086 41470.277 41471.895 166320.92 165829.64 166812.2
3 1 1388.9957 1388.3947 1389.5968 5027.0874 5024.9897 5029.1851 9231.418 9230.6963 9232.1396 18088.484 18084.846 18092.123 20968.271 20901.262 21035.281 20286.959 20286.332 20287.586 170792.02 170786.41 170797.62 165064.95 165061.06 165068.84 41475.48 41474.453 41476.508 41528.645 41527.684 41529.605 166824.89 166821.84 166827.94
4 2 1388.7762 1388.223 1389.3295 5033.8354 5031.5078 5036.1631 9260.0098 9259.3555 9260.6641 18109.824 18108.805 18110.844 21048.404 21047.924 21048.885 20354.592 20354.098 20355.086 171145.12 171140.94 171149.31 165515.59 165511.66 165519.53 41583.41 41582.383 41584.438 41643.316 41641.996 41644.637 166962.69 166359.5 167565.88
5 3 1389.2411 1388.7584 1389.7238 5030.2002 5028.9575 5031.4429 9239.7422 9239.1396 9240.3447 18027.953 18024.689 18031.217 21032.553 21032.098 21033.008 20313.242 20312.57 20313.914 171017.05 171013.84 171020.25 165231.08 165227.28 165234.88 41521.387 41520.555 41522.219 41580.211 41579.453 41580.969 167016.34 167014.17 167018.52
@@ -0,0 +1,2 @@
workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
device_inv_int,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:27:36 PM (CST),2,t007-002.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,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1
1 workload_name command ip_blocks timestamp version hostname cpu_model sbios linux_distro linux_kernel_version amd_gpu_kernel_version cpu_memory gpu_memory rocm_version vbios compute_partition memory_partition gpu_model gpu_arch gpu_l1 gpu_l2 cu_per_gpu simd_per_cu se_per_gpu wave_size workgroup_max_size max_waves_per_cu max_sclk max_mclk cur_sclk cur_mclk total_l2_chan lds_banks_per_cu sqc_per_gpu pipes_per_gpu hbm_bw num_xcd
2 device_inv_int ./sample/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline Thu 07 Mar 2024 02:27:36 PM (CST) 2 t007-002.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 527650760 6.0.2-115 113-D67301-059 NA NA MI200 gfx90a 16 8192 104 4 8 64 1024 32 1700 1600 1700 1600 32 32 56 4 1638.4 1
@@ -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) [clone .kd]",2,0,0,325033,325033,1048576,256,0,0,8,0,16,64,0x0,0x7f31a7fccec0,199001894911168,199001894935363,199001894955843,199001894968617
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,325033,325033,1048576,256,0,0,8,0,16,64,0x0,0x7f31a7fccec0,199001894966613,199001895045923,199001895062403,199001895063647
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,325033,325033,1048576,256,0,0,8,0,16,64,0x0,0x7f31a7fccec0,199001895073536,199001895083363,199001895098883,199001895100126
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) [clone .kd] 2 0 0 325033 325033 1048576 256 0 0 8 0 16 64 0x0 0x7f31a7fccec0 199001894911168 199001894935363 199001894955843 199001894968617
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 325033 325033 1048576 256 0 0 8 0 16 64 0x0 0x7f31a7fccec0 199001894966613 199001895045923 199001895062403 199001895063647
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 325033 325033 1048576 256 0 0 8 0 16 64 0x0 0x7f31a7fccec0 199001895073536 199001895083363 199001895098883 199001895100126
@@ -1,2 +1,2 @@
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) ",2,0,0,2847318,2847318,1048576,256,0,0,8,8,16,64,0x0,0x7f6648898e80,47274,47274,16384,65536,13112,1663272,2187803528527851,2187803983015672,2187803983039992,2187803536033431
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,150756,150756,1048576,256,0,0,8,8,16,64,0x0,0x7f820df66e80,47744,47744,16384,65536,12856,1674844,194204807313230,194218184431477,194218184455957,194204815275476
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 2847318 150756 2847318 150756 1048576 256 0 0 8 8 16 64 0x0 0x7f6648898e80 0x7f820df66e80 47274 47744 47274 47744 16384 65536 13112 12856 1663272 1674844 2187803528527851 194204807313230 2187803983015672 194218184431477 2187803983039992 194218184455957 2187803536033431 194204815275476
