update workloads]

Signed-off-by: Jose Santos <josantos@amd.com>
Dieser Commit ist enthalten in:
Jose Santos
2024-03-07 15:19:48 -06:00
committet von Karl W. Schulz
Ursprung afea510551
Commit 35ef8c0707
1472 geänderte Dateien mit 5798 neuen und 630 gelöschten Zeilen
@@ -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) ",2,0,0,2829307,2829307,1048576,256,0,0,8,8,16,64,0x0,0x7f9162978e80,47896,47896,16384,65536,14144,1821868,2187750283384897,2187743821221227,2187743821245387,2187750291014289
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2829307,2829307,1048576,256,0,0,8,8,16,64,0x0,0x7f9162978e80,42919,42919,16384,65536,8247,1048596,2187750291036811,2187743821344427,2187743821363787,2187750291347865
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2829307,2829307,1048576,256,0,0,8,8,16,64,0x0,0x7f9162978e80,42863,42863,16384,65536,8142,1048592,2187750291380486,2187743821384907,2187743821403627,2187750291558360
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,130205,130205,1048576,256,0,0,8,8,16,64,0x0,0x7f1e188c0e80,49176,49176,16384,65536,12923,1629704,194140706168662,194153002188417,194153002212257,194140713966136
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,130205,130205,1048576,256,0,0,8,8,16,64,0x0,0x7f1e188c0e80,43143,43143,16384,65536,8155,1048584,194140713987878,194153002382497,194153002401697,194140714336267
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,130205,130205,1048576,256,0,0,8,8,16,64,0x0,0x7f1e188c0e80,43319,43319,16384,65536,8275,1048584,194140714368438,194153002423297,194153002442177,194140714551494
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 2829307 130205 2829307 130205 1048576 256 0 0 8 8 16 64 0x0 0x7f9162978e80 0x7f1e188c0e80 47896 49176 47896 49176 16384 65536 14144 12923 1821868 1629704 2187750283384897 194140706168662 2187743821221227 194153002188417 2187743821245387 194153002212257 2187750291014289 194140713966136
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2829307 130205 2829307 130205 1048576 256 0 0 8 8 16 64 0x0 0x7f9162978e80 0x7f1e188c0e80 42919 43143 42919 43143 16384 65536 8247 8155 1048596 1048584 2187750291036811 194140713987878 2187743821344427 194153002382497 2187743821363787 194153002401697 2187750291347865 194140714336267
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2829307 130205 2829307 130205 1048576 256 0 0 8 8 16 64 0x0 0x7f9162978e80 0x7f1e188c0e80 42863 43319 42863 43319 16384 65536 8142 8275 1048592 1048584 2187750291380486 194140714368438 2187743821384907 194153002423297 2187743821403627 194153002442177 2187750291558360 194140714551494
@@ -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) ",2,0,0,2830218,2830218,1048576,256,0,0,8,8,16,64,0x0,0x7f231d55ce80,0,0,0,2187752574623379,2187743821221227,2187743821245387,2187752582339824
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2830218,2830218,1048576,256,0,0,8,8,16,64,0x0,0x7f231d55ce80,0,0,0,2187752582357027,2187743821344427,2187743821363787,2187752582675765
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2830218,2830218,1048576,256,0,0,8,8,16,64,0x0,0x7f231d55ce80,0,0,0,2187752582704759,2187743821384907,2187743821403627,2187752582876261
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,130394,130394,1048576,256,0,0,8,8,16,64,0x0,0x7f47c7d0ee80,0,0,0,194141205843407,194153002188417,194153002212257,194141213761619
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,130394,130394,1048576,256,0,0,8,8,16,64,0x0,0x7f47c7d0ee80,0,0,0,194141213779673,194153002382497,194153002401697,194141214095882
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,130394,130394,1048576,256,0,0,8,8,16,64,0x0,0x7f47c7d0ee80,0,0,0,194141214124606,194153002423297,194153002442177,194141214303445
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 2830218 130394 2830218 130394 1048576 256 0 0 8 8 16 64 0x0 0x7f231d55ce80 0x7f47c7d0ee80 0 0 0 2187752574623379 194141205843407 2187743821221227 194153002188417 2187743821245387 194153002212257 2187752582339824 194141213761619
