Support MI 350 profiling (#632)
* Add MI 350 hardware information
* Refactor MI GPU YAML file and corresponding interface
* Add SoC file for gfx950 architecture
* Add analysis report configs for MI 350 containing existing metrics
* Add placeholder None valued metrics for previous architectures to make
baseline comparison work
* Enable testing on MI 350
* Analysis config metric changes
- SPI changes
- Update metric formula for default SPI pipe counter
- Use efficiently collected pipe wise SPI counters
- Add SPI Wave Occupancy
- Add Scheduler-Pipe Wave Utilization
- Update formula for VGPR Writes
- Add Scheduler-Pipe FIFO Full Rate
- CPC changes
- Add CPC SYNC FIFO Full Rate
- Add CPC CANE Stall Rate
- Add CPC ADC Utilization
- SQ changes
- Add VALU co-issue efficiency
- Add F6F4 datatype metrics
- Update formula for total FLOPs by adding F6F4 counters
- Add LDS STORE / LOAD / ATOMIC metrics
- Add LDS STORE / LOAD / ATOMIC bandwidth
- Add LDS FIFO and TA ADDR / CMD / DATA FIFO full rates
* Collect TCP_TCP_LATENCY_sum only for gfx950 (MI 350)
* Do not inject SQ_ACCUM_PREV_HIRES unnecesarily
* Do not hardcode memory and shader clock speeds
* Write num_hbm_channels to sysinfo.csv instead of hbm_bw while profiling
* Move generate sysinfo.csv to pre processing step of profiling
* Add warnings to use --specs-correction for missing sysinfo.csv values during analysis phase
* Update CHANGELOG
* Analysis phase warning to use --specs-correction when needed
[ROCm/rocprofiler-compute commit: f9aa7be97c]
This commit is contained in:
@@ -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
|
||||
no_roof,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:55:21 PM (CDT),2,t007-001.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,,527651008,,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
|
||||
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,num_hbm_channels
|
||||
path,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:52:12 PM (CDT),2,t007-001.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,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1,32
|
||||
|
||||
|
@@ -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
|
||||
no_roof,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 04:54:41 PM (CDT),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
|
||||
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,num_hbm_channels
|
||||
path,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:16:46 PM (CDT),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,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1,32
|
||||
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID
|
||||
0,"vecCopy(double*, double*, double*, int, int) (.kd)",11995
|
||||
1,"vecCopy(double*, double*, double*, int, int) (.kd)",11995
|
||||
2,"vecCopy(double*, double*, double*, int, int) (.kd)",11995
|
||||
|
@@ -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
|
||||
no_roof,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Wed 29 May 2024 01:42:47 PM (CDT),2,sh5-1w300-rg3-3,AMD Instinct MI300A Accelerator,"American Megatrends International, LLC.RMO1002DS",Ubuntu 22.04.2 LTS,5.18.2-mi300-build-140423-ubuntu-22.04+,,131174852,,6.1.2-110,N/A,SPX,NPS1,MI300A_A1,gfx942,32,24576,228,4,24,64,1024,32,2100,1300,2100,1300,96,32,120,4,5324.8,6
|
||||
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,num_hbm_channels
|
||||
vcopy,tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 30 May 2024 02:09:51 PM (CDT),2,sh5-1w300-rg3-3,AMD Instinct MI300A Accelerator,"American Megatrends International, LLC.RMO1002DS",Ubuntu 22.04.2 LTS,5.18.2-mi300-build-140423-ubuntu-22.04+,,131174852,,6.1.2-110,N/A,SPX,NPS1,MI300A_A1,gfx942,32,24576,228,4,24,64,1024,32,2100,1300,2100,1300,96,32,120,4,5324.8,6,96
|
||||
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID
|
||||
0,"vecCopy(double*, double*, double*, int, int) (.kd)",60633
|
||||
1,"vecCopy(double*, double*, double*, int, int) (.kd)",60633
|
||||
2,"vecCopy(double*, double*, double*, int, int) (.kd)",60633
|
||||
|
@@ -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
|
||||
no_roof,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Wed 29 May 2024 12:05:44 PM (CDT),2,splinter-126-wr-c6,AMD Ryzen 9 7950X 16-Core Processor,"American Megatrends International, LLC.VS2683299N.FD",Ubuntu 22.04.4 LTS,5.18.2-mi300-build-140423-ubuntu-22.04+,,114656528,,6.2.0-13611,113-MI3SRIOV-001,SPX,NPS1,MI300X_A1,gfx942,32,4096,304,4,32,64,1024,32,2100,1300,2100,1300,128,32,160,4,5324.8,8
|
||||
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,num_hbm_channels
|
||||
vcopy,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 30 May 2024 02:19:39 PM (CDT),2,splinter-126-wr-c6,AMD Ryzen 9 7950X 16-Core Processor,"American Megatrends International, LLC.VS2683299N.FD",Ubuntu 22.04.4 LTS,5.18.2-mi300-build-140423-ubuntu-22.04+,,114656528,,6.2.0-13611,113-MI3SRIOV-001,SPX,NPS1,MI300X_A1,gfx942,32,4096,304,4,32,64,1024,32,2100,1300,2100,1300,128,32,160,4,5324.8,8,128
|
||||
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,Kernel_ID,CPC_ME1_BUSY_FOR_PACKET_DECODE,CPC_SYNC_WRREQ_FIFO_BUSY,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_BUSY,GRBM_GUI_ACTIVE,SPI_CS0_WAVE,SPI_CS1_WAVE,SPI_CS2_WAVE,SPI_CS3_WAVE,SQC_DCACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQ_IFETCH_LEVEL,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_VMEM_WR_TA_DATA_FIFO_FULL,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_FLAT_WAVEFRONTS_sum,TCC_EA0_RDREQ[0],TCC_EA0_RDREQ[10],TCC_EA0_RDREQ[11],TCC_EA0_RDREQ[12],TCC_EA0_RDREQ[13],TCC_EA0_RDREQ[14],TCC_EA0_RDREQ[15],TCC_EA0_RDREQ[16],TCC_EA0_RDREQ[17],TCC_EA0_RDREQ[18],TCC_EA0_RDREQ[19],TCC_EA0_RDREQ[1],TCC_EA0_RDREQ[20],TCC_EA0_RDREQ[21],TCC_EA0_RDREQ[22],TCC_EA0_RDREQ[23],TCC_EA0_RDREQ[25],TCC_EA0_RDREQ[26],TCC_EA0_RDREQ[27],TCC_EA0_RDREQ[28],TCC_EA0_RDREQ[29],TCC_EA0_RDREQ[2],TCC_EA0_RDREQ[30],TCC_EA0_RDREQ[31],TCC_EA0_RDREQ[32],TCC_EA0_RDREQ[33],TCC_EA0_RDREQ[34],TCC_EA0_RDREQ[35],TCC_EA0_RDREQ[36],TCC_EA0_RDREQ[37],TCC_EA0_RDREQ[38],TCC_EA0_RDREQ[39],TCC_EA0_RDREQ[3],TCC_EA0_RDREQ[40],TCC_EA0_RDREQ[41],TCC_EA0_RDREQ[42],TCC_EA0_RDREQ[43],TCC_EA0_RDREQ[45],TCC_EA0_RDREQ[46],TCC_EA0_RDREQ[47],TCC_EA0_RDREQ[48],TCC_EA0_RDREQ[49],TCC_EA0_RDREQ[50],