Update workloads (#290)
* updating workloads Signed-off-by: Jose Santos <josantos@amd.com> * updating workloads Signed-off-by: Jose Santos <josantos@amd.com> * Adding generate workloads script Signed-off-by: Jose Santos <josantos@amd.com> * Changing output workloads dir in shell script Signed-off-by: Jose Santos <josantos@amd.com> --------- Signed-off-by: Jose Santos <josantos@amd.com>
This commit is contained in:
1 parent
1dc4553091
commit
2d1f73ad11
360 files changed
+958
-828
No files matched your search
Executable
+62
@@ -0,0 +1,62 @@
|
||||
#!/bin/bash
|
||||
declare -A commands=(
|
||||
[path]=' '
|
||||
[no_roof]='--no-roof'
|
||||
[kernel_names]='--roof-only --kernel-names'
|
||||
[device_filter]='--device 0'
|
||||
[kernel]='--kernel "vecCopy(double*, double*, double*, int, int) [clone .kd]"'
|
||||
[kernel_summaries]='--kernel-summaries vcopy'
|
||||
[ipblocks_SQ]='-b SQ'
|
||||
[ipblocks_SQC]='-b SQC'
|
||||
[ipblocks_TA]='-b TA'
|
||||
[ipblocks_TD]='-b TD'
|
||||
[ipblocks_TCP]='-b TCP'
|
||||
[ipblocks_TCC]='-b TCC'
|
||||
[ipblocks_SPI]='-b SPI'
|
||||
[ipblocks_CPC]='-b CPC'
|
||||
[ipblocks_CPF]='-b CPF'
|
||||
[ipblocks_SQ_CPC]='-b SQ CPC'
|
||||
[ipblocks_SQ_TA]='-b SQ TA'
|
||||
[ipblocks_SQ_SPI]='-b SQ SPI'
|
||||
[ipblocks_SQ_SQC_TCP_CPC]='-b SQ SQC TCP CPC'
|
||||
[ipblocks_SQ_SPI_TA_TCC_CPF]='-b SQ SPI TA TCC CPF'
|
||||
[dispatch_0]='--dispatch 0'
|
||||
[dispatch_0_1]='--dispatch 0:2'
|
||||
[dispatch_2]='--dispatch 1'
|
||||
[kernel_verbose_0]='--kernel-verbose 0'
|
||||
[kernel_verbose_1]='--kernel-verbose 1'
|
||||
[kernel_verbose_2]='--kernel-verbose 2'
|
||||
[kernel_verbose_3]='--kernel-verbose 3'
|
||||
[kernel_verbose_4]='--kernel-verbose 4'
|
||||
[kernel_verbose_5]='--kernel-verbose 5'
|
||||
[join_type_grid]='--join-type grid'
|
||||
[join_type_kernel]='--join-type kernel'
|
||||
[sort_dispatches]='--roof-only --sort dispatches'
|
||||
[sort_kernels]='--roof-only --sort kernels'
|
||||
[mem_levels_HBM]='--roof-only --mem-level HBM'
|
||||
[mem_levels_L2]='--roof-only --mem-level L2'
|
||||
[mem_levels_vL1D]='--roof-only --mem-level vL1D'
|
||||
[mem_levels_LDS]='--roof-only --mem-level LDS'
|
||||
[mem_levels_HBM_LDS]='--roof-only --mem-level HBM LDS'
|
||||
[mem_levels_vL1d_LDS]='--roof-only --mem-level vL1D LDS'
|
||||
[mem_levels_L2_vL1d_LDS]='--roof-only --mem-level L2 vL1D LDS'
|
||||
#########################################################
|
||||
# Attempt to break omniperf #
|
||||
#########################################################
|
||||
[dispatch_7]='--dispatch 7'
|
||||
[dispatch_6_8]='--dispatch 6:8'
|
||||
[dispatch_inv]='--dispatch invalid'
|
||||
[kernel_substr]='--kernel vecCopy'
|
||||
[kernel_inv_str]='--kernel vecPaste'
|
||||
[kernel_inv_int]='--kernel 42'
|
||||
[device_inv]='--device invalid' # does not generate a workload
|
||||
[device_inv_int]='--device -1'
|
||||
)
|
||||
soc=MI100
|
||||
echo "starting"
|
||||
for key in "${!commands[@]}"; do
|
||||
echo profiling $key;
|
||||
command="${commands[$key]}"
|
||||
echo "$key = ./src/omniperf profile -n $key ${dirs[@]}"
|
||||
./src/omniperf profile -n $key $command -p tests/workloads/$key/$soc -- ./tests/vcopy -n 1048576 -b 256 -i 3 ;
|
||||
echo "done" ; done
|
||||
@@ -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) ",2,0,0,2869770,2869770,1048576,256,0,0,8,8,16,64,0x0,0x7eff6a3d2e80,48732,48732,16384,65536,12984,1684952,2187869534755189,2187863086843344,2187863086866864,2187869542260328
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2869770,2869770,1048576,256,0,0,8,8,16,64,0x0,0x7eff6a3d2e80,43698,43698,16384,65536,8101,1048580,2187869542283442,2187863086979504,2187863086998544,2187869542602320
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2869770,2869770,1048576,256,0,0,8,8,16,64,0x0,0x7eff6a3d2e80,42890,42890,16384,65536,8070,1048588,2187869542634450,2187863087020944,2187863087039824,2187869542818836
|
||||
|
@@ -0,0 +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) ",2,0,0,2869952,2869952,1048576,256,0,0,8,8,16,64,0x0,0x7f72072bae80,0,0,0,2187869977668644,2187863086843344,2187863086866864,2187869985176257
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2869952,2869952,1048576,256,0,0,8,8,16,64,0x0,0x7f72072bae80,0,0,0,2187869985195062,2187863086979504,2187863086998544,2187869985509663
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2869952,2869952,1048576,256,0,0,8,8,16,64,0x0,0x7f72072bae80,0,0,0,2187869985538427,2187863087020944,2187863087039824,2187869985711863
|
||||
|
@@ -0,0 +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) ",2,0,0,2867946,2867946,1048576,256,0,0,8,8,16,64,0x0,0x7fde64f1ae80,65536,193254,24880920,2187864659556927,2187863086843344,2187863086866864,2187864667075622
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2867946,2867946,1048576,256,0,0,8,8,16,64,0x0,0x7fde64f1ae80,65536,177776,22778168,2187864667094427,2187863086979504,2187863086998544,2187864667403628
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2867946,2867946,1048576,256,0,0,8,8,16,64,0x0,0x7fde64f1ae80,65536,177040,22689848,2187864667432131,2187863087020944,2187863087039824,2187864667600928
|
||||
|
@@ -0,0 +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) ",2,0,0,2870680,2870680,1048576,256,0,0,8,8,16,64,0x0,0x7f9a920b2e80,32768,646946,82808524,2187872008481374,2187863086843344,2187863086866864,2187872016007002
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2870680,2870680,1048576,256,0,0,8,8,16,64,0x0,0x7f9a920b2e80,32768,665028,85108136,2187872016024845,2187863086979504,2187863086998544,2187872016349314
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2870680,2870680,1048576,256,0,0,8,8,16,64,0x0,0x7f9a920b2e80,32768,662924,84848200,2187872016378269,2187863087020944,2187863087039824,2187872016554119
|
||||
|
@@ -0,0 +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) ",2,0,0,2870862,2870862,1048576,256,0,0,8,8,16,64,0x0,0x7febf83ace80,49355,49355,18227,394848,16384,25114743,232859,0,100948108,2187872453712459,2187863086843344,2187863086866864,2187872461243888
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2870862,2870862,1048576,256,0,0,8,8,16,64,0x0,0x7febf83ace80,44034,44034,15357,352280,16384,24796619,227952,0,99683264,2187872461273072,2187863086979504,2187863086998544,2187872461597281
