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) ",2,0,0,2836054,2836054,1048576,256,0,0,8,8,16,64,0x0,0x7f6ed7a82e80,48021,48021,16384,65536,12934,1687980,2187769696640836,2187770153039589,2187770153063749,2187769704195328
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2836054,2836054,1048576,256,0,0,8,8,16,64,0x0,0x7f6ed7a82e80,43919,43919,16384,65536,8143,1048580,2187769704219062,2187770153157189,2187770153176229,2187769704517543
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2836054,2836054,1048576,256,0,0,8,8,16,64,0x0,0x7f6ed7a82e80,42855,42855,16384,65536,8405,1048620,2187769704549483,2187770153197349,2187770153216709,2187769704705115
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,137526,137526,1048576,256,0,0,8,8,16,64,0x0,0x7ff7d60b8e80,48136,48136,16384,65536,12547,1608968,194163174117052,194175534630063,194175534654063,194163181897573
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,137526,137526,1048576,256,0,0,8,8,16,64,0x0,0x7ff7d60b8e80,43175,43175,16384,65536,8463,1048596,194163181922491,194175534674223,194175534693583,194163182207089
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,137526,137526,1048576,256,0,0,8,8,16,64,0x0,0x7ff7d60b8e80,44071,44071,16384,65536,8088,1048576,194163182239821,194175534779503,194175534798543,194163182401738
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 2836054 137526 2836054 137526 1048576 256 0 0 8 8 16 64 0x0 0x7f6ed7a82e80 0x7ff7d60b8e80 48021 48136 48021 48136 16384 65536 12934 12547 1687980 1608968 2187769696640836 194163174117052 2187770153039589 194175534630063 2187770153063749 194175534654063 2187769704195328 194163181897573
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2836054 137526 2836054 137526 1048576 256 0 0 8 8 16 64 0x0 0x7f6ed7a82e80 0x7ff7d60b8e80 43919 43175 43919 43175 16384 65536 8143 8463 1048580 1048596 2187769704219062 194163181922491 2187770153157189 194175534674223 2187770153176229 194175534693583 2187769704517543 194163182207089
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2836054 137526 2836054 137526 1048576 256 0 0 8 8 16 64 0x0 0x7f6ed7a82e80 0x7ff7d60b8e80 42855 44071 42855 44071 16384 65536 8405 8088 1048620 1048576 2187769704549483 194163182239821 2187770153197349 194175534779503 2187770153216709 194175534798543 2187769704705115 194163182401738
@@ -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) ",2,0,0,2836603,2836603,1048576,256,0,0,8,8,16,64,0x0,0x7f5948092e80,0,0,0,2187771300749952,2187770153039589,2187770153063749,2187771308278485
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2836603,2836603,1048576,256,0,0,8,8,16,64,0x0,0x7f5948092e80,0,0,0,2187771308299725,2187770153157189,2187770153176229,2187771308585822
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2836603,2836603,1048576,256,0,0,8,8,16,64,0x0,0x7f5948092e80,0,0,0,2187771308614426,2187770153197349,2187770153216709,2187771308783663
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,137714,137714,1048576,256,0,0,8,8,16,64,0x0,0x7f3cb4fe8e80,0,0,0,194163677587142,194175534630063,194175534654063,194163685530482
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,137714,137714,1048576,256,0,0,8,8,16,64,0x0,0x7f3cb4fe8e80,0,0,0,194163685548716,194175534674223,194175534693583,194163685853083
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,137714,137714,1048576,256,0,0,8,8,16,64,0x0,0x7f3cb4fe8e80,0,0,0,194163685881677,194175534779503,194175534798543,194163686052871
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 2836603 137714 2836603 137714 1048576 256 0 0 8 8 16 64 0x0 0x7f5948092e80 0x7f3cb4fe8e80 0 0 0 2187771300749952 194163677587142 2187770153039589 194175534630063 2187770153063749 194175534654063 2187771308278485 194163685530482
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2836603 137714 2836603 137714 1048576 256 0 0 8 8 16 64 0x0 0x7f5948092e80 0x7f3cb4fe8e80 0 0 0 2187771308299725 194163685548716 2187770153157189 194175534674223 2187770153176229 194175534693583 2187771308585822 194163685853083