TCC_EA0_RDREQ[51],TCC_EA0_RDREQ[52],TCC_EA0_RDREQ[53],TCC_EA0_RDREQ[54],TCC_EA0_RDREQ[55],TCC_EA0_RDREQ[56],TCC_EA0_RDREQ[57],TCC_EA0_RDREQ[58],TCC_EA0_RDREQ[59],TCC_EA0_RDREQ[5],TCC_EA0_RDREQ[60],TCC_EA0_RDREQ[61],TCC_EA0_RDREQ[62],TCC_EA0_RDREQ[63],TCC_EA0_RDREQ[6],TCC_EA0_RDREQ[7],TCC_EA0_RDREQ[8],TCC_EA0_RDREQ[9],TCC_EA0_WRREQ_LEVEL[0],TCC_EA0_WRREQ_LEVEL[10],TCC_EA0_WRREQ_LEVEL[11],TCC_EA0_WRREQ_LEVEL[12],TCC_EA0_WRREQ_LEVEL[13],TCC_EA0_WRREQ_LEVEL[14],TCC_EA0_WRREQ_LEVEL[15],TCC_EA0_WRREQ_LEVEL[16],TCC_EA0_WRREQ_LEVEL[17],TCC_EA0_WRREQ_LEVEL[18],TCC_EA0_WRREQ_LEVEL[19],TCC_EA0_WRREQ_LEVEL[1],TCC_EA0_WRREQ_LEVEL[20],TCC_EA0_WRREQ_LEVEL[21],TCC_EA0_WRREQ_LEVEL[22],TCC_EA0_WRREQ_LEVEL[23],TCC_EA0_WRREQ_LEVEL[25],TCC_EA0_WRREQ_LEVEL[26],TCC_EA0_WRREQ_LEVEL[27],TCC_EA0_WRREQ_LEVEL[28],TCC_EA0_WRREQ_LEVEL[29],TCC_EA0_WRREQ_LEVEL[2],TCC_EA0_WRREQ_LEVEL[30],TCC_EA0_WRREQ_LEVEL[31],TCC_EA0_WRREQ_LEVEL[32],TCC_EA0_WRREQ_LEVEL[33],TCC_EA0_WRREQ_LEVEL[34],TCC_EA0_WRREQ_LEVEL[35],TCC_EA0_WRREQ_LEVEL[36],TCC_EA0_WRREQ_LEVEL[37],TCC_EA0_WRREQ_LEVEL[38],TCC_EA0_WRREQ_LEVEL[39],TCC_EA0_WRREQ_LEVEL[3],TCC_EA0_WRREQ_LEVEL[40],TCC_EA0_WRREQ_LEVEL[41],TCC_EA0_WRREQ_LEVEL[42],TCC_EA0_WRREQ_LEVEL[43],TCC_EA0_WRREQ_LEVEL[45],TCC_EA0_WRREQ_LEVEL[46],TCC_EA0_WRREQ_LEVEL[47],TCC_EA0_WRREQ_LEVEL[48],TCC_EA0_WRREQ_LEVEL[49],TCC_EA0_WRREQ_LEVEL[50],TCC_EA0_WRREQ_LEVEL[51],TCC_EA0_WRREQ_LEVEL[52],TCC_EA0_WRREQ_LEVEL[53],TCC_EA0_WRREQ_LEVEL[54],TCC_EA0_WRREQ_LEVEL[55],TCC_EA0_WRREQ_LEVEL[56],TCC_EA0_WRREQ_LEVEL[57],TCC_EA0_WRREQ_LEVEL[58],TCC_EA0_WRREQ_LEVEL[59],TCC_EA0_WRREQ_LEVEL[5],TCC_EA0_WRREQ_LEVEL[60],TCC_EA0_WRREQ_LEVEL[61],TCC_EA0_WRREQ_LEVEL[62],TCC_EA0_WRREQ_LEVEL[63],TCC_EA0_WRREQ_LEVEL[6],TCC_EA0_WRREQ_LEVEL[7],TCC_EA0_WRREQ_LEVEL[8],TCC_EA0_WRREQ_LEVEL[9],TCC_NC_REQ_sum,TCC_REQ[0],TCC_REQ[10],TCC_REQ[11],TCC_REQ[12],TCC_REQ[13],TCC_REQ[14],TCC_REQ[15],TCC_REQ[16],TCC_REQ[17],TCC_REQ[18],TCC_REQ[19],TCC_REQ[1],TCC_REQ[20],TCC_REQ[21],TCC_REQ[22],TCC_REQ[23],TCC_REQ[25],TCC_REQ[26],TCC_REQ[27],TCC_REQ[28],TCC_REQ[29],TCC_REQ[2],TCC_REQ[30],TCC_REQ[31],TCC_REQ[32],TCC_REQ[33],TCC_REQ[34],TCC_REQ[35],TCC_REQ[36],TCC_REQ[37],TCC_REQ[38],TCC_REQ[39],TCC_REQ[3],TCC_REQ[40],TCC_REQ[41],TCC_REQ[42],TCC_REQ[43],TCC_REQ[45],TCC_REQ[46],TCC_REQ[47],TCC_REQ[48],TCC_REQ[49],TCC_REQ[50],TCC_REQ[51],TCC_REQ[52],TCC_REQ[53],TCC_REQ[54],TCC_REQ[55],TCC_REQ[56],TCC_REQ[57],TCC_REQ[58],TCC_REQ[59],TCC_REQ[5],TCC_REQ[60],TCC_REQ[61],TCC_REQ[62],TCC_REQ[63],TCC_REQ[6],TCC_REQ[7],TCC_REQ[8],TCC_REQ[9],TCP_GATE_EN1_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_TOTAL_WRITE_sum,TD_ATOMIC_WAVEFRONT_sum,TD_TC_STALL_sum
|
||||
0,0,1,15737,15737,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248224501556303,1248224501579103,1,13,39762.0,8.0,3350.0,78383.0,78383.0,16384.0,0.0,0.0,0.0,63304.0,72.0,1358.0,19849.0,0.0,0.0,0.0,73772.0,32768.0,2048.0,1029.0,1024.0,1024.0,1025.0,1029.0,1024.0,2048.0,1024.0,1025.0,1029.0,1024.0,1024.0,1024.0,1025.0,1029.0,1024.0,1028.0,1024.0,1024.0,1032.0,1025.0,1029.0,1024.0,2048.0,1024.0,1032.0,1029.0,1024.0,1024.0,1025.0,1029.0,1029.0,1025.0,1029.0,1024.0,1024.0,1024.0,1028.0,1024.0,1024.0,1024.0,1024.0,1028.0,1024.0,1024.0,1032.0,1029.0,1025.0,1029.0,1024.0,1024.0,1024.0,1025.0,1029.0,1024.0,1024.0,1024.0,1024.0,1028.0,1032.0,299809.0,150330.0,152966.0,140377.0,141618.0,143102.0,153709.0,289555.0,136667.0,135044.0,132763.0,136304.0,146473.0,146928.0,141940.0,138800.0,153648.0,153921.0,153401.0,142275.0,158958.0,137764.0,154480.0,160030.0,287362.0,150932.0,153809.0,136102.0,148758.0,146780.0,137156.0,142600.0,132260.0,153858.0,148372.0,158797.0,150948.0,156084.0,155637.0,155676.0,134811.0,154657.0,151789.0,152058.0,156935.0,147692.0,137836.0,152194.0,155650.0,149350.0,159350.0,155714.0,151894.0,143590.0,140617.0,158498.0,151931.0,149816.0,134354.0,152344.0,153376.0,0.0,6144.0,3145.0,3072.0,3072.0,3073.0,3145.0,3072.0,6144.0,3072.0,3073.0,3145.0,3072.0,3072.0,3072.0,3090.0,3145.0,3072.0,3144.0,3072.0,3072.0,3114.0,3090.0,3145.0,3072.0,6144.0,3072.0,3114.0,3145.0,3072.0,3072.0,3073.0,3145.0,3145.0,3090.0,3145.0,3072.0,3072.0,3072.0,3144.0,3072.0,3072.0,3072.0,3072.0,3144.0,3072.0,3072.0,3114.0,3145.0,3073.0,3145.0,3072.0,3072.0,3072.0,3090.0,3145.0,3072.0,3072.0,3072.0,3072.0,3144.0,3114.0,1418304.0,0.0,0.0,1048576.0,0.0,571910.0
|
||||
1,0,1,15737,15737,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248224502357113,1248224502373752,2,13,35094.0,8.0,3391.0,64716.0,64716.0,16384.0,0.0,0.0,0.0,63304.0,72.0,996.0,17914.0,0.0,0.0,0.0,0.0,32768.0,2048.0,1028.0,1024.0,1025.0,1026.0,1028.0,1024.0,2049.0,1024.0,1026.0,1028.0,1024.0,1024.0,1024.0,1024.0,1028.0,1024.0,1028.0,1024.0,1024.0,1026.0,1024.0,1028.0,1024.0,2048.0,1025.0,1026.0,1028.0,1024.0,1024.0,1026.0,1028.0,1028.0,1024.0,1028.0,1024.0,1024.0,1024.0,1028.0,1024.0,1024.0,1024.0,1024.0,1028.0,1024.0,1025.0,1026.0,1028.0,1026.0,1028.0,1024.0,1024.0,1024.0,1024.0,1028.0,1024.0,1024.0,1024.0,1024.0,1028.0,1026.0,307368.0,162005.0,160446.0,151060.0,153141.0,157304.0,151470.0,305183.0,146408.0,156888.0,152592.0,146297.0,143934.0,145080.0,157918.0,159116.0,146547.0,154796.0,157202.0,148817.0,159205.0,153646.0,161241.0,155953.0,316781.0,151490.0,159946.0,158706.0,146499.0,145428.0,160731.0,157547.0,151609.0,154421.0,158188.0,161612.0,161330.0,158057.0,162267.0,154697.0,156653.0,151979.0,161987.0,154131.0,157525.0,139803.0,153051.0,159171.0,150842.0,160845.0,161000.0,157519.0,152887.0,158287.0,158280.0,149117.0,164042.0,142572.0,153599.0,158627.0,147290.0,0.0,6144.0,3144.0,3072.0,3073.0,3091.0,3144.0,3072.0,6145.0,3072.0,3091.0,3144.0,3072.0,3072.0,3072.0,3072.0,3144.0,3072.0,3144.0,3072.0,3072.0,3108.0,3072.0,3144.0,3072.0,6144.0,3073.0,3108.0,3144.0,3072.0,3072.0,3091.0,3144.0,3144.0,3072.0,3144.0,3072.0,3072.0,3072.0,3144.0,3072.0,3072.0,3072.0,3072.0,3144.0,3072.0,3073.0,3108.0,3144.0,3091.0,3144.0,3072.0,3072.0,3072.0,3072.0,3144.0,3072.0,3072.0,3072.0,3072.0,3144.0,3108.0,1062800.0,0.0,0.0,1048576.0,0.0,347780.0
|
||||