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2870862,2870862,1048576,256,0,0,8,8,16,64,0x0,0x7febf83ace80,44730,44730,15579,357848,16384,24297029,232090,0,97687376,2187872461636034,2187863087020944,2187863087039824,2187872461826611
|
||||
|
@@ -0,0 +1,5 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_EA_ATOMIC_LEVEL_sum
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31]
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31]
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31]
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31]
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31]
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31]
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS_SMEM TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS SQ_WAIT_ANY TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,5 @@
|
||||
pmc:
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -0,0 +1,4 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_1,obj_1,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_2,obj_2,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_3,obj_3,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],wave_size_4,obj_4,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_5,obj_5,TCC_EA_ATOMIC_LEVEL_sum,wave_size_6,obj_6,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_7,obj_7,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_LLine truncated
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f4e659bce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86630.0,44442.0,131112.0,0.0,64,0x7f8dad7cee80,0,0,192,0,65536,64397,48,1372,31201,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,47235,1720,0,48.0,339.0,0.0,262288.0,64,0x7f48ded7ce80,386640,236475,3450540,16384,25581398,144,48,0,48329,48329,3899682.0,2989415.0,5268.0,966859.0,2049533.0,0.0,2980362.0,2669526.0,385183,246412,48329,0,48329,0,1546528.0,957726.0,0.0,0.0,64,0x7f5e2cfc4e80,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fb21fe58e80,32768,0,0,0,16384,16384,393216,23050929,960.0,513890.0,0.0,524288.0,1114083.0,32768.0,0,0,0,17041,131072.0,131072.0,0.0,131072.0,64,0x7fea92c9ae80,0.0,64,0x7fd78d976e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131292.0,0.0,432.0,131291.0,64,0x7f0dce858e80,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,64,0x7f468f6d0e80,2579,0,0,1919912,2736,0,0,1925348,2713,0,0,1871657,2342,0,0,1815952,3200,0,0,1867731,2494,0,0,1888385,2355,0,0,1880021,4336,0,0,2231068,2637,0,0,1900127,643,0,0,1579931,5744,0,0,2192760,932,0,0,1738650,2822,0,0,1918072,886,0,0,1651251,1530,0,0,1787081,2331,0,0,1934359,4040,0,0,1980397,953,0,0,1635180,5421,0,0,2152545,1559,0,0,1702324,4295,0,0,2038417,971,0,0,1652548,1670,0,0,1746359,2173,0,0,1790259,3036,0,0,1840325,950,0,0,1642207,2200,0,0,1869283,2869,0,0,1988779,7566,0,0,2332139,2406,0,0,1842139,1570,0,0,1740592,2650,0,0,1965375,64,0x7f06f910ee80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,63224.0,129223.0,64,0x7fdfc3e88e80,194569,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13202,29586,9853,550,0,47728,262720.0,0.0,188.0,262532.0,64,0x7fe55b430e80,131072.0,131072.0,0.0,2560155.0,0.0,0.0,129583622.0,60018628.0,64,0x7fc701a42e80,2216157,360448,163840,0,0,180224,114688,0,71312939.0,171827287.0,70038535.0,131072.0,0.0,610894.0,0,0,26910,72105.0,0.0,0.0,72105.0,64,0x7f3119578e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8363,4408,8504,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8198,4102,8198,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f842d1bae80,0,3235050,4096,4096,0,3276819,4096,4096,0,3119192,4096,4096,0,2748450,4096,4096,0,2837173,4096,4096,0,3204393,4096,4096,0,3105910,4096,4096,0,3581114,4096,4096,0,3291469,4096,4096,0,4130633,4096,4096,0,3274382,4096,4096,0,3109424,4096,4096,0,3301210,4096,4096,0,2510362,4096,4096,0,3025633,4096,4096,0,3488333,4096,4096,0,3366075,4096,4096,0,2752798,4096,4096,0,3408785,4096,4096,0,3633022,4096,4096,0,3261018,4096,4096,0,2938563,4096,4096,0,3023265,4096,4096,0,3217978,4096,4096,0,2815878,4096,4096,0,3226586,4096,4096,0,3196368,4096,4096,0,3067972,4096,4096,0,2942037,4096,4096,0,2640435,4096,4096,0,3070656,4096,4096,0,3194085,4096,4096,64,0x7f8530110e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47510,0,131530.0,131072.0,0.0,131104.0,64,0x7f940eb4ae80,4096,0,1551,0,4096,0,2605,0,4096,0,1531,0,4099,0,227,0,4096,0,1913,0,4096,0,573,0,4144,0,421,0,4096,0,2924,0,4096,0,894,0,4096,0,1838,0,4096,0,5705,0,4096,0,737,0,4096,0,1327,0,4096,0,228,0,4097,0,783,0,4096,0,782,0,4096,0,3317,0,4096,0,3382,0,4096,0,4238,0,4096,0,711,0,4096,0,629,0,4096,0,691,0,4096,0,1601,0,4264,0,2346,0,4096,0,1461,0,4096,0,2043,0,4096,0,3213,0,4144,0,1322,0,4096,0,308,0,4096,0,0,0,4096,0,4828,0,4096,0,455,0,2187863086843344,2187863086866864
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f4e659bce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86558.0,0.0,131112.0,0.0,64,0x7f8dad7cee80,0,0,48,0,65536,65536,0,0,31297,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,43077,1676,0,48.0,372.0,0.0,262144.0,64,0x7f48ded7ce80,901152,232843,3386282,16384,25149701,0,48,0,112643,112643,4128378.0,2996471.0,7750.0,1188195.0,2036416.0,0.0,2987786.0,2676363.0,901144,254595,52202,60441,112643,158,3604576.0,820977.0,0.0,0.0,64,0x7f5e2cfc4e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fb21fe58e80,32768,0,0,0,16384,16384,393216,25318453,1079.0,512633.0,0.0,524288.0,1143932.0,32768.0,0,0,0,17461,87038.0,87038.0,0.0,87038.0,64,0x7fea92c9ae80,0.0,64,0x7fd78d976e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131310.0,0.0,474.0,131309.0,64,0x7f0dce858e80,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,64,0x7f468f6d0e80,1182,0,0,1356396,3701,0,0,1596032,719,0,0,1363877,1959,0,0,1508187,1531,0,0,1334922,1554,0,0,1382105,1382,0,0,1404342,4702,0,0,1711766,1503,0,0,1356199,1384,0,0,1337753,2625,0,0,1604973,1633,0,0,1482760,1437,0,0,1444568,1679,0,0,1467442,722,0,0,1252792,930,0,0,1460653,1315,0,0,1418333,1815,0,0,1385305,2646,0,0,1554377,1690,0,0,1431662,1870,0,0,1523971,2878,0,0,1520985,812,0,0,1319095,770,0,0,1260467,1579,0,0,1352077,1798,0,0,1501544,648,0,0,1246394,1739,0,0,1457116,1271,0,0,1284429,2548,0,0,1531659,1142,0,0,1432715,3454,0,0,1680022,64,0x7f06f910ee80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,60649.0,129018.0,64,0x7fdfc3e88e80