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2836603 137714 2836603 137714 1048576 256 0 0 8 8 16 64 0x0 0x7f5948092e80 0x7f3cb4fe8e80 0 0 0 2187771308614426 194163685881677 2187770153197349 194175534779503 2187770153216709 194175534798543 2187771308783663 194163686052871
@@ -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) ",2,0,0,2835871,2835871,1048576,256,0,0,8,8,16,64,0x0,0x7f3df6fdce80,65536,201602,25951040,2187769240096984,2187770153039589,2187770153063749,2187769247791258
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2835871,2835871,1048576,256,0,0,8,8,16,64,0x0,0x7f3df6fdce80,65536,187442,24081592,2187769247811146,2187770153157189,2187770153176229,2187769248133701
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2835871,2835871,1048576,256,0,0,8,8,16,64,0x0,0x7f3df6fdce80,65536,177588,22725384,2187769248162956,2187770153197349,2187770153216709,2187769248335169
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,137904,137904,1048576,256,0,0,8,8,16,64,0x0,0x7f071b3dce80,65536,188508,24142904,194164172303568,194175534630063,194175534654063,194164179881035
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,137904,137904,1048576,256,0,0,8,8,16,64,0x0,0x7f071b3dce80,65536,169170,21619920,194164179900282,194175534674223,194175534693583,194164180246938
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,137904,137904,1048576,256,0,0,8,8,16,64,0x0,0x7f071b3dce80,65536,168242,21557048,194164180274780,194175534779503,194175534798543,194164180454190
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 2835871 137904 2835871 137904 1048576 256 0 0 8 8 16 64 0x0 0x7f3df6fdce80 0x7f071b3dce80 65536 201602 188508 25951040 24142904 2187769240096984 194164172303568 2187770153039589 194175534630063 2187770153063749 194175534654063 2187769247791258 194164179881035
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2835871 137904 2835871 137904 1048576 256 0 0 8 8 16 64 0x0 0x7f3df6fdce80 0x7f071b3dce80 65536 187442 169170 24081592 21619920 2187769247811146 194164179900282 2187770153157189 194175534674223 2187770153176229 194175534693583 2187769248133701 194164180246938
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2835871 137904 2835871 137904 1048576 256 0 0 8 8 16 64 0x0 0x7f3df6fdce80 0x7f071b3dce80 65536 177588 168242 22725384 21557048 2187769248162956 194164180274780 2187770153197349 194175534779503 2187770153216709 194175534798543 2187769248335169 194164180454190
@@ -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) ",2,0,0,2837335,2837335,1048576,256,0,0,8,8,16,64,0x0,0x7f505984ce80,32768,666558,85325644,2187773130816574,2187770153039589,2187770153063749,2187773138365636
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2837335,2837335,1048576,256,0,0,8,8,16,64,0x0,0x7f505984ce80,32768,667867,85503424,2187773138386926,2187770153157189,2187770153176229,2187773138681358
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2837335,2837335,1048576,256,0,0,8,8,16,64,0x0,0x7f505984ce80,32768,655830,83946444,2187773138709522,2187770153197349,2187770153216709,2187773138879962
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,138091,138091,1048576,256,0,0,8,8,16,64,0x0,0x7f290d802e80,32768,655161,83871140,194164678008099,194175534630063,194175534654063,194164686165985
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,138091,138091,1048576,256,0,0,8,8,16,64,0x0,0x7f290d802e80,32768,672735,86120852,194164686184760,194175534674223,194175534693583,194164686503344
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,138091,138091,1048576,256,0,0,8,8,16,64,0x0,0x7f290d802e80,32768,657649,84175780,194164686531978,194175534779503,194175534798543,194164686707520
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 2837335 138091 2837335 138091 1048576 256 0 0 8 8 16 64 0x0 0x7f505984ce80 0x7f290d802e80 32768 666558 655161 85325644 83871140 2187773130816574 194164678008099 2187770153039589 194175534630063 2187770153063749 194175534654063 2187773138365636 194164686165985