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2830218 130394 2830218 130394 1048576 256 0 0 8 8 16 64 0x0 0x7f231d55ce80 0x7f47c7d0ee80 0 0 0 2187752582357027 194141213779673 2187743821344427 194153002382497 2187743821363787 194153002401697 2187752582675765 194141214095882
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2830218 130394 2830218 130394 1048576 256 0 0 8 8 16 64 0x0 0x7f231d55ce80 0x7f47c7d0ee80 0 0 0 2187752582704759 194141214124606 2187743821384907 194153002423297 2187743821403627 194153002442177 2187752582876261 194141214303445
@@ -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) ",2,0,0,2828758,2828758,1048576,256,0,0,8,8,16,64,0x0,0x7f48097ece80,65536,196562,25083360,2187748678121644,2187743821221227,2187743821245387,2187748685806060
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2828758,2828758,1048576,256,0,0,8,8,16,64,0x0,0x7f48097ece80,65536,174780,22367608,2187748685826879,2187743821344427,2187743821363787,2187748686143153
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2828758,2828758,1048576,256,0,0,8,8,16,64,0x0,0x7f48097ece80,65536,178254,22772312,2187748686171375,2187743821384907,2187743821403627,2187748686348839
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,130583,130583,1048576,256,0,0,8,8,16,64,0x0,0x7ffa81e48e80,65536,207770,26636360,194141699115738,194153002188417,194153002212257,194141706852657
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,130583,130583,1048576,256,0,0,8,8,16,64,0x0,0x7ffa81e48e80,65536,172514,22100544,194141706871934,194153002382497,194153002401697,194141707163035
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,130583,130583,1048576,256,0,0,8,8,16,64,0x0,0x7ffa81e48e80,65536,173222,22213280,194141707191379,194153002423297,194153002442177,194141707358225
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 2828758 130583 2828758 130583 1048576 256 0 0 8 8 16 64 0x0 0x7f48097ece80 0x7ffa81e48e80 65536 196562 207770 25083360 26636360 2187748678121644 194141699115738 2187743821221227 194153002188417 2187743821245387 194153002212257 2187748685806060 194141706852657
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2828758 130583 2828758 130583 1048576 256 0 0 8 8 16 64 0x0 0x7f48097ece80 0x7ffa81e48e80 65536 174780 172514 22367608 22100544 2187748685826879 194141706871934 2187743821344427 194153002382497 2187743821363787 194153002401697 2187748686143153 194141707163035
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2828758 130583 2828758 130583 1048576 256 0 0 8 8 16 64 0x0 0x7f48097ece80 0x7ffa81e48e80 65536 178254 173222 22772312 22213280 2187748686171375 194141707191379 2187743821384907 194153002423297 2187743821403627 194153002442177 2187748686348839 194141707358225
@@ -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) ",2,0,0,2827300,2827300,1048576,256,0,0,8,8,16,64,0x0,0x7f1b549bae80,32768,666018,85250220,2187744271163280,2187743821221227,2187743821245387,2187744278877542
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2827300,2827300,1048576,256,0,0,8,8,16,64,0x0,0x7f1b549bae80,32768,716228,91669424,2187744278894895,2187743821344427,2187743821363787,2187744279239712
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2827300,2827300,1048576,256,0,0,8,8,16,64,0x0,0x7f1b549bae80,32768,658257,84241660,2187744279268115,2187743821384907,2187743821403627,2187744279417896
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,130770,130770,1048576,256,0,0,8,8,16,64,0x0,0x7f2b68738e80,32768,666828,85347504,194142193797318,194153002188417,194153002212257,194142201496365
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,130770,130770,1048576,256,0,0,8,8,16,64,0x0,0x7f2b68738e80,32768,685493,87733280,194142201516323,194153002382497,194153002401697,194142201816672
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,130770,130770,1048576,256,0,0,8,8,16,64,0x0,0x7f2b68738e80,32768,682699,87381264,194142201844274,194153002423297,194153002442177,194142202018574
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 2827300 130770 2827300 130770 1048576 256 0 0 8 8 16 64 0x0 0x7f1b549bae80 0x7f2b68738e80 32768 666018 666828 85250220 85347504 2187744271163280 194142193797318 2187743821221227 194153002188417 2187743821245387 194153002212257 2187744278877542 194142201496365