,190714,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14464,30848,8598,2398,0,41285,262578.0,0.0,47.0,262531.0,64,0x7fe55b430e80,131072.0,131072.0,0.0,2585772.0,0.0,0.0,98644666.0,35097245.0,64,0x7fc701a42e80,251293,360448,163840,0,0,180224,114688,0,74325709.0,208450256.0,81919876.0,131072.0,0.0,598233.0,0,0,23838,75387.0,0.0,0.0,75387.0,64,0x7f3119578e80,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8360,4264,8360,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8203,4107,8203,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f842d1bae80,0,3296762,2700,2700,0,2800131,2754,2754,0,3014128,2680,2680,0,3125592,2738,2738,0,3162929,2696,2696,0,3159611,2740,2740,0,2986529,2712,2712,0,3138461,2723,2723,0,3140239,2678,2678,0,4016201,2760,2760,0,2859019,2726,2726,0,4060789,2756,2756,0,2946893,2690,2690,0,3346125,2736,2736,0,3003604,2688,2688,0,3295432,2726,2726,0,3259249,2692,2692,0,4757243,2736,2736,0,3115366,2660,2660,0,3808340,2730,2730,0,2797113,2690,2690,0,3251511,2780,2780,0,3001038,2681,2681,0,2791354,2702,2702,0,2991406,2688,2688,0,3162125,2756,2756,0,3109257,2703,2703,0,2505988,2728,2728,0,2660814,2692,2692,0,2884983,2756,2756,0,2901429,2684,2684,0,3219141,2726,2726,64,0x7f8530110e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,6401,44248,1576,131861.0,131072.0,0.0,87933.0,64,0x7f940eb4ae80,4096,0,1490,0,4096,0,604,0,4096,0,1885,0,4096,0,253,0,4096,0,11,0,4096,0,869,0,4144,0,572,0,4096,0,8461,0,4096,0,2547,0,4096,0,2849,0,4096,0,2097,0,4096,0,2679,0,4097,0,648,0,4096,0,0,0,4097,0,1673,0,4096,0,0,0,4096,0,2256,0,4096,0,3270,0,4096,0,561,0,4096,0,2688,0,4096,0,1516,0,4096,0,2349,0,4096,0,239,0,4264,0,1410,0,4096,0,551,0,4096,0,2397,0,4096,0,310,0,4144,0,76,0,4099,0,0,0,4096,0,959,0,4098,0,766,0,4096,0,452,0,2187863086979504,2187863086998544
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f4e659bce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86351.0,0.0,131112.0,0.0,64,0x7f8dad7cee80,0,0,48,0,65536,65536,0,0,30268,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,41565,1700,0,48.0,359.0,0.0,262144.0,64,0x7f48ded7ce80,367752,229861,3352454,16384,24242363,0,48,0,45968,45968,3738176.0,3006931.0,5264.0,1128558.0,2115342.0,0.0,2997268.0,2685623.0,367744,239661,45968,0,45968,0,1470976.0,799772.0,0.0,0.0,64,0x7f5e2cfc4e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fb21fe58e80,32768,0,0,0,16384,16384,393216,22727205,960.0,513893.0,0.0,524288.0,1049491.0,32768.0,0,0,0,13567,86780.0,86780.0,0.0,86780.0,64,0x7fea92c9ae80,0.0,64,0x7fd78d976e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131295.0,0.0,444.0,131294.0,64,0x7f0dce858e80,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,64,0x7f468f6d0e80,1310,0,0,1408633,2314,0,0,1474929,2181,0,0,1515275,2009,0,0,1469597,997,0,0,1294023,1589,0,0,1423479,1853,0,0,1451504,1918,0,0,1499084,774,0,0,1320407,1766,0,0,1448322,3102,0,0,1572650,2095,0,0,1502786,1685,0,0,1395911,1787,0,0,1440739,1678,0,0,1413744,2752,0,0,1609026,2849,0,0,1533368,1237,0,0,1342248,2846,0,0,1558478,3207,0,0,1569433,2892,0,0,1556941,2277,0,0,1494411,2814,0,0,1564909,4039,0,0,1640045,1338,0,0,1299289,1110,0,0,1324259,1953,0,0,1439185,3874,0,0,1621768,1617,0,0,1497262,4515,0,0,1719101,1570,0,0,1447537,4077,0,0,1658063,64,0x7f06f910ee80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,70782.0,142056.0,64,0x7fdfc3e88e80,192865,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13718,30102,8437,2402,0,41253,262582.0,0.0,47.0,262535.0,64,0x7fe55b430e80,131072.0,131072.0,0.0,2540173.0,0.0,0.0,129657272.0,46319629.0,64,0x7fc701a42e80,1191650,360448,163840,0,0,180224,114688,0,70322285.0,193567953.0,75673930.0,131072.0,0.0,584751.0,0,0,25130,75046.0,0.0,0.0,75046.0,64,0x7f3119578e80,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8360,4264,8360,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8194,4098,8194,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f842d1bae80,0,4001358,2730,2730,0,2376511,2714,2714,0,3561771,2708,2708,0,3491281,2757,2757,0,3341479,2692,2692,0,2875055,2744,2744,0,2758286,2732,2732,0,3132213,2712,2712,0,2992028,2714,2714,0,4159175,2700,2700,0,3014378,2748,2748,0,4094375,2752,2752,0,2742996,2706,2706,0,2910611,2728,2728,0,3206642,2710,2710,0,3351558,2720,2720,0,2941077,2690,2690,0,3805700,2688,2688,0,3421874,2718,2718,0,4447243,2720,2720,0,2885785,2711,2711,0,3003164,2753,2753,0,3667575,2706,2706,0,2949001,2726,2726,0,2603147,2700,2700,0,2978629,2738,2738,0,2644933,2734,2734,0,2719145,2728,2728,0,3299129,2697,2697,0,2829861,2699,2699,0,3928716,2740,2740,0,2778257,2708,2708,64,0x7f8530110e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3296,39481,0,131412.0,131072.0,0.0,86838.0,64,0x7f940eb4ae80,4096,0,4211,0,4096,0,790,0,4096,0,1715,0,4096,0,1732,0,4096,0,3056,0,4096,0,6473,0,4144,0,871,0,4096,0,628,0,4096,0,141,0,4096,0,3897,0,4096,0,853,0,4096,0,4587,0,4097,0,2237,0,4096,0,1784,0,4097,0,5499,0,4096,0,2290,0,4096,0,2588,0,4096,0,2954,0,4096,0,5043,0,4096,0,3383,0,4096,0,1282,0,4096,0,2519,0,4096,0,688,0,4264,0,210,0,4096,0,5,0,4096,0,968,0,4096,0,4673,0,4144,0,160,0,4099,0,567,0,4096,0,349,0,4098,0,5281,0,4096,0,4220,0,2187863087020944,2187863087039824
|
||||
@@ -0,0 +1,2 @@
|
||||
workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
|
||||
device_filter,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:46:13 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1
|
||||
|
@@ -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]",2,0,0,2867400,2867400,1048576,256,0,0,8,8,16,64,0x0,0x7f1016c04e80,2187863086818021,2187863086843344,2187863086866864,2187863086880578
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2867400,2867400,1048576,256,0,0,8,8,16,64,0x0,0x7f1016c04e80,2187863086879366,2187863086979504,2187863086998544,2187863086999782
|
||||
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2867400,2867400,1048576,256,0,0,8,8,16,64,0x0,0x7f1016c04e80,2187863087011163,2187863087020944,2187863087039824,2187863087040899
|
||||
|
@@ -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) ",2,0,0,181827,181827,1048576,256,0,0,8,8,16,64,0x0,0x7f07663bae80,47978,47978,16384,65536,14494,1861536,6402045414567,6401146042762,6401146066762,6402053157530
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,181827,181827,1048576,256,0,0,8,8,16,64,0x0,0x7f07663bae80,44012,44012,16384,65536,8160,1048580,6402053180624,6401146167882,6401146186922,6402053517320