2,0,1,15737,15737,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248224503046887,1248224503063847,3,13,35834.0,8.0,376.0,62877.0,62877.0,16384.0,0.0,0.0,0.0,63304.0,72.0,1039.0,18047.0,0.0,0.0,0.0,0.0,32768.0,2048.0,1028.0,1024.0,1024.0,1024.0,1028.0,1024.0,2048.0,1024.0,1024.0,1028.0,1024.0,1024.0,1024.0,1024.0,1028.0,1025.0,1028.0,1024.0,1024.0,1026.0,1024.0,1028.0,1024.0,2048.0,1024.0,1026.0,1028.0,1024.0,1024.0,1024.0,1028.0,1028.0,1024.0,1028.0,1024.0,1024.0,1025.0,1028.0,1024.0,1024.0,1024.0,1025.0,1028.0,1024.0,1024.0,1026.0,1028.0,1024.0,1028.0,1024.0,1024.0,1024.0,1024.0,1028.0,1024.0,1024.0,1024.0,1025.0,1028.0,1026.0,297690.0,151572.0,166245.0,153966.0,152335.0,145177.0,155284.0,305526.0,157035.0,150029.0,149885.0,155828.0,160141.0,154195.0,151522.0,154137.0,145865.0,151468.0,159289.0,156374.0,151317.0,155030.0,151653.0,156309.0,306747.0,153464.0,147495.0,145937.0,158635.0,156119.0,151800.0,147953.0,147121.0,150499.0,157270.0,159094.0,162440.0,154810.0,149439.0,150285.0,151413.0,156221.0,151239.0,147915.0,162813.0,149282.0,153992.0,156456.0,151068.0,159130.0,163566.0,164073.0,155062.0,156829.0,142277.0,152961.0,146665.0,148927.0,154406.0,155546.0,152788.0,0.0,6144.0,3144.0,3072.0,3072.0,3072.0,3144.0,3072.0,6144.0,3072.0,3072.0,3144.0,3072.0,3072.0,3072.0,3072.0,3144.0,3090.0,3144.0,3072.0,3072.0,3108.0,3072.0,3144.0,3072.0,6144.0,3072.0,3108.0,3144.0,3072.0,3072.0,3072.0,3144.0,3144.0,3072.0,3144.0,3072.0,3072.0,3090.0,3144.0,3072.0,3072.0,3072.0,3090.0,3144.0,3072.0,3072.0,3108.0,3144.0,3072.0,3144.0,3072.0,3072.0,3072.0,3072.0,3144.0,3072.0,3072.0,3072.0,3090.0,3144.0,3108.0,1074680.0,0.0,0.0,1048576.0,0.0,343195.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,Kernel_ID,CPC_CPC_TCIU_BUSY,CPC_ME1_DC0_SPI_BUSY,SPI_RA_REQ_NO_ALLOC_CSN,SPI_VWC0_VDATA_VALID_WR,SQC_DCACHE_ATOMIC,SQC_DCACHE_MISSES,SQC_ICACHE_REQ,SQC_TC_STALL,SQ_INSTS_VALU_MUL_F16,SQ_INST_LEVEL_LDS,SQ_WAVES_SAVED,TA_BUFFER_WRITE_WAVEFRONTS_sum,TA_TA_BUSY_sum,TCC_ATOMIC_sum,TCC_EA0_ATOMIC_LEVEL_sum,TCC_EA0_WRREQ_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_UTCL1_REQUEST_sum
|
||||
0,0,1,15744,15744,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248225042558134,1248225042580173,1,13,628.0,28511.0,18570.0,32768.0,0.0,72.0,65536.0,0.0,0.0,0.0,0.0,0.0,730768.0,0.0,0.0,131072.0,0.0,0.0,0.0,128.0,524288.0
|
||||
1,0,1,15744,15744,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248225043214988,1248225043231667,2,13,628.0,21899.0,17097.0,32768.0,0.0,72.0,65536.0,0.0,0.0,0.0,0.0,0.0,587815.0,0.0,0.0,131072.0,0.0,0.0,0.0,128.0,524288.0
|
||||
2,0,1,15744,15744,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248225043788046,1248225043804766,3,13,628.0,21865.0,17000.0,32768.0,0.0,72.0,65536.0,0.0,0.0,0.0,0.0,0.0,587705.0,0.0,0.0,131072.0,0.0,0.0,0.0,128.0,524288.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,Kernel_ID,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_IDLE,CPF_CPF_STAT_STALL,SPI_CSQ_P0_OCCUPANCY,SPI_CSQ_P1_OCCUPANCY,SPI_CSQ_P2_OCCUPANCY,SPI_CSQ_P3_OCCUPANCY,SPI_RA_SGPR_SIMD_FULL_CSN,SQC_DCACHE_REQ_READ_16,SQ_BUSY_CU_CYCLES,SQ_INSTS_LDS_LOAD,SQ_INSTS_LDS_STORE,SQ_INSTS_VALU_MUL_F64,SQ_INST_LEVEL_SMEM,SQ_LDS_CMD_FIFO_FULL,TA_BUFFER_TOTAL_CYCLES_sum,TA_FLAT_READ_WAVEFRONTS_sum,TCC_ATOMIC[0],TCC_ATOMIC[10],TCC_ATOMIC[11],TCC_ATOMIC[12],TCC_ATOMIC[13],TCC_ATOMIC[15],TCC_ATOMIC[16],TCC_ATOMIC[17],TCC_ATOMIC[18],TCC_ATOMIC[19],TCC_ATOMIC[1],TCC_ATOMIC[21],TCC_ATOMIC[22],TCC_ATOMIC[23],TCC_ATOMIC[24],TCC_ATOMIC[26],TCC_ATOMIC[27],TCC_ATOMIC[28],TCC_ATOMIC[29],TCC_ATOMIC[2],TCC_ATOMIC[31],TCC_ATOMIC[32],TCC_ATOMIC[33],TCC_ATOMIC[34],TCC_ATOMIC[35],TCC_ATOMIC[37],TCC_ATOMIC[38],TCC_ATOMIC[39],TCC_ATOMIC[3],TCC_ATOMIC[40],TCC_ATOMIC[42],TCC_ATOMIC[43],TCC_ATOMIC[44],TCC_ATOMIC[45],TCC_ATOMIC[47],TCC_ATOMIC[48],TCC_ATOMIC[49],TCC_ATOMIC[50],TCC_ATOMIC[51],TCC_ATOMIC[53],TCC_ATOMIC[54],TCC_ATOMIC[55],TCC_ATOMIC[56],TCC_ATOMIC[58],TCC_ATOMIC[59],TCC_ATOMIC[5],TCC_ATOMIC[60],TCC_ATOMIC[61],TCC_ATOMIC[63],TCC_ATOMIC[6],TCC_ATOMIC[7],TCC_ATOMIC[8],TCC_BUBBLE[0],TCC_BUBBLE[10],TCC_BUBBLE[11],TCC_BUBBLE[12],TCC_BUBBLE[13],TCC_BUBBLE[15],TCC_BUBBLE[16],TCC_BUBBLE[17],TCC_BUBBLE[18],TCC_BUBBLE[19],TCC_BUBBLE[1],TCC_BUBBLE[21],TCC_BUBBLE[22],TCC_BUBBLE[23],TCC_BUBBLE[24],TCC_BUBBLE[26],TCC_BUBBLE[27],TCC_BUBBLE[28],TCC_BUBBLE[29],TCC_BUBBLE[2],TCC_BUBBLE[31],TCC_BUBBLE[32],TCC_BUBBLE[33],TCC_BUBBLE[34],TCC_BUBBLE[35],TCC_BUBBLE[37],TCC_BUBBLE[38],TCC_BUBBLE[39],TCC_BUBBLE[3],TCC_BUBBLE[40],TCC_BUBBLE[42],TCC_BUBBLE[43],TCC_BUBBLE[44],TCC_BUBBLE[45],TCC_BUBBLE[47],TCC_BUBBLE[48],TCC_BUBBLE[49],TCC_BUBBLE[50],TCC_BUBBLE[51],TCC_BUBBLE[53],TCC_BUBBLE[54],TCC_BUBBLE[55],TCC_BUBBLE[56],TCC_BUBBLE[58],TCC_BUBBLE[59],TCC_BUBBLE[5],TCC_BUBBLE[60],TCC_BUBBLE[61],TCC_BUBBLE[63],TCC_BUBBLE[6],TCC_BUBBLE[7],TCC_BUBBLE[8],TCC_EA0_ATOMIC[0],TCC_EA0_ATOMIC[10],TCC_EA0_ATOMIC[11],TCC_EA0_ATOMIC[12],TCC_EA0_ATOMIC[13],TCC_EA0_ATOMIC[15],TCC_EA0_ATOMIC[16],TCC_EA0_ATOMIC[17],TCC_EA0_ATOMIC[18],TCC_EA0_ATOMIC[19],TCC_EA0_ATOMIC[1],TCC_EA0_ATOMIC[21],TCC_EA0_ATOMIC[22],TCC_EA0_ATOMIC[23],TCC_EA0_ATOMIC[24],TCC_EA0_ATOMIC[26],TCC_EA0_ATOMIC[27],TCC_EA0_ATOMIC[28],TCC_EA0_ATOMIC[29],TCC_EA0_ATOMIC[2],TCC_EA0_ATOMIC[31],TCC_EA0_ATOMIC[32],TCC_EA0_ATOMIC[33],TCC_EA0_ATOMIC[34],TCC_EA0_ATOMIC[35],TCC_EA0_ATOMIC[37],TCC_EA0_ATOMIC[38],TCC_EA0_ATOMIC[39],TCC_EA0_ATOMIC[3],TCC_EA0_ATOMIC[40],TCC_EA0_ATOMIC[42],TCC_EA0_ATOMIC[43],TCC_EA0_ATOMIC[44],TCC_EA0_ATOMIC[45],TCC_EA0_ATOMIC[47],TCC_EA0_ATOMIC[48],TCC_EA0_ATOMIC[49],TCC_EA0_ATOMIC[50],TCC_EA0_ATOMIC[51],TCC_EA0_ATOMIC[53],TCC_EA0_ATOMIC[54],TCC_EA0_ATOMIC[55],TCC_EA0_ATOMIC[56],TCC_EA0_ATOMIC[58],TCC_EA0_ATOMIC[59],TCC_EA0_ATOMIC[5],TCC_EA0_ATOMIC[60],TCC_EA0_ATOMIC[61],TCC_EA0_ATOMIC[63],TCC_EA0_ATOMIC[6],TCC_EA0_ATOMIC[7],TCC_EA0_ATOMIC[8],TCC_HIT[0],TCC_HIT[10],TCC_HIT[11],TCC_HIT[12],TCC_HIT[13],TCC_HIT[15],TCC_HIT[16],TCC_HIT[17],TCC_HIT[18],TCC_HIT[19],TCC_HIT[1],TCC_HIT[21],TCC_HIT[22],TCC_HIT[23],TCC_HIT[24],TCC_HIT[26],TCC_HIT[27],TCC_HIT[28],TCC_HIT[29],TCC_HIT[2],TCC_HIT[31],TCC_HIT[32],TCC_HIT[33],TCC_HIT[34],TCC_HIT[35],TCC_HIT[37],TCC_HIT[38],TCC_HIT[39],TCC_HIT[3],TCC_HIT[40],TCC_HIT[42],TCC_HIT[43],TCC_HIT[44],TCC_HIT[45],TCC_HIT[47],TCC_HIT[48],TCC_HIT[49],TCC_HIT[50],TCC_HIT[51],TCC_HIT[53],TCC_HIT[54],TCC_HIT[55],TCC_HIT[56],TCC_HIT[58],TCC_HIT[59],TCC_HIT[5],TCC_HIT[60],TCC_HIT[61],TCC_HIT[63],TCC_HIT[6],TCC_HIT[7],TCC_HIT[8],TCP_TA_TCP_STATE_READ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TD_LOAD_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum