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2827300 130770 2827300 130770 1048576 256 0 0 8 8 16 64 0x0 0x7f1b549bae80 0x7f2b68738e80 32768 716228 685493 91669424 87733280 2187744278894895 194142201516323 2187743821344427 194153002382497 2187743821363787 194153002401697 2187744279239712 194142201816672
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2827300 130770 2827300 130770 1048576 256 0 0 8 8 16 64 0x0 0x7f1b549bae80 0x7f2b68738e80 32768 658257 682699 84241660 87381264 2187744279268115 194142201844274 2187743821384907 194153002423297 2187743821403627 194153002442177 2187744279417896 194142202018574
@@ -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) ",2,0,0,2829671,2829671,1048576,256,0,0,8,8,16,64,0x0,0x7fb9800e0e80,48011,48011,17431,384096,16384,24735031,234285,0,99446176,2187751196353507,2187743821221227,2187743821245387,2187751204008948
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2829671,2829671,1048576,256,0,0,8,8,16,64,0x0,0x7fb9800e0e80,43074,43074,14103,344600,16384,24405726,227357,0,98132920,2187751204037842,2187743821344427,2187743821363787,2187751204376889
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2829671,2829671,1048576,256,0,0,8,8,16,64,0x0,0x7fb9800e0e80,43538,43538,14836,348312,16384,24216655,230702,0,97375204,2187751204416002,2187743821384907,2187743821403627,2187751204603625
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,130957,130957,1048576,256,0,0,8,8,16,64,0x0,0x7f1fb6b00e80,48043,48043,16838,384352,16384,23962213,233085,0,96351644,194142688404657,194153002188417,194153002212257,194142696446684
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,130957,130957,1048576,256,0,0,8,8,16,64,0x0,0x7f1fb6b00e80,42690,42690,13932,341528,16384,24486089,227571,0,98428804,194142696476260,194153002382497,194153002401697,194142696816625
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,130957,130957,1048576,256,0,0,8,8,16,64,0x0,0x7f1fb6b00e80,42213,42213,14088,337712,16384,24121330,225136,0,96970788,194142696855067,194153002423297,194153002442177,194142697041180
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 2829671 130957 2829671 130957 1048576 256 0 0 8 8 16 64 0x0 0x7fb9800e0e80 0x7f1fb6b00e80 48011 48043 48011 48043 17431 16838 384096 384352 16384 24735031 23962213 234285 233085 0 99446176 96351644 2187751196353507 194142688404657 2187743821221227 194153002188417 2187743821245387 194153002212257 2187751204008948 194142696446684
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 2829671 130957 2829671 130957 1048576 256 0 0 8 8 16 64 0x0 0x7fb9800e0e80 0x7f1fb6b00e80 43074 42690 43074 42690 14103 13932 344600 341528 16384 24405726 24486089 227357 227571 0 98132920 98428804 2187751204037842 194142696476260 2187743821344427 194153002382497 2187743821363787 194153002401697 2187751204376889 194142696816625
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 2829671 130957 2829671 130957 1048576 256 0 0 8 8 16 64 0x0 0x7fb9800e0e80 0x7f1fb6b00e80 43538 42213 43538 42213 14836 14088 348312 337712 16384 24216655 24121330 230702 225136 0 97375204 96970788 2187751204416002 194142696855067 2187743821384907 194153002423297 2187743821403627 194153002442177 2187751204603625 194142697041180
@@ -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
Dateidiff unterdrückt, weil mindestens eine Zeile zu lang ist
+1 -1
Datei anzeigen
@@ -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
path,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:44:12 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
path,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:06:45 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 path ./tests/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF Fri Mar 1 16:44:12 2024 (CST) Thu 07 Mar 2024 01:06:45 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
+3 -3
Datei anzeigen
@@ -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]",2,0,0,2827118,2827118,1048576,256,0,0,8,8,16,64,0x0,0x7f6c9de8ee80,2187743821192147,2187743821221227,2187743821245387,2187743821258732