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2837335 138091 2837335 138091 1048576 256 0 0 8 8 16 64 0x0 0x7f505984ce80 0x7f290d802e80 32768 667867 672735 85503424 86120852 2187773138386926 194164686184760 2187770153157189 194175534674223 2187770153176229 194175534693583 2187773138681358 194164686503344
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2837335 138091 2837335 138091 1048576 256 0 0 8 8 16 64 0x0 0x7f505984ce80 0x7f290d802e80 32768 655830 657649 83946444 84175780 2187773138709522 194164686531978 2187770153197349 194175534779503 2187770153216709 194175534798543 2187773138879962 194164686707520
@@ -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) ",2,0,0,2837702,2837702,1048576,256,0,0,8,8,16,64,0x0,0x7fca353b2e80,48056,48056,17112,384456,16384,24538298,233738,0,98639592,2187774290395852,2187770153039589,2187770153063749,2187774297961515
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2837702,2837702,1048576,256,0,0,8,8,16,64,0x0,0x7fca353b2e80,42197,42197,13955,337584,16384,23746856,227641,0,95474444,2187774297971513,2187770153157189,2187770153176229,2187774298393586
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2837702,2837702,1048576,256,0,0,8,8,16,64,0x0,0x7fca353b2e80,43173,43173,14204,345392,16384,23959905,227347,0,96331984,2187774298432208,2187770153197349,2187770153216709,2187774298619610
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,138275,138275,1048576,256,0,0,8,8,16,64,0x0,0x7f5d7a4c8e80,47598,47598,16289,380792,16384,24789627,229303,0,99653036,194165181026564,194175534630063,194175534654063,194165189084451
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,138275,138275,1048576,256,0,0,8,8,16,64,0x0,0x7f5d7a4c8e80,42421,42421,14055,339376,16384,24679834,225411,0,99219160,194165189106292,194175534674223,194175534693583,194165189431618
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,138275,138275,1048576,256,0,0,8,8,16,64,0x0,0x7f5d7a4c8e80,41925,41925,13806,335408,16384,24141356,225187,0,97056972,194165189469360,194175534779503,194175534798543,194165189654570
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 2837702 138275 2837702 138275 1048576 256 0 0 8 8 16 64 0x0 0x7fca353b2e80 0x7f5d7a4c8e80 48056 47598 48056 47598 17112 16289 384456 380792 16384 24538298 24789627 233738 229303 0 98639592 99653036 2187774290395852 194165181026564 2187770153039589 194175534630063 2187770153063749 194175534654063 2187774297961515 194165189084451
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2837702 138275 2837702 138275 1048576 256 0 0 8 8 16 64 0x0 0x7fca353b2e80 0x7f5d7a4c8e80 42197 42421 42197 42421 13955 14055 337584 339376 16384 23746856 24679834 227641 225411 0 95474444 99219160 2187774297971513 194165189106292 2187770153157189 194175534674223 2187770153176229 194175534693583 2187774298393586 194165189431618
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2837702 138275 2837702 138275 1048576 256 0 0 8 8 16 64 0x0 0x7fca353b2e80 0x7f5d7a4c8e80 43173 41925 43173 41925 14204 13806 345392 335408 16384 23959905 24141356 227347 225187 0 96331984 97056972 2187774298432208 194165189469360 2187770153197349 194175534779503 2187770153216709 194175534798543 2187774298619610 194165189654570
@@ -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
kernel_substr,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:44:33 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
kernel_substr,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:07:08 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 kernel_substr ./tests/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF Fri Mar 1 16:44:33 2024 (CST) Thu 07 Mar 2024 01:07:08 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]",2,0,0,2836237,2836237,1048576,256,0,0,8,8,16,64,0x0,0x7f9c41858e80,2187770153013918,2187770153039589,2187770153063749,2187770153075112
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2836237,2836237,1048576,256,0,0,8,8,16,64,0x0,0x7f9c41858e80,2187770153076695,2187770153157189,2187770153176229,2187770153177465