|
||||
0,0,1,15751,15751,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248225586306035,1248225586327794,1,13,77276.0,0.0,0.0,3438.0,26015654.0,0.0,0.0,0.0,0.0,0.0,1005075.0,0.0,0.0,0.0,170074.0,0.0,0.0,16384.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2135.0,1024.0,1041.0,1094.0,1024.0,1024.0,2118.0,2118.0,2048.0,1024.0,2118.0,1094.0,1024.0,1024.0,1024.0,1024.0,1024.0,1094.0,1024.0,2048.0,1024.0,2118.0,2118.0,2048.0,1024.0,1094.0,1024.0,1024.0,1041.0,1024.0,1024.0,1024.0,1094.0,1024.0,1024.0,2118.0,2153.0,2083.0,1024.0,1094.0,1059.0,1024.0,1024.0,1024.0,1024.0,1094.0,1094.0,1059.0,1024.0,1024.0,1024.0,1041.0,32768.0,0.0,0.0,493416.0,32768.0,16384.0
|
||||
1,0,1,15751,15751,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248225587128604,1248225587145724,2,13,66157.0,0.0,0.0,3477.0,18725576.0,0.0,0.0,0.0,0.0,0.0,751413.0,0.0,0.0,0.0,109530.0,0.0,0.0,16384.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2118.0,1024.0,1024.0,1094.0,1024.0,1024.0,2135.0,2118.0,2048.0,1041.0,2118.0,1094.0,1024.0,1024.0,1041.0,1024.0,1041.0,1094.0,1024.0,2048.0,1024.0,2118.0,2118.0,2048.0,1024.0,1094.0,1024.0,1024.0,1024.0,1024.0,1024.0,1024.0,1094.0,1024.0,1024.0,2118.0,2153.0,2083.0,1024.0,1094.0,1059.0,1024.0,1024.0,1024.0,1024.0,1094.0,1094.0,1059.0,1024.0,1024.0,1024.0,1024.0,32768.0,0.0,0.0,524288.0,32768.0,16384.0
|
||||
2,0,1,15751,15751,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248225587833139,1248225587849859,3,13,62396.0,0.0,0.0,376.0,18327092.0,0.0,0.0,0.0,0.0,0.0,740907.0,0.0,0.0,0.0,108626.0,0.0,0.0,16384.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2118.0,1024.0,1024.0,1094.0,1024.0,1024.0,2118.0,2118.0,2048.0,1024.0,2118.0,1094.0,1024.0,1024.0,1024.0,1024.0,1024.0,1094.0,1024.0,2048.0,1024.0,2118.0,2118.0,2048.0,1024.0,1094.0,1024.0,1024.0,1024.0,1024.0,1024.0,1024.0,1094.0,1024.0,1024.0,2135.0,2153.0,2083.0,1041.0,1094.0,1059.0,1024.0,1041.0,1024.0,1041.0,1094.0,1094.0,1059.0,1024.0,1024.0,1024.0,1024.0,32768.0,0.0,0.0,524288.0,32768.0,16384.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,Kernel_ID,CPC_CANE_STALL,CPC_CPC_STAT_STALL,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,GRBM_COUNT,GRBM_SPI_BUSY,SPI_CS0_CRAWLER_STALL,SPI_CS1_CRAWLER_STALL,SPI_CS2_CRAWLER_STALL,SPI_CS3_CRAWLER_STALL,SQ_ACTIVE_INST_VMEM,SQ_INSTS_GDS,SQ_INSTS_LDS_ATOMIC,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VSKIPPED,SQ_INST_LEVEL_VMEM,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TCC_EA0_WRREQ[0],TCC_EA0_WRREQ[10],TCC_EA0_WRREQ[11],TCC_EA0_WRREQ[12],TCC_EA0_WRREQ[14],TCC_EA0_WRREQ[15],TCC_EA0_WRREQ[16],TCC_EA0_WRREQ[17],TCC_EA0_WRREQ[18],TCC_EA0_WRREQ[19],TCC_EA0_WRREQ[1],TCC_EA0_WRREQ[21],TCC_EA0_WRREQ[22],TCC_EA0_WRREQ[23],TCC_EA0_WRREQ[24],TCC_EA0_WRREQ[25],TCC_EA0_WRREQ[26],TCC_EA0_WRREQ[27],TCC_EA0_WRREQ[28],TCC_EA0_WRREQ[2],TCC_EA0_WRREQ[30],TCC_EA0_WRREQ[31],TCC_EA0_WRREQ[32],TCC_EA0_WRREQ[33],TCC_EA0_WRREQ[34],TCC_EA0_WRREQ[35],TCC_EA0_WRREQ[36],TCC_EA0_WRREQ[37],TCC_EA0_WRREQ[38],TCC_EA0_WRREQ[39],TCC_EA0_WRREQ[3],TCC_EA0_WRREQ[41],TCC_EA0_WRREQ[42],TCC_EA0_WRREQ[43],TCC_EA0_WRREQ[44],TCC_EA0_WRREQ[45],TCC_EA0_WRREQ[46],TCC_EA0_WRREQ[47],TCC_EA0_WRREQ[48],TCC_EA0_WRREQ[49],TCC_EA0_WRREQ[50],TCC_EA0_WRREQ[51],TCC_EA0_WRREQ[52],TCC_EA0_WRREQ[53],TCC_EA0_WRREQ[54],TCC_EA0_WRREQ[55],TCC_EA0_WRREQ[57],TCC_EA0_WRREQ[58],TCC_EA0_WRREQ[59],TCC_EA0_WRREQ[5],TCC_EA0_WRREQ[60],TCC_EA0_WRREQ[61],TCC_EA0_WRREQ[62],TCC_EA0_WRREQ[63],TCC_EA0_WRREQ[6],TCC_EA0_WRREQ[7],TCC_EA0_WRREQ[8],TCC_EA0_WRREQ[9],TCC_MISS[0],TCC_MISS[10],TCC_MISS[11],TCC_MISS[12],TCC_MISS[14],TCC_MISS[15],TCC_MISS[16],TCC_MISS[17],TCC_MISS[18],TCC_MISS[19],TCC_MISS[1],TCC_MISS[21],TCC_MISS[22],TCC_MISS[23],TCC_MISS[24],TCC_MISS[25],TCC_MISS[26],TCC_MISS[27],TCC_MISS[28],TCC_MISS[2],TCC_MISS[30],TCC_MISS[31],TCC_MISS[32],TCC_MISS[33],TCC_MISS[34],TCC_MISS[35],TCC_MISS[36],TCC_MISS[37],TCC_MISS[38],TCC_MISS[39],TCC_MISS[3],TCC_MISS[41],TCC_MISS[42],TCC_MISS[43],TCC_MISS[44],TCC_MISS[45],TCC_MISS[46],TCC_MISS[47],TCC_MISS[48],TCC_MISS[49],TCC_MISS[50],TCC_MISS[51],TCC_MISS[52],TCC_MISS[53],TCC_MISS[54],TCC_MISS[55],TCC_MISS[57],TCC_MISS[58],TCC_MISS[59],TCC_MISS[5],TCC_MISS[60],TCC_MISS[61],TCC_MISS[62],TCC_MISS[63],TCC_MISS[6],TCC_MISS[7],TCC_MISS[8],TCC_MISS[9],TCC_READ[0],TCC_READ[10],TCC_READ[11],TCC_READ[12],TCC_READ[14],TCC_READ[15],TCC_READ[16],TCC_READ[17],TCC_READ[18],TCC_READ[19],TCC_READ[1],TCC_READ[21],TCC_READ[22],TCC_READ[23],TCC_READ[24],TCC_READ[25],TCC_READ[26],TCC_READ[27],TCC_READ[28],TCC_READ[2],TCC_READ[30],TCC_READ[31],TCC_READ[32],TCC_READ[33],TCC_READ[34],TCC_READ[35],TCC_READ[36],TCC_READ[37],TCC_READ[38],TCC_READ[39],TCC_READ[3],TCC_READ[41],TCC_READ[42],TCC_READ[43],TCC_READ[44],TCC_READ[45],TCC_READ[46],TCC_READ[47],TCC_READ[48],TCC_READ[49],TCC_READ[50],TCC_READ[51],TCC_READ[52],TCC_READ[53],TCC_READ[54],TCC_READ[55],TCC_READ[57],TCC_READ[58],TCC_READ[59],TCC_READ[5],TCC_READ[60],TCC_READ[61],TCC_READ[62],TCC_READ[63],TCC_READ[6],TCC_READ[7],TCC_READ[8],TCC_READ[9],TCC_WRITE[0],TCC_WRITE[10],TCC_WRITE[11],TCC_WRITE[12],TCC_WRITE[14],TCC_WRITE[15],TCC_WRITE[16],TCC_WRITE[17],TCC_WRITE[18],TCC_WRITE[19],TCC_WRITE[1],TCC_WRITE[21],TCC_WRITE[22],TCC_WRITE[23],TCC_WRITE[24],TCC_WRITE[25],TCC_WRITE[26],TCC_WRITE[27],TCC_WRITE[28],TCC_WRITE[2],TCC_WRITE[30],TCC_WRITE[31],TCC_WRITE[32],TCC_WRITE[33],TCC_WRITE[34],TCC_WRITE[35],TCC_WRITE[36],TCC_WRITE[37],TCC_WRITE[38],TCC_WRITE[39],TCC_WRITE[3],TCC_WRITE[41],TCC_WRITE[42],TCC_WRITE[43],TCC_WRITE[44],TCC_WRITE[45],TCC_WRITE[46],TCC_WRITE[47],TCC_WRITE[48],TCC_WRITE[49],TCC_WRITE[50],TCC_WRITE[51],TCC_WRITE[52],TCC_WRITE[53],TCC_WRITE[54],TCC_WRITE[55],TCC_WRITE[57],TCC_WRITE[58],TCC_WRITE[59],TCC_WRITE[5],TCC_WRITE[60],TCC_WRITE[61],TCC_WRITE[62],TCC_WRITE[63],TCC_WRITE[6],TCC_WRITE[7],TCC_WRITE[8],TCC_WRITE[9],TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_RW_READ_REQ_sum,TCP_TCP_LATENCY_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_SPI_STALL_sum
|
||||