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,181827,181827,1048576,256,0,0,8,8,16,64,0x0,0x7f07663bae80,43085,43085,16384,65536,8145,1048584,6402053549281,6401146207402,6401146226282,6402053732076
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2858631,2858631,1048576,256,0,0,8,8,16,64,0x0,0x7f306d022e80,48693,48693,16384,65536,14587,1861268,2187837651454006,2187843682406959,2187843682431279,2187837659153650
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2858631,2858631,1048576,256,0,0,8,8,16,64,0x0,0x7f306d022e80,43450,43450,16384,65536,8185,1048576,2187837659175581,2187843682524719,2187843682543599,2187837659498637
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2858631,2858631,1048576,256,0,0,8,8,16,64,0x0,0x7f306d022e80,42429,42429,16384,65536,8118,1048580,2187837659530768,2187843682565519,2187843682585039,2187837659713381
|
||||
|
@@ -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) ",2,0,0,178576,178576,1048576,256,0,0,8,8,16,64,0x0,0x7f74bd5b6e80,0,0,0,6386463651065,6401146042762,6401146066762,6386471177349
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,178576,178576,1048576,256,0,0,8,8,16,64,0x0,0x7f74bd5b6e80,0,0,0,6386471197998,6401146167882,6401146186922,6386471552869
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,178576,178576,1048576,256,0,0,8,8,16,64,0x0,0x7f74bd5b6e80,0,0,0,6386471582034,6401146207402,6401146226282,6386471757676
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2862637,2862637,1048576,256,0,0,8,8,16,64,0x0,0x7f5be8850e80,0,0,0,2187848852549207,2187843682406959,2187843682431279,2187848859975488
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2862637,2862637,1048576,256,0,0,8,8,16,64,0x0,0x7f5be8850e80,0,0,0,2187848859994684,2187843682524719,2187843682543599,2187848860303414
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2862637,2862637,1048576,256,0,0,8,8,16,64,0x0,0x7f5be8850e80,0,0,0,2187848860332038,2187843682565519,2187843682585039,2187848860506154
|
||||
|
@@ -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) ",2,0,0,182838,182838,1048576,256,0,0,8,8,16,64,0x0,0x7faf17528e80,65536,221118,28351800,6406815203658,6401146042762,6401146066762,6406822956018
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,182838,182838,1048576,256,0,0,8,8,16,64,0x0,0x7faf17528e80,65536,203702,26080032,6406822974133,6401146167882,6401146186922,6406823418142
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,182838,182838,1048576,256,0,0,8,8,16,64,0x0,0x7faf17528e80,65536,203144,25999920,6406823446055,6401146207402,6401146226282,6406823622218
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2861181,2861181,1048576,256,0,0,8,8,16,64,0x0,0x7f4afbf56e80,65536,210560,26916328,2187844811633072,2187843682406959,2187843682431279,2187844819158530
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2861181,2861181,1048576,256,0,0,8,8,16,64,0x0,0x7f4afbf56e80,65536,180192,23099952,2187844819178597,2187843682524719,2187843682543599,2187844819476596
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2861181,2861181,1048576,256,0,0,8,8,16,64,0x0,0x7f4afbf56e80,65536,192032,24611128,2187844819505521,2187843682565519,2187843682585039,2187844819677133
|
||||
|
@@ -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) ",2,0,0,178778,178778,1048576,256,0,0,8,8,16,64,0x0,0x7fc7e6412e80,32768,659106,84360532,6387368867286,6401146042762,6401146066762,6387376507826
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,178778,178778,1048576,256,0,0,8,8,16,64,0x0,0x7fc7e6412e80,32768,653457,83634844,6387376528044,6401146167882,6401146186922,6387376826258
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,178778,178778,1048576,256,0,0,8,8,16,64,0x0,0x7fc7e6412e80,32768,670775,85843888,6387376854291,6401146207402,6401146226282,6387377024353
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2859725,2859725,1048576,256,0,0,8,8,16,64,0x0,0x7f77365b0e80,32768,648628,83041940,2187840584839972,2187843682406959,2187843682431279,2187840592444006
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2859725,2859725,1048576,256,0,0,8,8,16,64,0x0,0x7f77365b0e80,32768,665455,85189652,2187840592464465,2187843682524719,2187843682543599,2187840592804623
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2859725,2859725,1048576,256,0,0,8,8,16,64,0x0,0x7f77365b0e80,32768,630264,80689312,2187840592833738,2187843682565519,2187843682585039,2187840593022011
|
||||
|
@@ -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) ",2,0,0,180006,180006,1048576,256,0,0,8,8,16,64,0x0,0x7ff7b376ee80,49008,49008,17099,392072,16384,25315374,242746,0,101780108,6393202548827,6401146042762,6401146066762,6393210198774
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,180006,180006,1048576,256,0,0,8,8,16,64,0x0,0x7ff7b376ee80,42135,42135,12945,337088,16384,24545355,232922,0,98697060,6393210228730,6401146167882,6401146186922,6393210558173
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,180006,180006,1048576,256,0,0,8,8,16,64,0x0,0x7ff7b376ee80,41623,41623,13083,332992,16384,24635089,231002,0,99051052,6393210596947,6401146207402,6401146226282,6393210786946
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2861545,2861545,1048576,256,0,0,8,8,16,64,0x0,0x7f66b3458e80,49547,49547,16868,396384,16384,26740947,242792,0,107460160,2187845706739501,2187843682406959,2187843682431279,2187845714403057
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2861545,2861545,1048576,256,0,0,8,8,16,64,0x0,0x7f66b3458e80,43543,43543,13929,348352,16384,25132807,235648,0,101028984,2187845714431621,2187843682524719,2187843682543599,2187845714748586
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2861545,2861545,1048576,256,0,0,8,8,16,64,0x0,0x7f66b3458e80,43359,43359,14054,346880,16384,24431177,229443,0,98220436,2187845714786918,2187843682565519,2187843682585039,2187845714981864
|
||||
|
@@ -1,4 +0,0 @@
|
||||
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
|
||||
|
@@ -1,4 +1,4 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_1,obj_1,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_2,obj_2,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_3,obj_3,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],wave_size_4,obj_4,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sLine truncated