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2836237,2836237,1048576,256,0,0,8,8,16,64,0x0,0x7f9c41858e80,2187770153189046,2187770153197349,2187770153216709,2187770153218061
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,141682,141682,1048576,256,0,0,8,8,16,64,0x0,0x7feb54db6e80,194175534602589,194175534630063,194175534654063,194175534670638
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,141682,141682,1048576,256,0,0,8,8,16,64,0x0,0x7feb54db6e80,194175534666220,194175534674223,194175534693583,194175534776909
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,141682,141682,1048576,256,0,0,8,8,16,64,0x0,0x7feb54db6e80,194175534704713,194175534779503,194175534798543,194175534799382
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 2836237 141682 2836237 141682 1048576 256 0 0 8 8 16 64 0x0 0x7f9c41858e80 0x7feb54db6e80 2187770153013918 194175534602589 2187770153039589 194175534630063 2187770153063749 194175534654063 2187770153075112 194175534670638
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 2836237 141682 2836237 141682 1048576 256 0 0 8 8 16 64 0x0 0x7f9c41858e80 0x7feb54db6e80 2187770153076695 194175534666220 2187770153157189 194175534674223 2187770153176229 194175534693583 2187770153177465 194175534776909
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 2836237 141682 2836237 141682 1048576 256 0 0 8 8 16 64 0x0 0x7f9c41858e80 0x7feb54db6e80 2187770153189046 194175534704713 2187770153197349 194175534779503 2187770153216709 194175534798543 2187770153218061 194175534799382
@@ -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) ",2,0,0,291276,291276,1048576,256,0,0,8,0,16,64,0x0,0x7f1828160ec0,27737,27737,16384,65536,13722,1525308,198261588061508,198274458325591,198274458345911,198261603806363
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,291276,291276,1048576,256,0,0,8,0,16,64,0x0,0x7f1828160ec0,41413,41413,16384,65536,9460,1048596,198261603830830,198274458365591,198274458381111,198261604082847
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,291276,291276,1048576,256,0,0,8,0,16,64,0x0,0x7f1828160ec0,40275,40275,16384,65536,9096,1048700,198261604112302,198274458443671,198274458459991,198261604256605
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 291276 291276 1048576 256 0 0 8 0 16 64 0x0 0x7f1828160ec0 27737 27737 16384 65536 13722 1525308 198261588061508 198274458325591 198274458345911 198261603806363
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 291276 291276 1048576 256 0 0 8 0 16 64 0x0 0x7f1828160ec0 41413 41413 16384 65536 9460 1048596 198261603830830 198274458365591 198274458381111 198261604082847
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 291276 291276 1048576 256 0 0 8 0 16 64 0x0 0x7f1828160ec0 40275 40275 16384 65536 9096 1048700 198261604112302 198274458443671 198274458459991 198261604256605
@@ -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) ",2,0,0,291478,291478,1048576,256,0,0,8,0,16,64,0x0,0x7f1f8e050ec0,0,0,0,198262073743594,198274458325591,198274458345911,198262089831408
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,291478,291478,1048576,256,0,0,8,0,16,64,0x0,0x7f1f8e050ec0,0,0,0,198262089848571,198274458365591,198274458381111,198262090150562
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,291478,291478,1048576,256,0,0,8,0,16,64,0x0,0x7f1f8e050ec0,0,0,0,198262090176932,198274458443671,198274458459991,198262090341423
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 291478 291478 1048576 256 0 0 8 0 16 64 0x0 0x7f1f8e050ec0 0 0 0 198262073743594 198274458325591 198274458345911 198262089831408
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 291478 291478 1048576 256 0 0 8 0 16 64 0x0 0x7f1f8e050ec0 0 0 0 198262089848571 198274458365591 198274458381111 198262090150562
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 291478 291478 1048576 256 0 0 8 0 16 64 0x0 0x7f1f8e050ec0 0 0 0 198262090176932 198274458443671 198274458459991 198262090341423
@@ -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) ",2,0,0,291685,291685,1048576,256,0,0,8,0,16,64,0x0,0x7fddd2fc4ec0,65536,187092,20917768,198262558091736,198274458325591,198274458345911,198262574290691