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2827118,2827118,1048576,256,0,0,8,8,16,64,0x0,0x7f6c9de8ee80,2187743821258602,2187743821344427,2187743821363787,2187743821365102
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2827118,2827118,1048576,256,0,0,8,8,16,64,0x0,0x7f6c9de8ee80,2187743821375982,2187743821384907,2187743821403627,2187743821405077
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,134351,134351,1048576,256,0,0,8,8,16,64,0x0,0x7f7e012a4e80,194153002162090,194153002188417,194153002212257,194153002225981
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,134351,134351,1048576,256,0,0,8,8,16,64,0x0,0x7f7e012a4e80,194153002224879,194153002382497,194153002401697,194153002402936
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,134351,134351,1048576,256,0,0,8,8,16,64,0x0,0x7f7e012a4e80,194153002414157,194153002423297,194153002442177,194153002443232
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 2827118 134351 2827118 134351 1048576 256 0 0 8 8 16 64 0x0 0x7f6c9de8ee80 0x7f7e012a4e80 2187743821192147 194153002162090 2187743821221227 194153002188417 2187743821245387 194153002212257 2187743821258732 194153002225981
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 2827118 134351 2827118 134351 1048576 256 0 0 8 8 16 64 0x0 0x7f6c9de8ee80 0x7f7e012a4e80 2187743821258602 194153002224879 2187743821344427 194153002382497 2187743821363787 194153002401697 2187743821365102 194153002402936
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 2827118 134351 2827118 134351 1048576 256 0 0 8 8 16 64 0x0 0x7f6c9de8ee80 0x7f7e012a4e80 2187743821375982 194153002414157 2187743821384907 194153002423297 2187743821403627 194153002442177 2187743821405077 194153002443232
@@ -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) ",2,0,0,282537,282537,1048576,256,0,0,8,0,16,64,0x0,0x7fe3cb2f4ec0,27474,27474,16384,65536,14001,1557960,198053593279677,198066321926096,198066321946896,198053609365457
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,282537,282537,1048576,256,0,0,8,0,16,64,0x0,0x7fe3cb2f4ec0,39998,39998,16384,65536,9140,1048648,198053609385856,198066321965776,198066321981616,198053609679742
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,282537,282537,1048576,256,0,0,8,0,16,64,0x0,0x7fe3cb2f4ec0,39794,39794,16384,65536,9293,1048652,198053609709659,198066322044816,198066322061136,198053609866545
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 282537 282537 1048576 256 0 0 8 0 16 64 0x0 0x7fe3cb2f4ec0 27474 27474 16384 65536 14001 1557960 198053593279677 198066321926096 198066321946896 198053609365457
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 282537 282537 1048576 256 0 0 8 0 16 64 0x0 0x7fe3cb2f4ec0 39998 39998 16384 65536 9140 1048648 198053609385856 198066321965776 198066321981616 198053609679742
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 282537 282537 1048576 256 0 0 8 0 16 64 0x0 0x7fe3cb2f4ec0 39794 39794 16384 65536 9293 1048652 198053609709659 198066322044816 198066322061136 198053609866545
@@ -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) ",2,0,0,282723,282723,1048576,256,0,0,8,0,16,64,0x0,0x7f0d7e5c0ec0,0,0,0,198054073410791,198066321926096,198066321946896,198054089119128
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,282723,282723,1048576,256,0,0,8,0,16,64,0x0,0x7f0d7e5c0ec0,0,0,0,198054089144676,198066321965776,198066321981616,198054089454743
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,282723,282723,1048576,256,0,0,8,0,16,64,0x0,0x7f0d7e5c0ec0,0,0,0,198054089482736,198066322044816,198066322061136,198054089647788
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 282723 282723 1048576 256 0 0 8 0 16 64 0x0 0x7f0d7e5c0ec0 0 0 0 198054073410791 198066321926096 198066321946896 198054089119128
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 282723 282723 1048576 256 0 0 8 0 16 64 0x0 0x7f0d7e5c0ec0 0 0 0 198054089144676 198066321965776 198066321981616 198054089454743
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 282723 282723 1048576 256 0 0 8 0 16 64 0x0 0x7f0d7e5c0ec0 0 0 0 198054089482736 198066322044816 198066322061136 198054089647788