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8d2f830e80,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,0,49587,0,0,64,0x7f644a954e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87134.0,43938.0,131111.0,0.0,64,0x7f2b60eb0e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131344.0,0.0,536.0,131343.0,64,0x7f0f4a34ae80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8432,4336,8432,64,0x7f3046420e80,131072.0,131072.0,0.0,2395494.0,0.0,0.0,120528457.0,58922799.0,64,0x7f4f4b326e80,4096,0,0,0,4096,0,78,0,4099,0,92,0,4096,0,107,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,164,0,4096,0,465,0,4096,0,73,0,4096,0,1130,0,4096,0,0,0,4096,0,540,0,4096,0,0,0,4096,0,0,0,4096,0,8945,0,4096,0,3,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,498,0,4097,0,1091,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4144,0,1477,0,4096,0,0,0,4144,0,32,0,4284,0,497,0,64,0x7fecb0d5ce80,376904,230792,3357903,16384,24760041,144,48,0,47112,47112,3814019.0,2976853.0,5738.0,985388.0,2192342.0,0.0,2967674.0,2658473.0,375583,240738,47112,0,47112,0,1507584.0,975483.0,0.0,0.0,64,0x7fa07fd82e80,0.0,64,0x7fdf3cd2ae80,190442,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14624,31008,9370,588,0,45997,262548.0,0.0,188.0,262360.0,64,0x7fb38df68e80,0,0,192,0,65536,64516,48,1237,30682,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,513,46290,1694,0,48.0,374.0,0.0,262288.0,64,0x7f127d5a6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47172,0,131586.0,131072.0,0.0,131104.0,64,0x7ff1b2b5ee80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f02303c8e80,2761247,360448,163840,0,0,180224,114688,0,62712797.0,166197421.0,65940938.0,131072.0,0.0,809165.0,0,0,27263,129275.0,0.0,0.0,129275.0,64,0x7f6fac218e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,46034.0,117861.0,64,0x7f772616ee80,32768,0,0,0,16384,16384,393216,22041595,960.0,513895.0,0.0,524288.0,1139463.0,32768.0,0,0,0,16845,131072.0,131072.0,0.0,131072.0,64,0x7ff8e5aa2e80,0,3390202,4096,4096,0,3030998,4096,4096,0,3199857,4096,4096,0,2899960,4096,4096,0,3249414,4096,4096,0,3140864,4096,4096,0,3182508,4096,4096,0,3420545,4096,4096,0,3369133,4096,4096,0,3127958,4096,4096,0,3562084,4096,4096,0,4725832,4096,4096,0,3264542,4096,4096,0,3046568,4096,4096,0,3119683,4096,4096,0,2197731,4096,4096,0,3318429,4096,4096,0,3410159,4096,4096,0,3308436,4096,4096,0,3031551,4096,4096,0,3053087,4096,4096,0,3004147,4096,4096,0,3427244,4096,4096,0,2541016,4096,4096,0,2657709,4096,4096,0,3272631,4096,4096,0,3134811,4096,4096,0,2953171,4096,4096,0,3141282,4096,4096,0,3068986,4096,4096,0,3613602,4096,4096,0,2498301,4096,4096,64,0x7f399fc26e80,2511,0,0,1845207,2711,0,0,1931071,4658,0,0,2096105,1902,0,0,1809377,2599,0,0,1898147,552,0,0,1553694,3710,0,0,2049510,1978,0,0,1822040,2864,0,0,1893049,4732,0,0,2143090,1506,0,0,1788296,2356,0,0,1878544,3357,0,0,1941504,1504,0,0,1742355,979,0,0,1698673,2117,0,0,1799752,2628,0,0,1841567,1473,0,0,1735184,3412,0,0,1991946,3915,0,0,2002789,2692,0,0,1875124,978,0,0,1666762,5266,0,0,2124752,3676,0,0,1982064,3091,0,0,1884284,525,0,0,1613866,3723,0,0,1942532,2528,0,0,1825903,3073,0,0,1948604,1468,0,0,1765924,3170,0,0,1961447,4769,0,0,2069353,6401146042762,6401146066762
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8d2f830e80,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,0,43503,0,0,64,0x7f644a954e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86942.0,0.0,131112.0,0.0,64,0x7f2b60eb0e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131210.0,0.0,274.0,131209.0,64,0x7f0f4a34ae80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8431,4335,8431,64,0x7f3046420e80,131072.0,131072.0,0.0,2667257.0,0.0,0.0,119196319.0,59225115.0,64,0x7f4f4b326e80,4096,0,2591,0,4096,0,43,0,4096,0,18,0,4096,0,480,0,4096,0,2247,0,4096,0,0,0,4096,0,0,0,4096,0,189,0,4096,0,2031,0,4096,0,2817,0,4096,0,0,0,4096,0,900,0,4096,0,1395,0,4096,0,237,0,4096,0,297,0,4097,0,1117,0,4096,0,660,0,4096,0,3283,0,4096,0,0,0,4099,0,875,0,4096,0,1658,0,4096,0,684,0,4096,0,0,0,4097,0,0,0,4096,0,2017,0,4096,0,1741,0,4096,0,0,0,4096,0,72,0,4146,0,2462,0,4096,0,1131,0,4144,0,25,0,4380,0,4417,0,64,0x7fecb0d5ce80,419656,278055,3935784,16384,25396552,0,48,0,52456,52456,4455405.0,3611224.0,5448.0,1173370.0,2546417.0,0.0,3602470.0,3296128.0,419648,286455,52456,0,52456,1044,1678592.0,985135.0,1.0,0.0,64,0x7fa07fd82e80,0.0,64,0x7fdf3cd2ae80,225120,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,15120,31504,8587,3265,0,41265,262452.0,0.0,47.0,262405.0,64,0x7fb38df68e80,0,0,48,0,65536,65536,0,0,30644,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42370,1710,0,48.0,360.0,0.0,262144.0,64,0x7f127d5a6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,5046,43509,1088,131544.0,131072.0,0.0,86787.0,64,0x7ff1b2b5ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f02303c8e80,231746,360448,163840,0,0,180224,114688,0,71282283.0,196480494.0,73304574.0,131072.0,0.0,600606.0,0,0,23735,65455.0,0.0,0.0,65455.0,64,0x7f6fac218e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,34860.0,104541.0,64,0x7f772616ee80,32768,0,0,0,16384,16384,393216,21576120,960.0,513874.0,0.0,524288.0,1117900.0,32768.0,0,0,0,13633,87306.0,87306.0,0.0,87306.0,64,0x7ff8e5aa2e80,0,3182435,2748,2748,0,2846843,2712,2712,0,3270560,2672,2672,0,3370231,2731,2731,0,3319924,2669,2669,0,3222460,2744,2744,0,3457492,2720,2720,0,4095239,2733,2733,0,3439885,2708,2708,0,3520704,2690,2690,0,3563263,2724,2724,0,4747701,2726,2726,0,3201333,2674,2674,0,3394553,2716,2716,0,3411636,2704,2704,0,3140342,2726,2726,0,3677889,2708,2708,0,3342911,2714,2714,0,3950057,2736,2736,0,3631324,2728,2728,0,3361026,2679,2679,0,3623698,2762,2762,0,3983237,2738,2738,0,3360600,2712,2712,0,3286797,2684,2684,0,3472804,2732,2732,0,3621270,2726,2726,0,3675557,2730,2730,0,3218851,2708,2708,0,2643686,2725,2725,0,3394416,2720,2720,0,3344836,2732,2732,64,0x7f399fc26e80,2308,0,0,1453175,950,0,0,1344904,2068,0,0,1454846,3164,0,0,1557269,2190,0,0,1548144,153,0,0,1191643,3461,0,0,1652838,958,0,0,1290631,868,0,0,1353851,609,0,0,1317645,1858,0,0,1443457,2397,0,0,1487712,3980,0,0,1629665,4143,0,0,1669882,629,0,0,1231148,7582,0,0,1932016,2543,0,0,1551398,2407,0,0,1486532,1601,0,0,1366745,1637,0,0,1449874,4451,0,0,1632486,3069,0,0,1574008,2691,0,0,1465045,3460,0,0,1567805,4203,0,0,1699639,512,0,0,1195455,1275,0,0,1458267,1954,0,0,1479178,2049,0,0,1503491,1285,0,0,1354941,690,0,0,1290003,4214,0,0,1656569,6401146167882,6401146186922