@@ -1,2 +1,2 @@
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) ",2,0,0,2846769,2846769,1048576,256,0,0,8,8,16,64,0x0,0x7fe51c612e80,0,0,0,2187801917565820,2187803983015672,2187803983039992,2187801925224307
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,150941,150941,1048576,256,0,0,8,8,16,64,0x0,0x7fb5db332e80,0,0,0,194205315685723,194218184431477,194218184455957,194205323317172
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 2846769 150941 2846769 150941 1048576 256 0 0 8 8 16 64 0x0 0x7fe51c612e80 0x7fb5db332e80 0 0 0 2187801917565820 194205315685723 2187803983015672 194218184431477 2187803983039992 194218184455957 2187801925224307 194205323317172
@@ -1,2 +1,2 @@
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) ",2,0,0,2849331,2849331,1048576,256,0,0,8,8,16,64,0x0,0x7f6f424dce80,65536,205200,26259424,2187809164143107,2187803983015672,2187803983039992,2187809171645862
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,151125,151125,1048576,256,0,0,8,8,16,64,0x0,0x7f690a0c0e80,65536,205956,26258976,194205816966838,194218184431477,194218184455957,194205824797164
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 2849331 151125 2849331 151125 1048576 256 0 0 8 8 16 64 0x0 0x7f6f424dce80 0x7f690a0c0e80 65536 205200 205956 26259424 26258976 2187809164143107 194205816966838 2187803983015672 194218184431477 2187803983039992 194218184455957 2187809171645862 194205824797164
@@ -1,2 +1,2 @@
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) ",2,0,0,2849148,2849148,1048576,256,0,0,8,8,16,64,0x0,0x7f37e6006e80,32768,652733,83542268,2187808723799978,2187803983015672,2187803983039992,2187808731263349
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,151312,151312,1048576,256,0,0,8,8,16,64,0x0,0x7fa9adb0ce80,32768,667106,85389576,194206315490934,194218184431477,194218184455957,194206323400790
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 2849148 151312 2849148 151312 1048576 256 0 0 8 8 16 64 0x0 0x7f37e6006e80 0x7fa9adb0ce80 32768 652733 667106 83542268 85389576 2187808723799978 194206315490934 2187803983015672 194218184431477 2187803983039992 194218184455957 2187808731263349 194206323400790
@@ -1,2 +1,2 @@
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) ",2,0,0,2847684,2847684,1048576,256,0,0,8,8,16,64,0x0,0x7f54e0f84e80,47118,47118,17095,376952,16384,24302477,224867,0,97701064,2187804428513108,2187803983015672,2187803983039992,2187804436177596
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,151497,151497,1048576,256,0,0,8,8,16,64,0x0,0x7fd5b2e38e80,48008,48008,17263,384072,16384,24600233,232757,0,98897844,194207844573840,194218184431477,194218184455957,194207852970067
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 2847684 151497 2847684 151497 1048576 256 0 0 8 8 16 64 0x0 0x7f54e0f84e80 0x7fd5b2e38e80 47118 48008 47118 48008 17095 17263 376952 384072 16384 24302477 24600233 224867 232757 0 97701064 98897844 2187804428513108 194207844573840 2187803983015672 194218184431477 2187803983039992 194218184455957 2187804436177596 194207852970067
@@ -0,0 +1,2 @@
Dispatch_ID,Kernel_Name,GPU_ID
0,"vecCopy(double*, double*, double*, int, int) ",2
1 Dispatch_ID Kernel_Name GPU_ID
2 0 vecCopy(double*, double*, double*, int, int) 2
File diff suppressed because one or more lines are too long
+1 -1
View File
@@ -1,2 +1,2 @@
workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
dispatch_0,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:45:11 2024 (CST),1,t006-003.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,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1
dispatch_0,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:07:49 PM (CST),2,t008-007.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,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1