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,291685,291685,1048576,256,0,0,8,0,16,64,0x0,0x7fddd2fc4ec0,65536,245200,27582200,198262574309346,198274458365591,198274458381111,198262574602852
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,291685,291685,1048576,256,0,0,8,0,16,64,0x0,0x7fddd2fc4ec0,65536,263490,29654280,198262574629011,198274458443671,198274458459991,198262574756552
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 291685 291685 1048576 256 0 0 8 0 16 64 0x0 0x7fddd2fc4ec0 65536 187092 20917768 198262558091736 198274458325591 198274458345911 198262574290691
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 291685 291685 1048576 256 0 0 8 0 16 64 0x0 0x7fddd2fc4ec0 65536 245200 27582200 198262574309346 198274458365591 198274458381111 198262574602852
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 291685 291685 1048576 256 0 0 8 0 16 64 0x0 0x7fddd2fc4ec0 65536 263490 29654280 198262574629011 198274458443671 198274458459991 198262574756552
@@ -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) ",2,0,0,291870,291870,1048576,256,0,0,8,0,16,64,0x0,0x7f5a50b30ec0,32768,288882,32369320,198263038694323,198274458325591,198274458345911,198263054914017
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,291870,291870,1048576,256,0,0,8,0,16,64,0x0,0x7f5a50b30ec0,32768,596098,66767128,198263054932602,198274458365591,198274458381111,198263055228652
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,291870,291870,1048576,256,0,0,8,0,16,64,0x0,0x7f5a50b30ec0,32768,572975,64171428,198263055254551,198274458443671,198274458459991,198263055412490
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 291870 291870 1048576 256 0 0 8 0 16 64 0x0 0x7f5a50b30ec0 32768 288882 32369320 198263038694323 198274458325591 198274458345911 198263054914017
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 291870 291870 1048576 256 0 0 8 0 16 64 0x0 0x7f5a50b30ec0 32768 596098 66767128 198263054932602 198274458365591 198274458381111 198263055228652
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 291870 291870 1048576 256 0 0 8 0 16 64 0x0 0x7f5a50b30ec0 32768 572975 64171428 198263055254551 198274458443671 198274458459991 198263055412490
@@ -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) ",2,0,0,292068,292068,1048576,256,0,0,8,0,16,64,0x0,0x7f06a0314ec0,27371,27371,10912,218976,16384,10605927,126253,0,42923692,198263526253279,198274458325591,198274458345911,198263542014035
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,292068,292068,1048576,256,0,0,8,0,16,64,0x0,0x7f06a0314ec0,41749,41749,13458,334000,16384,19718416,225192,0,79338420,198263542042509,198274458365591,198274458381111,198263542340142
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,292068,292068,1048576,256,0,0,8,0,16,64,0x0,0x7f06a0314ec0,41423,41423,13486,331392,16384,19225946,220329,0,77380152,198263542374808,198274458443671,198274458459991,198263542550089
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 292068 292068 1048576 256 0 0 8 0 16 64 0x0 0x7f06a0314ec0 27371 27371 10912 218976 16384 10605927 126253 0 42923692 198263526253279 198274458325591 198274458345911 198263542014035
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 292068 292068 1048576 256 0 0 8 0 16 64 0x0 0x7f06a0314ec0 41749 41749 13458 334000 16384 19718416 225192 0 79338420 198263542042509 198274458365591 198274458381111 198263542340142
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 292068 292068 1048576 256 0 0 8 0 16 64 0x0 0x7f06a0314ec0 41423 41423 13486 331392 16384 19225946 220329 0 77380152 198263542374808 198274458443671 198274458459991 198263542550089
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -0,0 +1,5 @@
pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4
gpu:
range:
kernel: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -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: vecCopy
@@ -0,0 +1,5 @@
pmc:
gpu:
range:
kernel: vecCopy
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