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8d2f830e80,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,64,0x7f644a954e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86888.0,0.0,131112.0,0.0,64,0x7f2b60eb0e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131231.0,0.0,316.0,131230.0,64,0x7f0f4a34ae80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8432,4336,8432,64,0x7f3046420e80,131072.0,131072.0,0.0,2599947.0,0.0,0.0,116939011.0,45174328.0,64,0x7f4f4b326e80,4096,0,2763,0,4096,0,0,0,4096,0,1147,0,4096,0,0,0,4096,0,2838,0,4096,0,73,0,4096,0,881,0,4096,0,397,0,4096,0,1306,0,4096,0,987,0,4096,0,1237,0,4096,0,325,0,4096,0,2033,0,4096,0,1345,0,4096,0,293,0,4097,0,0,0,4096,0,1954,0,4096,0,1865,0,4096,0,1496,0,4099,0,285,0,4096,0,1423,0,4096,0,1418,0,4096,0,1487,0,4097,0,0,0,4096,0,171,0,4096,0,1977,0,4096,0,594,0,4096,0,319,0,4146,0,0,0,4096,0,2263,0,4144,0,884,0,4373,0,3262,0,64,0x7fecb0d5ce80,340944,229788,3312307,16384,23742902,0,48,0,42617,42617,3736001.0,3016003.0,5658.0,1045666.0,2227860.0,0.0,3006820.0,2696975.0,340936,239245,42617,0,42617,0,1363744.0,837264.0,0.0,0.0,64,0x7fa07fd82e80,0.0,64,0x7fdf3cd2ae80,186336,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12999,29383,8585,3731,0,39879,262474.0,0.0,47.0,262427.0,64,0x7fb38df68e80,0,0,48,0,65536,65536,0,0,30652,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41950,1676,0,48.0,341.0,0.0,262144.0,64,0x7f127d5a6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3745,37920,0,131395.0,131072.0,0.0,86456.0,64,0x7ff1b2b5ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f02303c8e80,1446255,360448,163840,0,0,180224,114688,0,68875193.0,192103698.0,81403584.0,131072.0,0.0,797205.0,0,0,25888,107142.0,0.0,0.0,107142.0,64,0x7f6fac218e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,44536.0,114067.0,64,0x7f772616ee80,32768,0,0,0,16384,16384,393216,22220888,960.0,513849.0,0.0,524288.0,1247745.0,32768.0,0,0,0,15202,86695.0,86695.0,0.0,86695.0,64,0x7ff8e5aa2e80,0,3496500,2720,2720,0,3656242,2725,2725,0,3170717,2707,2707,0,3169735,2742,2742,0,3253209,2744,2744,0,3890092,2737,2737,0,3069789,2716,2716,0,3595758,2736,2736,0,3015176,2724,2724,0,3687216,2756,2756,0,3106520,2756,2756,0,4237156,2768,2768,0,3105540,2746,2746,0,3358141,2744,2744,0,3218054,2748,2748,0,3078502,2700,2700,0,2877904,2739,2739,0,4015336,2724,2724,0,3138255,2711,2711,0,3700361,2760,2760,0,3405314,2710,2710,0,3221275,2749,2749,0,3450631,2728,2728,0,2844359,2717,2717,0,2959011,2716,2716,0,3542425,2752,2752,0,2866822,2739,2739,0,2599880,2757,2757,0,3369847,2731,2731,0,3481744,2722,2722,0,2751536,2728,2728,0,3157248,2757,2757,64,0x7f399fc26e80,1797,0,0,1360084,2530,0,0,1534985,1156,0,0,1319985,4323,0,0,1695977,2177,0,0,1419788,1030,0,0,1353190,3272,0,0,1687855,2304,0,0,1499520,65,0,0,1170703,1085,0,0,1322718,763,0,0,1270235,3255,0,0,1621990,1263,0,0,1274922,1361,0,0,1339329,1362,0,0,1416040,3535,0,0,1605487,1309,0,0,1279842,1190,0,0,1260519,3864,0,0,1624298,3192,0,0,1568979,572,0,0,1298418,1787,0,0,1438456,3539,0,0,1656845,2282,0,0,1552154,658,0,0,1291293,1066,0,0,1335287,2735,0,0,1548004,3480,0,0,1569792,1332,0,0,1300340,1891,0,0,1385489,2664,0,0,1592361,3400,0,0,1551854,6401146207402,6401146226282
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_1,obj_1,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],wave_size_2,obj_2,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_3,obj_3,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_4,obj_4,SQ_WAIT_INST_Line truncated
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f0f15e9ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,83850.0,157724.0,64,0x7f78aacc2e80,4096,0,1809,0,4096,0,1486,0,4096,0,10,0,4099,0,0,0,4096,0,2430,0,4096,0,2858,0,4096,0,14,0,4096,0,213,0,4096,0,1805,0,4096,0,1016,0,4096,0,2282,0,4096,0,424,0,4096,0,1546,0,4096,0,2367,0,4097,0,3039,0,4096,0,222,0,4096,0,603,0,4096,0,2979,0,4096,0,0,0,4096,0,851,0,4096,0,0,0,4368,0,5823,0,4096,0,756,0,4096,0,470,0,4096,0,2239,0,4144,0,1429,0,4096,0,117,0,4144,0,16,0,4096,0,793,0,4096,0,1569,0,4096,0,0,0,4096,0,106,0,64,0x7f3e903f6e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131447.0,0.0,742.0,131446.0,64,0x7f5207bbae80,383472,230437,3361985,16384,24810359,144,48,0,47933,47933,3808992.0,2988866.0,7672.0,1199121.0,2121014.0,0.0,2979905.0,2668348.0,382015,240366,47933,0,47933,0,1533856.0,952676.0,0.0,0.0,64,0x7fe3613dce80,1993346,360448,163840,0,0,180224,114688,0,72137845.0,204245558.0,80040364.0,131072.0,0.0,600159.0,0,0,26531,76707.0,0.0,0.0,76707.0,64,0x7fdc9c4a8e80,0,3604738,4096,4096,0,4585940,4096,4096,0,4267033,4096,4096,0,3446747,4096,4096,0,3793604,4096,4096,0,3120752,4096,4096,0,4865543,4096,4096,0,4041474,4096,4096,0,3471550,4096,4096,0,3791145,4096,4096,0,3977519,4096,4096,0,4599172,4096,4096,0,3296690,4096,4096,0,3568287,4096,4096,0,4574830,4096,4096,0,3915129,4096,4096,0,3511945,4096,4096,0,4098794,4096,4096,0,4971185,4096,4096,0,4701434,4096,4096,0,3999737,4096,4096,0,4198270,4096,4096,0,4453092,4096,4096,0,3251912,4096,4096,0,3352648,4096,4096,0,3256301,4096,4096,0,4508553,4096,4096,0,3473699,4096,4096,0,4743581,4096,4096,0,3297993,4096,4096,0,3332103,4096,4096,0,4891791,4096,4096,64,0x7fc1c877ce80,131072.0,131072.0,0.0,2540052.0,0.0,0.0,122645628.0,58889530.0,64,0x7ff6a8160e80,0.0,64,0x7fbf7ebc0e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86702.0,44370.0,131112.0,0.0,64,0x7f4ea442ce80,4693,0,0,2160231,3989,0,0,2077401,5526,0,0,2200155,3383,0,0,1904609,2545,0,0,1888302,728,0,0,1576011,2322,0,0,1910602,2010,0,0,1851259,5416,0,0,2299593,2128,0,0,1792462,4163,0,0,2034097,565,0,0,1589958,5431,0,0,2229071,2950,0,0,1928414,1016,0,0,1660636,4404,0,0,2088951,2304,0,0,1867755,702,0,0,1561880,5809,0,0,2158254,1529,0,0,1659923,2766,0,0,1874448,843,0,0,1607340,4223,0,0,2034999,4053,0,0,2079986,1251,0,0,1782637,1027,0,0,1645981,3675,0,0,1962876,2300,0,0,1772139,6370,0,0,2185656,1696,0,0,1745224,3911,0,0,1965501,1878,0,0,1773081,64,0x7fc40ea66e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,64,0x7f54e5e90e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8196,4100,8196,64,0x7facf8386e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46766,0,131517.0,131072.0,0.0,131104.0,64,0x7f79b459ee80,32768,0,0,0,16384,16384,393216,22590402,960.0,513877.0,0.0,524288.0,1064724.0,32768.0,0,0,0,17622,131072.0,131072.0,0.0,131072.0,64,0x7f5e4f946e80,0,0,192,0,65536,64514,48,1331,32988,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,49360,1742,0,48.0,533.0,0.0,262288.0,64,0x7f0e7a4a8e80,190320,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14382,30766,10004,550,0,46610,262603.0,0.0,188.0,262415.0,64,0x7f191a560e80,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,2187843682406959,2187843682431279