0,0,1,15758,15758,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248226140812256,1248226140833735,1,13,0.0,16354.0,2108.0,0.0,74761.0,37009.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,256862.0,0.0,0.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,4096.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,4098.0,2048.0,2048.0,2052.0,2050.0,2049.0,4097.0,4096.0,2050.0,2048.0,4098.0,2048.0,2048.0,2051.0,2048.0,2050.0,2048.0,2049.0,2048.0,2050.0,2052.0,2048.0,4102.0,2048.0,2050.0,2049.0,2048.0,2051.0,2050.0,2048.0,2048.0,2050.0,2049.0,2050.0,2048.0,2050.0,2048.0,2048.0,4096.0,2048.0,2051.0,2048.0,2049.0,2048.0,2050.0,2048.0,2052.0,2048.0,2048.0,2050.0,2048.0,2050.0,2048.0,2049.0,2048.0,2050.0,2049.0,2050.0,2050.0,1024.0,1024.0,1028.0,1096.0,1060.0,2066.0,2048.0,1096.0,1024.0,2050.0,1024.0,1024.0,1097.0,1024.0,1096.0,1024.0,1042.0,1024.0,1096.0,1098.0,1024.0,2054.0,1024.0,1096.0,1060.0,1024.0,1027.0,1096.0,1024.0,1024.0,1096.0,1060.0,1026.0,1024.0,1096.0,1024.0,1024.0,2048.0,1024.0,1097.0,1024.0,1042.0,1024.0,1096.0,1024.0,1098.0,1024.0,1024.0,1026.0,1024.0,1096.0,1024.0,1042.0,1024.0,1096.0,1060.0,1096.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,4096.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,0.0,0.0,65536.0,12901602.0,0.0,601.0
|
||||
1,0,1,15758,15758,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248226141632504,1248226141649503,2,13,0.0,14445.0,2112.0,0.0,66766.0,29059.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,186838.0,0.0,0.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,4096.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,4098.0,2048.0,2049.0,2048.0,2050.0,2049.0,4097.0,4096.0,2050.0,2048.0,4096.0,2049.0,2048.0,2050.0,2048.0,2050.0,2048.0,2048.0,2048.0,2050.0,2050.0,2048.0,4097.0,2048.0,2050.0,2049.0,2049.0,2048.0,2050.0,2048.0,2048.0,2050.0,2049.0,2049.0,2048.0,2050.0,2048.0,2049.0,4097.0,2048.0,2050.0,2048.0,2048.0,2048.0,2050.0,2048.0,2050.0,2048.0,2049.0,2049.0,2048.0,2050.0,2048.0,2048.0,2048.0,2050.0,2049.0,2050.0,2067.0,1024.0,1042.0,1024.0,1096.0,1060.0,2049.0,2048.0,1096.0,1024.0,2048.0,1025.0,1024.0,1096.0,1024.0,1096.0,1024.0,1024.0,1024.0,1096.0,1096.0,1024.0,2049.0,1024.0,1096.0,1060.0,1042.0,1024.0,1096.0,1024.0,1024.0,1096.0,1060.0,1025.0,1024.0,1096.0,1024.0,1042.0,2049.0,1024.0,1096.0,1024.0,1024.0,1024.0,1096.0,1024.0,1096.0,1024.0,1025.0,1025.0,1024.0,1096.0,1024.0,1024.0,1024.0,1096.0,1060.0,1096.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,4096.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,0.0,0.0,65536.0,8973198.0,0.0,897.0
|
||||
2,0,1,15758,15758,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248226142354637,1248226142371716,3,13,0.0,11292.0,2055.0,0.0,63585.0,29133.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,186316.0,0.0,0.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,4096.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,4097.0,2048.0,2048.0,2048.0,2050.0,2049.0,4096.0,4096.0,2050.0,2048.0,4096.0,2048.0,2048.0,2050.0,2048.0,2050.0,2048.0,2048.0,2048.0,2050.0,2050.0,2048.0,4097.0,2048.0,2050.0,2049.0,2048.0,2048.0,2050.0,2048.0,2048.0,2050.0,2049.0,2049.0,2048.0,2050.0,2048.0,2048.0,4096.0,2048.0,2050.0,2048.0,2048.0,2048.0,2050.0,2048.0,2050.0,2048.0,2048.0,2049.0,2048.0,2050.0,2048.0,2048.0,2048.0,2050.0,2049.0,2050.0,2066.0,1024.0,1024.0,1024.0,1096.0,1060.0,2048.0,2048.0,1096.0,1024.0,2048.0,1024.0,1024.0,1096.0,1024.0,1096.0,1024.0,1024.0,1024.0,1096.0,1096.0,1024.0,2066.0,1024.0,1096.0,1060.0,1024.0,1024.0,1096.0,1024.0,1024.0,1096.0,1060.0,1042.0,1024.0,1096.0,1024.0,1024.0,2048.0,1024.0,1096.0,1024.0,1024.0,1024.0,1096.0,1024.0,1096.0,1024.0,1024.0,1042.0,1024.0,1096.0,1024.0,1024.0,1024.0,1096.0,1060.0,1096.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,4096.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,4096.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,2048.0,0.0,0.0,65536.0,8951646.0,0.0,876.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,Kernel_ID,CPC_CPC_TCIU_IDLE,CPC_TG_SEND,CPF_CPF_TCIU_IDLE,SPI_CS0_BUSY,SPI_CS1_BUSY,SPI_CS2_BUSY,SPI_CS3_BUSY,SQ_INSTS_LDS,SQ_INSTS_LDS_LOAD_BANDWIDTH,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_FMA_F16,SQ_LDS_IDX_ACTIVE,SQ_LEVEL_WAVES,SQ_WAVE_CYCLES,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,TCC_BUBBLE_sum,TCC_EA0_ATOMIC_LEVEL[0],TCC_EA0_ATOMIC_LEVEL[11],TCC_EA0_ATOMIC_LEVEL[12],TCC_EA0_ATOMIC_LEVEL[13],TCC_EA0_ATOMIC_LEVEL[14],TCC_EA0_ATOMIC_LEVEL[16],TCC_EA0_ATOMIC_LEVEL[17],TCC_EA0_ATOMIC_LEVEL[18],TCC_EA0_ATOMIC_LEVEL[19],TCC_EA0_ATOMIC_LEVEL[1],TCC_EA0_ATOMIC_LEVEL[22],TCC_EA0_ATOMIC_LEVEL[23],TCC_EA0_ATOMIC_LEVEL[24],TCC_EA0_ATOMIC_LEVEL[25],TCC_EA0_ATOMIC_LEVEL[27],TCC_EA0_ATOMIC_LEVEL[28],TCC_EA0_ATOMIC_LEVEL[29],TCC_EA0_ATOMIC_LEVEL[2],TCC_EA0_ATOMIC_LEVEL[30],TCC_EA0_ATOMIC_LEVEL[32],TCC_EA0_ATOMIC_LEVEL[33],TCC_EA0_ATOMIC_LEVEL[34],TCC_EA0_ATOMIC_LEVEL[35],TCC_EA0_ATOMIC_LEVEL[37],TCC_EA0_ATOMIC_LEVEL[38],TCC_EA0_ATOMIC_LEVEL[39],TCC_EA0_ATOMIC_LEVEL[3],TCC_EA0_ATOMIC_LEVEL[40],TCC_EA0_ATOMIC_LEVEL[43],TCC_EA0_ATOMIC_LEVEL[44],TCC_EA0_ATOMIC_LEVEL[45],TCC_EA0_ATOMIC_LEVEL[46],TCC_EA0_ATOMIC_LEVEL[48],TCC_EA0_ATOMIC_LEVEL[49],TCC_EA0_ATOMIC_LEVEL[4],TCC_EA0_ATOMIC_LEVEL[50],TCC_EA0_ATOMIC_LEVEL[51],TCC_EA0_ATOMIC_LEVEL[53],TCC_EA0_ATOMIC_LEVEL[54],TCC_EA0_ATOMIC_LEVEL[55],TCC_EA0_ATOMIC_LEVEL[56],TCC_EA0_ATOMIC_LEVEL[58],TCC_EA0_ATOMIC_LEVEL[59],TCC_EA0_ATOMIC_LEVEL[60],TCC_EA0_ATOMIC_LEVEL[61],TCC_EA0_ATOMIC_LEVEL[6],TCC_EA0_ATOMIC_LEVEL[7],TCC_EA0_ATOMIC_LEVEL[8],TCC_EA0_ATOMIC_LEVEL[9],TCC_EA0_RDREQ_LEVEL[0],TCC_EA0_RDREQ_LEVEL[11],TCC_EA0_RDREQ_LEVEL[12],TCC_EA0_RDREQ_LEVEL[13],TCC_EA0_RDREQ_LEVEL[14],TCC_EA0_RDREQ_LEVEL[16],TCC_EA0_RDREQ_LEVEL[17],TCC_EA0_RDREQ_LEVEL[18],TCC_EA0_RDREQ_LEVEL[19],TCC_EA0_RDREQ_LEVEL[1],TCC_EA0_RDREQ_LEVEL[22],TCC_EA0_RDREQ_LEVEL[23],TCC_EA0_RDREQ_LEVEL[24],TCC_EA0_RDREQ_LEVEL[25],TCC_EA0_RDREQ_LEVEL[27],TCC_EA0_RDREQ_LEVEL[28],TCC_EA0_RDREQ_LEVEL[29],TCC_EA0_RDREQ_LEVEL[2],TCC_EA0_RDREQ_LEVEL[30],TCC_EA0_RDREQ_LEVEL[32],TCC_EA0_RDREQ_LEVEL[33],TCC_EA0_RDREQ_LEVEL[34],TCC_EA0_RDREQ_LEVEL[35],TCC_EA0_RDREQ_LEVEL[37],TCC_EA0_RDREQ_LEVEL[38],TCC_EA0_RDREQ_LEVEL[39],TCC_EA0_RDREQ_LEVEL[3],TCC_EA0_RDREQ_LEVEL[40],TCC_EA0_RDREQ_LEVEL[43],TCC_EA0_RDREQ_LEVEL[44],TCC_EA0_RDREQ_LEVEL[45],TCC_EA0_RDREQ_LEVEL[46],TCC_EA0_RDREQ_LEVEL[48],TCC_EA0_RDREQ_LEVEL[49],TCC_EA0_RDREQ_LEVEL[4],TCC_EA0_RDREQ_LEVEL[50],TCC_EA0_RDREQ_LEVEL[51],TCC_EA0_RDREQ_LEVEL[53],TCC_EA0_RDREQ_LEVEL[54],TCC_EA0_RDREQ_LEVEL[55],TCC_EA0_RDREQ_