0,1388.4747,1387.9553,1388.9941,5014.9604,5012.063,5017.8579,9222.5117,9221.9268,9223.0967,18050.73,18049.891,18051.57,20930.57,20869.91,20991.23,20265.133,20264.418,20265.848,170420.36,170416.08,170424.64,164859.31,164854.41,164864.22,41417.266,41416.672,41417.859,41477.48,41476.703,41478.258,166330.06,165840.5,166819.62
1,1389.7251,1389.1949,1390.2552,5028.3931,5026.2188,5030.5674,9234.2783,9233.5322,9235.0244,18087.188,18083.588,18090.787,20971.094,20904.305,21037.883,20291.975,20291.318,20292.631,170824.14,170818.92,170829.36,165082.02,165078.61,165085.42,41468.77,41467.949,41469.59,41525.664,41524.758,41526.57,166822.78,166819.69,166825.88
2,1388.7198,1388.2028,1389.2369,5036.1206,5033.917,5038.3242,9261.9297,9261.1611,9262.6982,18106.574,18105.59,18107.559,21049.045,21048.621,21049.469,20356.066,20355.422,20356.711,171138.38,171134.81,171141.94,165494.95,165491.14,165498.77,41581.402,41580.301,41582.504,41641.324,41640.227,41642.422,166971.16,166374.72,167567.59
3,1388.6997,1388.0704,1389.329,5030.8838,5029.3442,5032.4233,9239.749,9239.2314,9240.2666,18025.273,18022.016,18028.531,21030.592,21030.15,21031.033,20311.781,20311.162,20312.4,171031.81,171027.84,171035.78,165235.41,165231.41,165239.41,41440.09,41286.125,41594.055,41580.582,41580.031,41581.133,167008.56,167006.89,167010.23
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 1388.4747 1387.9553 1388.9941 5014.9604 5012.063 5017.8579 9222.5117 9221.9268 9223.0967 18050.73 18049.891 18051.57 20930.57 20869.91 20991.23 20265.133 20264.418 20265.848 170420.36 170416.08 170424.64 164859.31 164854.41 164864.22 41417.266 41416.672 41417.859 41477.48 41476.703 41478.258 166330.06 165840.5 166819.62
3 1 1389.7251 1389.1949 1390.2552 5028.3931 5026.2188 5030.5674 9234.2783 9233.5322 9235.0244 18087.188 18083.588 18090.787 20971.094 20904.305 21037.883 20291.975 20291.318 20292.631 170824.14 170818.92 170829.36 165082.02 165078.61 165085.42 41468.77 41467.949 41469.59 41525.664 41524.758 41526.57 166822.78 166819.69 166825.88
4 2 1388.7198 1388.2028 1389.2369 5036.1206 5033.917 5038.3242 9261.9297 9261.1611 9262.6982 18106.574 18105.59 18107.559 21049.045 21048.621 21049.469 20356.066 20355.422 20356.711 171138.38 171134.81 171141.94 165494.95 165491.14 165498.77 41581.402 41580.301 41582.504 41641.324 41640.227 41642.422 166971.16 166374.72 167567.59
5 3 1388.6997 1388.0704 1389.329 5030.8838 5029.3442 5032.4233 9239.749 9239.2314 9240.2666 18025.273 18022.016 18028.531 21030.592 21030.15 21031.033 20311.781 20311.162 20312.4 171031.81 171027.84 171035.78 165235.41 165231.41 165239.41 41440.09 41286.125 41594.055 41580.582 41580.031 41581.133 167008.56 167006.89 167010.23
@@ -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
kernel_substr,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:15:28 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 kernel_substr ./sample/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline Thu 07 Mar 2024 02:15:28 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]",2,0,0,295872,295872,1048576,256,0,0,8,0,16,64,0x0,0x7f38a4160ec0,198274458301241,198274458325591,198274458345911,198274458362076
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,295872,295872,1048576,256,0,0,8,0,16,64,0x0,0x7f38a4160ec0,198274458356796,198274458365591,198274458381111,198274458440294
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,295872,295872,1048576,256,0,0,8,0,16,64,0x0,0x7f38a4160ec0,198274458391411,198274458443671,198274458459991,198274458461033
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 295872 295872 1048576 256 0 0 8 0 16 64 0x0 0x7f38a4160ec0 198274458301241 198274458325591 198274458345911 198274458362076
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 295872 295872 1048576 256 0 0 8 0 16 64 0x0 0x7f38a4160ec0 198274458356796 198274458365591 198274458381111 198274458440294
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 295872 295872 1048576 256 0 0 8 0 16 64 0x0 0x7f38a4160ec0 198274458391411 198274458443671 198274458459991 198274458461033