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f0f15e9ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,64351.0,133143.0,64,0x7f78aacc2e80,4096,0,995,0,4096,0,778,0,4096,0,1730,0,4096,0,463,0,4096,0,1002,0,4096,0,1325,0,4096,0,1025,0,4096,0,2145,0,4098,0,1434,0,4096,0,1246,0,4097,0,295,0,4096,0,2005,0,4096,0,1368,0,4096,0,2235,0,4100,0,1892,0,4096,0,588,0,4096,0,2598,0,4096,0,3120,0,4096,0,7199,0,4096,0,1483,0,4096,0,402,0,4338,0,1599,0,4096,0,2888,0,4096,0,773,0,4096,0,982,0,4144,0,515,0,4096,0,2914,0,4144,0,929,0,4096,0,932,0,4096,0,4289,0,4096,0,433,0,4096,0,653,0,64,0x7f3e903f6e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131476.0,0.0,804.0,131474.0,64,0x7f5207bbae80,404752,260382,3813812,16384,28132994,0,96,0,50593,50593,4195766.0,3408194.0,3545.0,1276530.0,2465194.0,0.0,3389534.0,3074838.0,404744,270167,50593,0,50593,1091,1618976.0,906683.0,1.0,0.0,64,0x7fe3613dce80,1594799,360448,163840,0,0,180224,114688,0,73990968.0,195542709.0,78183566.0,131072.0,0.0,604206.0,0,0,26382,65878.0,0.0,0.0,65878.0,64,0x7fdc9c4a8e80,0,4051112,2676,2676,0,4041108,2720,2720,0,3478570,2688,2688,0,5111679,2720,2720,0,3644707,2669,2669,0,3532686,2728,2728,0,4622818,2716,2716,0,4395017,2718,2718,0,3081633,2676,2676,0,4668825,2676,2676,0,4266747,2732,2732,0,4015397,2744,2744,0,3736606,2686,2686,0,3321874,2693,2693,0,4316212,2696,2696,0,4227796,2728,2728,0,2983811,2676,2676,0,4197024,2714,2714,0,4567990,2688,2688,0,4184753,2728,2728,0,2870532,2676,2676,0,3761157,2734,2734,0,3584429,2671,2671,0,3420079,2702,2702,0,2788547,2668,2668,0,4223034,2708,2708,0,3967979,2718,2718,0,4150394,2724,2724,0,3602395,2668,2668,0,3457494,2706,2706,0,3468765,2720,2720,0,5519755,2698,2698,64,0x7fc1c877ce80,131072.0,131072.0,0.0,2631333.0,0.0,0.0,103319261.0,57890611.0,64,0x7ff6a8160e80,0.0,64,0x7fbf7ebc0e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86718.0,0.0,131113.0,0.0,64,0x7f4ea442ce80,1453,0,0,1403646,2083,0,0,1462053,2678,0,0,1501103,4270,0,0,1738551,1047,0,0,1327384,2483,0,0,1572061,1484,0,0,1422490,3218,0,0,1744533,1559,0,0,1377158,2524,0,0,1553708,312,0,0,1188208,2184,0,0,1637447,771,0,0,1267928,5124,0,0,1805083,515,0,0,1216849,4619,0,0,1736502,1825,0,0,1450823,1039,0,0,1353757,2896,0,0,1554454,948,0,0,1319921,197,0,0,1220378,2809,0,0,1583533,1614,0,0,1463415,4330,0,0,1700620,617,0,0,1320511,1222,0,0,1415643,3199,0,0,1641414,5535,0,0,1728794,1740,0,0,1400839,4621,0,0,1681592,1056,0,0,1245423,2705,0,0,1608985,64,0x7fc40ea66e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f54e5e90e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8194,4098,8194,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,64,0x7facf8386e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3678,39227,0,131385.0,131072.0,0.0,86647.0,64,0x7f79b459ee80,32768,0,0,0,16384,16384,393216,22546290,960.0,513895.0,0.0,524288.0,951731.0,32768.0,0,0,0,13296,86618.0,86618.0,0.0,86618.0,64,0x7f5e4f946e80,0,0,48,0,65536,65536,0,0,32447,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,45684,1736,0,48.0,549.0,0.0,262144.0,64,0x7f0e7a4a8e80,595845,0,0,65536,62560,96,2880,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14097,30481,26786,6313,0,43963,262913.0,0.0,94.0,262819.0,64,0x7f191a560e80,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,2187843682524719,2187843682543599
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f0f15e9ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,36142.0,100417.0,64,0x7f78aacc2e80,4096,0,2887,0,4096,0,1896,0,4096,0,1355,0,4096,0,674,0,4096,0,2332,0,4096,0,756,0,4096,0,1178,0,4096,0,62,0,4098,0,2595,0,4096,0,771,0,4097,0,1955,0,4096,0,1779,0,4096,0,1285,0,4096,0,1329,0,4100,0,950,0,4096,0,28,0,4096,0,1568,0,4096,0,1955,0,4096,0,3226,0,4096,0,898,0,4096,0,783,0,4366,0,5550,0,4096,0,621,0,4096,0,23,0,4096,0,1117,0,4144,0,2705,0,4096,0,957,0,4144,0,568,0,4096,0,1023,0,4096,0,652,0,4096,0,2869,0,4096,0,1687,0,64,0x7f3e903f6e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131392.0,0.0,638.0,131391.0,64,0x7f5207bbae80,336416,226914,3317645,16384,24684994,0,48,0,42051,42051,3693612.0,3036934.0,5739.0,963065.0,2103864.0,0.0,3027948.0,2716876.0,336408,236451,42051,0,42051,0,1345632.0,791443.0,0.0,0.0,64,0x7fe3613dce80,1365751,360448,163840,0,0,180224,114688,0,72176233.0,198948855.0,75443586.0,131072.0,0.0,645324.0,0,0,25546,63900.0,0.0,0.0,63900.0,64,0x7fdc9c4a8e80,0,2869900,2702,2702,0,2984662,2700,2700,0,3143822,2700,2700,0,3199680,2726,2726,0,2477745,2712,2712,0,3062864,2696,2696,0,3282513,2760,2760,0,3338896,2728,2728,0,2819761,2688,2688,0,2685114,2666,2666,0,3462555,2732,2732,0,3651008,2726,2726,0,2720493,2712,2712,0,2861909,2680,2680,0,2899788,2718,2718,0,3190254,2722,2722,0,2731290,2727,2727,0,3244031,2672,2672,0,4624944,2717,2717,0,3659512,2734,2734,0,2756363,2736,2736,0,4379239,2722,2722,0,5480708,2697,2697,0,2889464,2714,2714,0,2832733,2706,2706,0,3000202,2682,2682,0,4560562,2740,2740,0,2804984,2712,2712,0,2573922,2708,2708,0,2666828,2700,2700,0,3099584,2716,2716,0,4687973,2722,2722,64,0x7fc1c877ce80,131072.0,131072.0,0.0,2608383.0,0.0,0.0,129833075.0,46556315.0,64,0x7ff6a8160e80,0.0,64,0x7fbf7ebc0e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86733.0,0.0,131113.0,0.0,64,0x7f4ea442ce80,164,0,0,1066949,321,0,0,1130244,2027,0,0,1341051,400,0,0,1174658,228,0,0,1133467,557,0,0,1019064,1184,0,0,1284703,1458,0,0,1354504,449,0,0,1216061,333,0,0,1185097,2153,0,0,1405812,1424,0,0,1378677,112,0,0,1120892,194,0,0,1113229,23,0,0,995380,740,0,0,1236552,429,0,0,1247984,5289,0,0,1836573,1630,0,0,1340395,484,0,0,1179542,368,0,0,1250834,923,0,0,1185399,547,0,0,1223846,716,0,0,1213368,895,0,0,1317959,0,0,0,1081893,3451,0,0,1673173,247,0,0,1163334,52,0,0,1117875,142,0,0,1109344,498,0,0,1245936,524,0,0,1132521,64,0x7fc40ea66e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f54e5e90e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8194,4098,8194,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8200,4104,8200,64,0x7facf8386e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3793,38142,0,131374.0,131072.0,0.0,86597.0,64,0x7f79b459ee80,32768,0,0,0,16384,16384,393216,21289704,960.0,513860.0,0.0,524288.0,1248083.0,32768.0,0,0,0,14119,87763.0,87763.0,0.0,87763.0,64,0x7f5e4f946e80,0,0,48,0,65536,65536,0,0,31679,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,43126,1692,0,48.0,465.0,0.0,262144.0,64,0x7f0e7a4a8e80,176261,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13445,29829,8488,2558,0,41725,262523.0,0.0,47.0,262476.0,64,0x7f191a560e80,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,2187843682565519,2187843682585039