LEVEL[56],TCC_EA0_RDREQ_LEVEL[58],TCC_EA0_RDREQ_LEVEL[59],TCC_EA0_RDREQ_LEVEL[60],TCC_EA0_RDREQ_LEVEL[61],TCC_EA0_RDREQ_LEVEL[6],TCC_EA0_RDREQ_LEVEL[7],TCC_EA0_RDREQ_LEVEL[8],TCC_EA0_RDREQ_LEVEL[9],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_TOO_MANY_EA_WRREQS_STALL[32],TCC_TOO_MANY_EA_WRREQS_STALL[33],TCC_TOO_MANY_EA_WRREQS_STALL[34],TCC_TOO_MANY_EA_WRREQS_STALL[35],TCC_TOO_MANY_EA_WRREQS_STALL[37],TCC_TOO_MANY_EA_WRREQS_STALL[38],TCC_TOO_MANY_EA_WRREQS_STALL[39],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_TOO_MANY_EA_WRREQS_STALL[40],TCC_TOO_MANY_EA_WRREQS_STALL[43],TCC_TOO_MANY_EA_WRREQS_STALL[44],TCC_TOO_MANY_EA_WRREQS_STALL[45],TCC_TOO_MANY_EA_WRREQS_STALL[46],TCC_TOO_MANY_EA_WRREQS_STALL[48],TCC_TOO_MANY_EA_WRREQS_STALL[49],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_TOO_MANY_EA_WRREQS_STALL[50],TCC_TOO_MANY_EA_WRREQS_STALL[51],TCC_TOO_MANY_EA_WRREQS_STALL[53],TCC_TOO_MANY_EA_WRREQS_STALL[54],TCC_TOO_MANY_EA_WRREQS_STALL[55],TCC_TOO_MANY_EA_WRREQS_STALL[56],TCC_TOO_MANY_EA_WRREQS_STALL[58],TCC_TOO_MANY_EA_WRREQS_STALL[59],TCC_TOO_MANY_EA_WRREQS_STALL[60],TCC_TOO_MANY_EA_WRREQS_STALL[61],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCP_GATE_EN2_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TD_TD_BUSY_sum
|
||||
0,0,1,15765,15765,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248226695430472,1248226695452112,1,13,76230.0,4096.0,74700.0,146248.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,6406528.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,366347.0,357772.0,356963.0,349090.0,376766.0,737844.0,674665.0,709219.0,678639.0,690427.0,343990.0,324671.0,343293.0,346854.0,381616.0,358883.0,363344.0,703259.0,361957.0,743500.0,699149.0,680115.0,684746.0,338927.0,323941.0,341659.0,662566.0,341692.0,342216.0,362540.0,345698.0,325196.0,670504.0,706680.0,336552.0,689433.0,668474.0,338628.0,351132.0,343139.0,331632.0,367394.0,363667.0,344667.0,324349.0,343830.0,339430.0,345257.0,339020.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,823402.0,131072.0,0.0,524288.0,816209.0
|
||||
1,0,1,15765,15765,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248226696169603,1248226696186603,2,13,66030.0,4096.0,64509.0,108920.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,4413902.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,168628.0,188771.0,180374.0,166979.0,187051.0,341252.0,347378.0,366453.0,358634.0,349942.0,166901.0,185540.0,167789.0,186890.0,195821.0,191987.0,161167.0,349386.0,173327.0,351353.0,362889.0,349396.0,340194.0,166112.0,162174.0,179731.0,326950.0,183560.0,167731.0,191528.0,159788.0,174031.0,333041.0,347181.0,191522.0,361391.0,371374.0,166146.0,185780.0,171148.0,183365.0,196992.0,178416.0,168290.0,169604.0,172663.0,165574.0,182558.0,177592.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,647210.0,131072.0,0.0,524288.0,639099.0
|
||||
2,0,1,15765,15765,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248226696801619,1248226696818339,3,13,61716.0,4096.0,60350.0,107896.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,4337140.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,192457.0,179283.0,183607.0,168303.0,188445.0,363907.0,353513.0,336506.0,358454.0,357389.0,166113.0,175264.0,165655.0,198953.0,179626.0,182508.0,166395.0,349820.0,187371.0,369566.0,387313.0,340202.0,353747.0,167292.0,163935.0,187961.0,331568.0,189609.0,166929.0,186667.0,164998.0,190238.0,336870.0,380054.0,177919.0,357408.0,351545.0,166698.0,185523.0,186549.0,188624.0,178890.0,183734.0,165658.0,163188.0,167422.0,177959.0,191058.0,197686.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,648321.0,131072.0,0.0,524288.0,640253.0
|
||||
|
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
+1925
File diff suppressed because it is too large
Load Diff
+5
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INST_LEVEL_LDS SQ_INST_LEVEL_LDS_ACCUM SQC_DCACHE_ATOMIC SQC_TC_STALL SQC_ICACHE_REQ SQC_DCACHE_MISSES SQ_INSTS_VALU_MUL_F16 SQ_WAVES_SAVED TA_BUFFER_WRITE_WAVEFRONTS_sum TA_TA_BUSY_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_UTCL1_REQUEST_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCC_EA0_WRREQ_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_ATOMIC_sum TCC_EA0_ATOMIC_LEVEL_sum CPC_ME1_DC0_SPI_BUSY CPC_CPC_TCIU_BUSY SPI_VWC0_VDATA_VALID_WR SPI_RA_REQ_NO_ALLOC_CSN
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
SQ_INST_LEVEL_LDS_ACCUM:
|
||||
architectures:
|
||||
gfx942/gfx941/gfx940/gfx90a:
|
||||
expression: accumulate(SQ_INST_LEVEL_LDS, HIGH_RES)
|
||||
description: SQ_INST_LEVEL_LDS accumulation
|
||||
+5
File diff suppressed because one or more lines are too long
+2565
File diff suppressed because it is too large
Load Diff
+5
File diff suppressed because one or more lines are too long
+2565
File diff suppressed because it is too large
Load Diff
File diff suppressed because one or more lines are too long
+1925
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VALU_ADD_F64 SQ_ACTIVE_INST_VALU SQ_INSTS_SENDMSG SQ_VMEM_TA_CMD_FIFO_FULL SQC_DCACHE_REQ_READ_8 SQC_TC_DATA_ATOMIC_REQ SQ_LDS_BANK_CONFLICT SQ_BUSY_CYCLES TA_DATA_STALLED_BY_TC_CYCLES_sum TA_BUFFER_WAVEFRONTS_sum TCP_TCR_TCP_STALL_CYCLES_sum TCP_UTCL1_TRANSLATION_MISS_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_TCC_READ_REQ_sum TCC_UC_REQ_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_EA0_WRREQ_LEVEL_sum CPC_SYNC_FIFO_FULL CPC_CPC_UTCL2IU_BUSY SPI_CS2_NUM_THREADGROUPS SPI_CS3_NUM_THREADGROUPS SPI_CS1_NUM_THREADGROUPS SPI_CS0_NUM_THREADGROUPS
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VALU_MFMA_MOPS_F16 SQC_TC_DATA_READ_REQ SQ_INSTS_VMEM SQ_VALU_MFMA_BUSY_CYCLES SQ_INSTS_VALU_MFMA_MOPS_F6F4 SQ_INSTS_VALU_INT64 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VALU_TRANS_F64 TA_FLAT_WRITE_WAVEFRONTS_sum TA_BUFFER_READ_WAVEFRONTS_sum TCP_PENDING_STALL_CYCLES_sum TCP_TCC_NC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TCP_UTCL1_PERMISSION_MISS_sum TCC_EA0_RD_UNCACHED_32B_sum TCC_CC_REQ_sum TCC_EA0_RDREQ_LEVEL_sum TCC_RW_REQ_sum CPC_GD_BUSY CPC_CANE_BUSY SPI_RA_REQ_NO_ALLOC SPI_SWC_CSC_WR