@@ -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) ",2,0,0,282921,282921,1048576,256,0,0,8,0,16,64,0x0,0x7fa9cdc04ec0,65536,175020,19680912,198054547411278,198066321926096,198066321946896,198054563493783
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,282921,282921,1048576,256,0,0,8,0,16,64,0x0,0x7fa9cdc04ec0,65536,244314,27249496,198054563514422,198066321965776,198066321981616,198054563781747
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,282921,282921,1048576,256,0,0,8,0,16,64,0x0,0x7fa9cdc04ec0,65536,244834,27367848,198054563808789,198066322044816,198066322061136,198054563962109
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 282921 282921 1048576 256 0 0 8 0 16 64 0x0 0x7fa9cdc04ec0 65536 175020 19680912 198054547411278 198066321926096 198066321946896 198054563493783
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 282921 282921 1048576 256 0 0 8 0 16 64 0x0 0x7fa9cdc04ec0 65536 244314 27249496 198054563514422 198066321965776 198066321981616 198054563781747
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 282921 282921 1048576 256 0 0 8 0 16 64 0x0 0x7fa9cdc04ec0 65536 244834 27367848 198054563808789 198066322044816 198066322061136 198054563962109
@@ -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) ",2,0,0,283105,283105,1048576,256,0,0,8,0,16,64,0x0,0x7f68d7030ec0,32768,291935,32692868,198055031064325,198066321926096,198066321946896,198055046931984
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,283105,283105,1048576,256,0,0,8,0,16,64,0x0,0x7f68d7030ec0,32768,595936,66739628,198055046949266,198066321965776,198066321981616,198055047260485
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,283105,283105,1048576,256,0,0,8,0,16,64,0x0,0x7f68d7030ec0,32768,578290,64773016,198055047286755,198066322044816,198066322061136,198055047446537
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 283105 283105 1048576 256 0 0 8 0 16 64 0x0 0x7f68d7030ec0 32768 291935 32692868 198055031064325 198066321926096 198066321946896 198055046931984
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 283105 283105 1048576 256 0 0 8 0 16 64 0x0 0x7f68d7030ec0 32768 595936 66739628 198055046949266 198066321965776 198066321981616 198055047260485
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 283105 283105 1048576 256 0 0 8 0 16 64 0x0 0x7f68d7030ec0 32768 578290 64773016 198055047286755 198066322044816 198066322061136 198055047446537
@@ -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) ",2,0,0,283306,283306,1048576,256,0,0,8,0,16,64,0x0,0x7f054fe6cec0,28117,28117,11276,224944,16384,11085318,130224,0,44837220,198055510373355,198066321926096,198066321946896,198055526236264
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,283306,283306,1048576,256,0,0,8,0,16,64,0x0,0x7f054fe6cec0,41558,41558,14306,332472,16384,19035692,220378,0,76620008,198055526262163,198066321965776,198066321981616,198055526579233
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,283306,283306,1048576,256,0,0,8,0,16,64,0x0,0x7f054fe6cec0,41505,41505,14250,332048,16384,19350813,221811,0,77885816,198055526614049,198066322044816,198066322061136,198055526777638
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 283306 283306 1048576 256 0 0 8 0 16 64 0x0 0x7f054fe6cec0 28117 28117 11276 224944 16384 11085318 130224 0 44837220 198055510373355 198066321926096 198066321946896 198055526236264
3 1 vecCopy(double*, double*, double*, int, int) 2 0 2 283306 283306 1048576 256 0 0 8 0 16 64 0x0 0x7f054fe6cec0 41558 41558 14306 332472 16384 19035692 220378 0 76620008 198055526262163 198066321965776 198066321981616 198055526579233
4 2 vecCopy(double*, double*, double*, int, int) 2 0 4 283306 283306 1048576 256 0 0 8 0 16 64 0x0 0x7f054fe6cec0 41505 41505 14250 332048 16384 19350813 221811 0 77885816 198055526614049 198066322044816 198066322061136 198055526777638
@@ -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:
Dateidiff unterdrückt, weil mindestens eine Zeile zu lang ist
@@ -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