1 workload_name command ip_blocks timestamp version hostname cpu_model sbios linux_distro linux_kernel_version amd_gpu_kernel_version cpu_memory gpu_memory rocm_version vbios compute_partition memory_partition gpu_model gpu_arch gpu_l1 gpu_l2 cu_per_gpu simd_per_cu se_per_gpu wave_size workgroup_max_size max_waves_per_cu max_sclk max_mclk cur_sclk cur_mclk total_l2_chan lds_banks_per_cu sqc_per_gpu pipes_per_gpu hbm_bw num_xcd
2 dispatch_0 ./tests/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF Fri Mar 1 16:45:11 2024 (CST) Thu 07 Mar 2024 01:07:49 PM (CST) 1 2 t006-003.hpcfund t008-007.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 527651240 527651100 5.7.1-98 6.0.2-115 113-D3431401-100 NA NA MI100 gfx908 16 8192 120 4 8 64 1024 40 1502 1200 1502 1200 32 32 64 4 1228.8 1
@@ -1,2 +1,2 @@
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) [clone .kd]",2,0,0,2847501,2847501,1048576,256,0,0,8,8,16,64,0x0,0x7face032ee80,2187803982990937,2187803983015672,2187803983039992,2187803983054696
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,154895,154895,1048576,256,0,0,8,8,16,64,0x0,0x7f26e5422e80,194218184405603,194218184431477,194218184455957,194218184468662
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) [clone .kd] 2 0 0 2847501 154895 2847501 154895 1048576 256 0 0 8 8 16 64 0x0 0x7face032ee80 0x7f26e5422e80 2187803982990937 194218184405603 2187803983015672 194218184431477 2187803983039992 194218184455957 2187803983054696 194218184468662
@@ -0,0 +1,2 @@
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) ",2,0,0,306015,306015,1048576,256,0,0,8,0,16,64,0x0,0x7fd36d3a0ec0,27553,27553,16384,65536,14040,1568448,198487811862509,198500539781025,198500539801025,198487828148739
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 306015 306015 1048576 256 0 0 8 0 16 64 0x0 0x7fd36d3a0ec0 27553 27553 16384 65536 14040 1568448 198487811862509 198500539781025 198500539801025 198487828148739
@@ -0,0 +1,2 @@
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) ",2,0,0,306217,306217,1048576,256,0,0,8,0,16,64,0x0,0x7f1d6cb44ec0,0,0,0,198488296151539,198500539781025,198500539801025,198488312049765
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 306217 306217 1048576 256 0 0 8 0 16 64 0x0 0x7f1d6cb44ec0 0 0 0 198488296151539 198500539781025 198500539801025 198488312049765
@@ -0,0 +1,2 @@
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) ",2,0,0,306419,306419,1048576,256,0,0,8,0,16,64,0x0,0x7efbf7208ec0,65536,172952,19460368,198488779287609,198500539781025,198500539801025,198488795365134
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 306419 306419 1048576 256 0 0 8 0 16 64 0x0 0x7efbf7208ec0 65536 172952 19460368 198488779287609 198500539781025 198500539801025 198488795365134
@@ -0,0 +1,2 @@
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) ",2,0,0,306621,306621,1048576,256,0,0,8,0,16,64,0x0,0x7f5805234ec0,32768,291597,32660248,198489259151227,198500539781025,198500539801025,198489275062158
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 306621 306621 1048576 256 0 0 8 0 16 64 0x0 0x7f5805234ec0 32768 291597 32660248 198489259151227 198500539781025 198500539801025 198489275062158
@@ -0,0 +1,2 @@
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) ",2,0,0,306807,306807,1048576,256,0,0,8,0,16,64,0x0,0x7fe505304ec0,28097,28097,10788,224784,16384,11140767,132548,0,45073020,198489738658391,198500539781025,198500539801025,198489754777786
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 306807 306807 1048576 256 0 0 8 0 16 64 0x0 0x7fe505304ec0 28097 28097 10788 224784 16384 11140767 132548 0 45073020 198489738658391 198500539781025 198500539801025 198489754777786
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range: 0
kernel:

Some files were not shown because too many files have changed in this diff Show More