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_THREAD_CYCLES_VALU SQC_DCACHE_MISSES_DUPLICATE SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_MFMA_MOPS_F8 SQ_INSTS_VALU_MFMA_F8 SQ_INSTS_SMEM SQ_INSTS_VALU_INT32 SQ_INSTS_VALU_TRANS_F32 TA_BUFFER_COALESCED_WRITE_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum TCP_TCC_WRITE_REQ_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCC_BUSY_sum TCC_HIT_sum TCC_NORMAL_WRITEBACK_sum TCC_READ_sum CPC_CPC_UTCL2IU_IDLE CPC_UTCL1_STALL_ON_TRANSLATION SPI_RA_RES_STALL_CSN SPI_RA_BAR_CU_FULL_CSN
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQC_DCACHE_REQ_READ_2 SQ_INSTS_LDS_STORE_BANDWIDTH SQ_LDS_MEM_VIOLATIONS SQ_ACTIVE_INST_ANY SQ_LDS_ATOMIC_RETURN SQ_INSTS_BRANCH SQ_INSTS_VALU_CVT SQ_ACTIVE_INST_MISC TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TCC_CC_WRITE_REQ_sum TCC_WRITEBACK_sum TCC_PROBE_sum TCC_MISS_sum TCC_REQ_sum SPI_VWC1_VDATA_VALID_WR SPI_RA_VGPR_SIMD_FULL_CSN
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_WAVES_RESTORED SQ_WAVES SQ_LDS_DATA_FIFO_FULL SQC_TC_DATA_WRITE_REQ SQ_INSTS_VALU_MFMA_F64 SQ_INSTS_VALU_MFMA_BF16 SQ_ACTIVE_INST_LDS SQ_VMEM_TA_ADDR_FIFO_FULL TCC_EA0_WRREQ_64B_sum TCC_EA0_ATOMIC_sum TCC_EA0_RDREQ_DRAM_sum TCC_EA0_WRREQ_DRAM_sum SPI_CSC_WAVE_CNT_BUSY SPI_RA_WAVE_SIMD_FULL_CSN
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_LDS_ADDR_CONFLICT SQC_ICACHE_HITS SQ_INSTS_LDS_ATOMIC_BANDWIDTH SQ_INSTS_MFMA SQ_WAIT_INST_ANY SQ_INSTS_VALU_MFMA_F6F4 SQ_INSTS_VALU_MUL_F32 SQC_DCACHE_REQ_READ_1 TCC_STREAMING_REQ_sum TCC_EA0_RDREQ_32B_sum TCC_EA0_RDREQ_sum TCC_WRITE_sum SPI_RA_LDS_CU_FULL_CSN SPI_RA_TMP_STALL_CSN
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VALU_MFMA_MOPS_F64 SQ_LDS_UNALIGNED_STALL SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU SQ_WAIT_ANY SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQC_TC_INST_REQ TCC_EA0_WR_UNCACHED_32B_sum TCC_NORMAL_EVICT_sum SPI_RA_WVLIM_STALL_CSN SPI_RA_TGLIM_CU_FULL_CSN
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQC_DCACHE_REQ SQ_INSTS_SALU SQ_ACTIVE_INST_FLAT SQ_IFETCH SQ_ACTIVE_INST_SCA SQ_INSTS SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_ADD_F32
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID
|
||||
0,"vecCopy(double*, double*, double*, int, int)",0
|
||||
1,"vecCopy(double*, double*, double*, int, int)",0
|
||||
2,"vecCopy(double*, double*, double*, int, int)",0
|
||||
|
File diff suppressed because one or more lines are too long
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,Kernel_ID,CPC_CPC_UTCL2IU_BUSY,CPC_SYNC_FIFO_FULL,SPI_CS0_NUM_THREADGROUPS,SPI_CS1_NUM_THREADGROUPS,SPI_CS2_NUM_THREADGROUPS,SPI_CS3_NUM_THREADGROUPS,SQC_DCACHE_REQ_READ_8,SQC_TC_DATA_ATOMIC_REQ,SQ_ACTIVE_INST_VALU,SQ_BUSY_CYCLES,SQ_INSTS_SENDMSG,SQ_INSTS_VALU_ADD_F64,SQ_LDS_BANK_CONFLICT,SQ_VMEM_TA_CMD_FIFO_FULL,TA_BUFFER_WAVEFRONTS_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_EA0_WRREQ_LEVEL_sum,TCC_UC_REQ_sum,TCP_TCC_READ_REQ_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum
|
||||
0,0,1,15772,15772,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248227257271964,1248227257293723,1,13,389.0,0.0,4096.0,0.0,0.0,0.0,0.0,0.0,98304.0,126903.0,16384.0,0.0,0.0,0.0,0.0,154249.0,0.0,36146.0,9826410.0,26.0,65536.0,11.0,768.0,0.0
|
||||
1,0,1,15772,15772,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248227257962097,1248227257979016,2,13,0.0,0.0,4096.0,0.0,0.0,0.0,0.0,0.0,98304.0,96924.0,16384.0,0.0,0.0,0.0,0.0,103050.0,0.0,36209.0,10285296.0,8.0,65536.0,0.0,0.0,0.0
|
||||
2,0,1,15772,15772,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248227258551114,1248227258567914,3,13,0.0,0.0,4096.0,0.0,0.0,0.0,0.0,0.0,98304.0,96768.0,16384.0,0.0,0.0,0.0,0.0,100616.0,0.0,36239.0,10281734.0,0.0,65536.0,0.0,0.0,0.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,Kernel_ID,CPC_CANE_BUSY,CPC_GD_BUSY,SPI_RA_REQ_NO_ALLOC,SPI_SWC_CSC_WR,SQC_DCACHE_REQ_READ_4,SQC_TC_DATA_READ_REQ,SQ_INSTS_VALU_INT64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_F6F4,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VMEM,SQ_VALU_MFMA_BUSY_CYCLES,TA_BUFFER_READ_WAVEFRONTS_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TCC_CC_REQ_sum,TCC_EA0_RDREQ_LEVEL_sum,TCC_EA0_RD_UNCACHED_32B_sum,TCC_RW_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCP_TCC_NC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TCP_UTCL1_PERMISSION_MISS_sum
|
||||
0,0,1,15779,15779,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248227786612853,1248227786635252,1,13,630.0,30469.0,12744.0,32768.0,0.0,72.0,32768.0,0.0,0.0,0.0,32768.0,0.0,0.0,16384.0,0.0,22666001.0,58.0,197976.0,406733.0,0.0,0.0,0.0
|
||||
1,0,1,15779,15779,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248227787316865,1248227787333785,2,13,631.0,22019.0,4288.0,32768.0,0.0,72.0,32768.0,0.0,0.0,0.0,32768.0,0.0,0.0,16384.0,0.0,11922030.0,16.0,197976.0,289225.0,0.0,0.0,0.0
|
||||
2,0,1,15779,15779,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248227787897083,1248227787913762,3,13,630.0,21586.0,3860.0,32768.0,0.0,72.0,32768.0,0.0,0.0,0.0,32768.0,0.0,0.0,16384.0,0.0,11792534.0,0.0,197976.0,286818.0,0.0,0.0,0.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,Kernel_ID,CPC_CPC_UTCL2IU_IDLE,CPC_UTCL1_STALL_ON_TRANSLATION,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_RES_STALL_CSN,SQC_DCACHE_MISSES_DUPLICATE,SQ_INSTS_SMEM,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_MFMA_F8,SQ_INSTS_VALU_MFMA_MOPS_F8,SQ_INSTS_VALU_TRANS_F32,SQ_THREAD_CYCLES_VALU,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,TCC_BUSY_sum,TCC_HIT_sum,TCC_NORMAL_WRITEBACK_sum,TCC_READ_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TCC_CC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_WRITE_REQ_sum
|
||||
0,0,1,15786,15786,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248228340675080,1248228340696799,1,13,76981.0,399.0,0.0,9346.0,2160.0,65536.0,0.0,49152.0,0.0,0.0,0.0,6291456.0,0.0,32768.0,533130.0,66864.0,30395.0,66936.0,0.0,0.0,0.0,131072.0
|
||||
1,0,1,15786,15786,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248228341369934,1248228341386613,2,13,65633.0,0.0,0.0,3274.0,2160.0,65536.0,0.0,49152.0,0.0,0.0,0.0,6291456.0,0.0,32768.0,459164.0,66864.0,29343.0,66912.0,0.0,0.0,0.0,131072.0
|
||||