0,1388.7817,1388.1997,1389.3638,5016.855,5014.0708,5019.6392,9224.9346,9224.2139,9225.6553,18053.436,18052.646,18054.225,20938.699,20878.232,20999.166,20268.699,20268.057,20269.342,170460.84,170457.16,170464.53,164873.41,164867.12,164879.69,41422.461,41421.953,41422.969,41480.082,41479.18,41480.984,166350.34,165858.92,166841.77
1,1389.3734,1388.8273,1389.9196,5028.918,5026.8179,5031.0181,9235.2432,9234.6104,9235.876,18095.488,18092.15,18098.826,20976.51,20909.572,21043.447,20296.172,20295.555,20296.789,170853.42,170849.64,170857.2,165136.66,165132.58,165140.73,41487.176,41486.426,41487.926,41538.578,41537.527,41539.629,166883.66,166880.98,166886.33
2,1388.9829,1388.427,1389.5388,5036.1621,5033.7979,5038.5264,9260.1328,9259.2217,9261.0439,18102.061,18101.113,18103.008,21049.436,21049.027,21049.844,20356.162,20355.494,20356.83,171141.34,171137.19,171145.5,165517.05,165513.59,165520.5,41585.727,41584.75,41586.703,41645.672,41644.688,41646.656,166960.33,166359.64,167561.02
3,1389.2076,1388.5834,1389.8319,5031.7515,5030.3901,5033.1128,9241.3428,9240.71,9241.9756,18027.682,18024.373,18030.99,21037.742,21037.279,21038.205,20317.59,20317.133,20318.047,171067.7,171062.72,171072.69,165250.77,165246.25,165255.28,41443.941,41287.488,41600.395,41585.484,41584.891,41586.078,167028.16,167025.73,167030.58
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 1388.7817 1388.1997 1389.3638 5016.855 5014.0708 5019.6392 9224.9346 9224.2139 9225.6553 18053.436 18052.646 18054.225 20938.699 20878.232 20999.166 20268.699 20268.057 20269.342 170460.84 170457.16 170464.53 164873.41 164867.12 164879.69 41422.461 41421.953 41422.969 41480.082 41479.18 41480.984 166350.34 165858.92 166841.77
3 1 1389.3734 1388.8273 1389.9196 5028.918 5026.8179 5031.0181 9235.2432 9234.6104 9235.876 18095.488 18092.15 18098.826 20976.51 20909.572 21043.447 20296.172 20295.555 20296.789 170853.42 170849.64 170857.2 165136.66 165132.58 165140.73 41487.176 41486.426 41487.926 41538.578 41537.527 41539.629 166883.66 166880.98 166886.33
4 2 1388.9829 1388.427 1389.5388 5036.1621 5033.7979 5038.5264 9260.1328 9259.2217 9261.0439 18102.061 18101.113 18103.008 21049.436 21049.027 21049.844 20356.162 20355.494 20356.83 171141.34 171137.19 171145.5 165517.05 165513.59 165520.5 41585.727 41584.75 41586.703 41645.672 41644.688 41646.656 166960.33 166359.64 167561.02
5 3 1389.2076 1388.5834 1389.8319 5031.7515 5030.3901 5033.1128 9241.3428 9240.71 9241.9756 18027.682 18024.373 18030.99 21037.742 21037.279 21038.205 20317.59 20317.133 20318.047 171067.7 171062.72 171072.69 165250.77 165246.25 165255.28 41443.941 41287.488 41600.395 41585.484 41584.891 41586.078 167028.16 167025.73 167030.58
+2
Datei anzeigen
@@ -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
path,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:12:00 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 path ./sample/vcopy -n 1048576 -b 256 -i 3 SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline Thu 07 Mar 2024 02:12:00 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]",2,0,0,287126,287126,1048576,256,0,0,8,0,16,64,0x0,0x7f94deec4ec0,198066321901358,198066321926096,198066321946896,198066321960290
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,287126,287126,1048576,256,0,0,8,0,16,64,0x0,0x7f94deec4ec0,198066321957876,198066321965776,198066321981616,198066322042245
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,287126,287126,1048576,256,0,0,8,0,16,64,0x0,0x7f94deec4ec0,198066321992060,198066322044816,198066322061136,198066322062123
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 287126 287126 1048576 256 0 0 8 0 16 64 0x0 0x7f94deec4ec0 198066321901358 198066321926096 198066321946896 198066321960290
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 287126 287126 1048576 256 0 0 8 0 16 64 0x0 0x7f94deec4ec0 198066321957876 198066321965776 198066321981616 198066322042245
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 287126 287126 1048576 256 0 0 8 0 16 64 0x0 0x7f94deec4ec0 198066321992060 198066322044816 198066322061136 198066322062123