2,0,1,15786,15786,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248228341957512,1248228341974431,3,13,62962.0,0.0,0.0,3253.0,2160.0,65536.0,0.0,49152.0,0.0,0.0,0.0,6291456.0,0.0,32768.0,460697.0,66864.0,29330.0,66904.0,0.0,0.0,0.0,131072.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,Kernel_ID,SPI_RA_VGPR_SIMD_FULL_CSN,SPI_VWC1_VDATA_VALID_WR,SQC_DCACHE_REQ_READ_2,SQ_ACTIVE_INST_ANY,SQ_ACTIVE_INST_MISC,SQ_INSTS_BRANCH,SQ_INSTS_LDS_STORE_BANDWIDTH,SQ_INSTS_VALU_CVT,SQ_LDS_ATOMIC_RETURN,SQ_LDS_MEM_VIOLATIONS,TCC_MISS_sum,TCC_PROBE_sum,TCC_REQ_sum,TCC_WRITEBACK_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_READ_sum
|
||||
0,0,1,15793,15793,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248228890145284,1248228890166603,1,13,0.0,32768.0,32768.0,278528.0,32768.0,16384.0,0.0,0.0,0.0,0.0,131138.0,0.0,198002.0,65596.0,0.0,2097152.0,0.0,1048576.0
|
||||
1,0,1,15793,15793,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248228890710662,1248228890727781,2,13,0.0,32768.0,32768.0,278528.0,32768.0,16384.0,0.0,0.0,0.0,0.0,131120.0,0.0,197984.0,65596.0,0.0,2097152.0,0.0,1048576.0
|
||||
2,0,1,15793,15793,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248228891192003,1248228891208963,3,13,0.0,32768.0,32768.0,278528.0,32768.0,16384.0,0.0,0.0,0.0,0.0,131112.0,0.0,197976.0,65596.0,0.0,2097152.0,0.0,1048576.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,Kernel_ID,SPI_CSC_WAVE_CNT_BUSY,SPI_RA_WAVE_SIMD_FULL_CSN,SQC_TC_DATA_WRITE_REQ,SQ_ACTIVE_INST_LDS,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F64,SQ_LDS_DATA_FIFO_FULL,SQ_VMEM_TA_ADDR_FIFO_FULL,SQ_WAVES,SQ_WAVES_RESTORED,TCC_EA0_ATOMIC_sum,TCC_EA0_RDREQ_DRAM_sum,TCC_EA0_WRREQ_64B_sum,TCC_EA0_WRREQ_DRAM_sum
|
||||
0,0,1,15800,15800,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248229438857357,1248229438879317,1,13,129716.0,279581.0,0.0,0.0,0.0,0.0,0.0,0.0,16384.0,0.0,0.0,65622.0,131072.0,131072.0
|
||||
1,0,1,15800,15800,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248229439181269,1248229439198349,2,13,97526.0,104638.0,0.0,0.0,0.0,0.0,0.0,0.0,16384.0,0.0,0.0,65612.0,131072.0,131072.0
|
||||
2,0,1,15800,15800,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248229439450184,1248229439467063,3,13,97380.0,103228.0,0.0,0.0,0.0,0.0,0.0,0.0,16384.0,0.0,0.0,65612.0,131072.0,131072.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,Kernel_ID,SPI_RA_LDS_CU_FULL_CSN,SPI_RA_TMP_STALL_CSN,SQC_DCACHE_REQ_READ_1,SQC_ICACHE_HITS,SQ_INSTS_LDS_ATOMIC_BANDWIDTH,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_F6F4,SQ_INSTS_VALU_MUL_F32,SQ_LDS_ADDR_CONFLICT,SQ_WAIT_INST_ANY,TCC_EA0_RDREQ_32B_sum,TCC_EA0_RDREQ_sum,TCC_STREAMING_REQ_sum,TCC_WRITE_sum
|
||||
0,0,1,15807,15807,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248229989191714,1248229989213393,1,13,0.0,0.0,32768.0,64005.0,0.0,0.0,0.0,0.0,0.0,656853.0,0.0,65640.0,0.0,131072.0
|
||||
1,0,1,15807,15807,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248229989539141,1248229989555860,2,13,0.0,0.0,32768.0,64262.0,0.0,0.0,0.0,0.0,0.0,95857.0,0.0,65612.0,0.0,131072.0
|
||||
2,0,1,15807,15807,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248229989799091,1248229989816011,3,13,0.0,0.0,32768.0,64364.0,0.0,0.0,0.0,0.0,0.0,120606.0,0.0,65612.0,0.0,131072.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,Kernel_ID,SPI_RA_TGLIM_CU_FULL_CSN,SPI_RA_WVLIM_STALL_CSN,SQC_TC_INST_REQ,SQ_INSTS_VALU,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F64,SQ_INSTS_VALU_TRANS_F16,SQ_LDS_UNALIGNED_STALL,SQ_WAIT_ANY,TCC_EA0_WR_UNCACHED_32B_sum,TCC_NORMAL_EVICT_sum
|
||||
0,0,1,15814,15814,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248230542355535,1248230542376494,1,13,0.0,0.0,1296.0,98304.0,0.0,0.0,0.0,0.0,0.0,5300250.0,0.0,44.0
|
||||
1,0,1,15814,15814,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248230542613524,1248230542630444,2,13,0.0,0.0,1296.0,98304.0,0.0,0.0,0.0,0.0,0.0,4063067.0,0.0,44.0
|
||||
2,0,1,15814,15814,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248230542841396,1248230542858275,3,13,0.0,0.0,1296.0,98304.0,0.0,0.0,0.0,0.0,0.0,4109650.0,0.0,44.0
|
||||
|
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size,Kernel_Name,Start_Timestamp,End_Timestamp,Correlation_ID,Kernel_ID,SQC_DCACHE_REQ,SQ_ACTIVE_INST_FLAT,SQ_ACTIVE_INST_SCA,SQ_IFETCH,SQ_INSTS,SQ_INSTS_SALU,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MFMA_F32
|
||||
0,0,1,15821,15821,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248231092253037,1248231092274436,1,13,65536.0,32768.0,114688.0,65536.0,327680.0,49152.0,0.0,0.0
|
||||
1,0,1,15821,15821,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248231092448589,1248231092465748,2,13,65536.0,32768.0,114688.0,65536.0,327680.0,49152.0,0.0,0.0
|
||||
2,0,1,15821,15821,1048576,256,0,0,4,0,16,64,"vecCopy(double*, double*, double*, int, int)",1248231092604703,1248231092621702,3,13,65536.0,32768.0,114688.0,65536.0,327680.0,49152.0,0.0,0.0
|
||||
|
@@ -0,0 +1,39 @@
|
||||
config_dir: /app/src/rocprof_compute_soc/analysis_configs
|
||||
device: -1
|
||||
dispatch: null
|
||||
filter_blocks: {}
|
||||
format_rocprof_output: csv
|
||||
hip_trace: false
|
||||
join_type: grid
|
||||
kernel: null
|
||||
kernel_names: false
|
||||
kokkos_trace: false
|
||||
list_metrics: null
|
||||
loglevel: 10
|
||||
lucky: false
|
||||
mem_level: ALL
|
||||
mode: profile
|
||||
name: vcopy
|
||||
no_roof: true
|
||||
path: /app/workloads/vcopy/MI350
|
||||
quiet: false
|
||||
remaining:
|
||||
- --
|
||||
- tests/vcopy
|
||||
- -n
|
||||
- '1048576'
|
||||
- -b
|
||||
- '256'
|
||||
- -i
|
||||
- '3'
|
||||
roof_only: false
|
||||
roofline_data_type:
|
||||
- FP32
|
||||
sort: kernels
|
||||
spatial_multiplexing: null
|
||||
specs: false
|
||||
subpath: gpu
|
||||
summaries: false
|
||||
target: null
|
||||
use_rocscope: false
|
||||
verbose: 1
|
||||
@@ -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_series,gpu_model,gpu_arch,gpu_chip_id,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,num_xcd,num_hbm_channels
|
||||
vcopy,tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 28 22:43:57 2025 (UTC),3,f77021840818,AMD Ryzen Threadripper PRO 7985WX 64-Cores,AMDVBS1052957N.FD,Ubuntu 22.04.5 LTS,5.15.0-70-generic,,527456116,,6.5.0-831,113-M3550101-100,SPX,NPS1,MI350,MI350,gfx950,30112,32,4096,128,4,16,64,1024,32,0,,0,,128,32,64,4,8,128
|
||||
|
Reference in New Issue
Block a user