|
||||
@@ -1,2 +1,2 @@
|
||||
workload_name,command,host_name,host_cpu,sbios,host_distro,host_kernel,host_rocmver,date,gpu_soc,vbios,numSE,numCU,numSIMD,waveSize,maxWavesPerCU,maxWorkgroupSize,L1,L2,sclk,mclk,cur_sclk,cur_mclk,L2Banks,totalL2Banks,LDSBanks,name,numSQC,numPipes,hbmBW,compute_partition,memory_partition,ip_blocks
|
||||
device_inv_int,./tests/vcopy -n 1048576 -b 256 -i 3,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_64,5.7.1-98,Mon Feb 19 13:25:16 2024 (CST),gfx908,113-D3431401-100,8,120,4,64,40,1024,16,8192,1502,1200,1502,1200,32,32,32,MI100,30,4,1200,,,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
|
||||
workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
|
||||
device_inv_int,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:45:48 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1
|
||||
|
@@ -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) ",2,0,0,181625,181625,1048576,256,0,0,8,8,16,64,0x0,0x7f124867ce80,6401146016248,6401146042762,6401146066762,6401146079037
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,181625,181625,1048576,256,0,0,8,8,16,64,0x0,0x7f124867ce80,6401146079558,6401146167882,6401146186922,6401146188174
|
||||
2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,181625,181625,1048576,256,0,0,8,8,16,64,0x0,0x7f124867ce80,6401146198824,6401146207402,6401146226282,6401146227678
|
||||
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2860817,2860817,1048576,256,0,0,8,8,16,64,0x0,0x7fd32b2cce80,2187843682380846,2187843682406959,2187843682431279,2187843682443404
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2860817,2860817,1048576,256,0,0,8,8,16,64,0x0,0x7fd32b2cce80,2187843682444325,2187843682524719,2187843682543599,2187843682544844
|
||||
2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2860817,2860817,1048576,256,0,0,8,8,16,64,0x0,0x7fd32b2cce80,2187843682556025,2187843682565519,2187843682585039,2187843682586092
|
||||
|
@@ -1,2 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,103052,103052,1048576,256,0,0,8,8,16,64,0x0,0x7fe965116e80,47544,47544,16384,65536,13103,1693740,4876162203440,4881310843226,4881310867386,4876170172288
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2847318,2847318,1048576,256,0,0,8,8,16,64,0x0,0x7f6648898e80,47274,47274,16384,65536,13112,1663272,2187803528527851,2187803983015672,2187803983039992,2187803536033431
|
||||
|
@@ -1,2 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,101830,101830,1048576,256,0,0,8,8,16,64,0x0,0x7fb30b508e80,0,0,0,4870225346608,4881310843226,4881310867386,4870233229204
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2846769,2846769,1048576,256,0,0,8,8,16,64,0x0,0x7fe51c612e80,0,0,0,2187801917565820,2187803983015672,2187803983039992,2187801925224307
|
||||
|
@@ -1,2 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,100812,100812,1048576,256,0,0,8,8,16,64,0x0,0x7f3f44bd2e80,65536,195450,25045552,4865251370909,4881310843226,4881310867386,4865258954789
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2849331,2849331,1048576,256,0,0,8,8,16,64,0x0,0x7f6f424dce80,65536,205200,26259424,2187809164143107,2187803983015672,2187803983039992,2187809171645862
|
||||
|
@@ -1,2 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,103458,103458,1048576,256,0,0,8,8,16,64,0x0,0x7fa2e8b18e80,32768,633554,81092720,4878063446499,4881310843226,4881310867386,4878071065706
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2849148,2849148,1048576,256,0,0,8,8,16,64,0x0,0x7f37e6006e80,32768,652733,83542268,2187808723799978,2187803983015672,2187803983039992,2187808731263349
|
||||
|
@@ -1,2 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,99996,99996,1048576,256,0,0,8,8,16,64,0x0,0x7fec3b190e80,47808,47808,16527,382472,16384,24462222,233988,0,98360336,4861216749685,4881310843226,4881310867386,4861224344736
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2847684,2847684,1048576,256,0,0,8,8,16,64,0x0,0x7f54e0f84e80,47118,47118,17095,376952,16384,24302477,224867,0,97701064,2187804428513108,2187803983015672,2187803983039992,2187804436177596
|
||||
|
@@ -1,2 +0,0 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2
|
||||
|
@@ -1,2 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_1,obj_1,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_2,obj_2,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_3,obj_3,TCC_EA_ATOMIC_LEVEL_sum,wave_size_4,obj_4,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_5,obj_5,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_SLine truncated
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f91dd28ee80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f580b6a6e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86448.0,44624.0,131111.0,0.0,64,0x7fa33d1dce80,131072.0,131072.0,0.0,2534709.0,0.0,0.0,126704913.0,60098733.0,64,0x7f3404ff8e80,0.0,64,0x7f5e573a8e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131386.0,0.0,620.0,131385.0,64,0x7ffac2522e80,4899,0,0,2154490,5112,0,0,2141628,4242,0,0,2099314,5357,0,0,2015243,2858,0,0,1971340,5525,0,0,2178508,5077,0,0,2125203,5170,0,0,2080515,6188,0,0,2204969,2540,0,0,2011521,5484,0,0,2038214,3802,0,0,2057846,6120,0,0,2188834,3964,0,0,2027001,3383,0,0,1951352,4886,0,0,1980478,5245,0,0,2139220,2483,0,0,1951930,1638,0,0,1757386,4098,0,0,1994334,4640,0,0,2046564,5457,0,0,2072723,5415,0,0,2087828,3760,0,0,1964796,5619,0,0,2176379,4009,0,0,2014267,3014,0,0,1971646,5768,0,0,2094089,7323,0,0,2265486,3095,0,0,1937313,3916,0,0,2003354,5743,0,0,2105191,64,0x7f947ef90e80,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,0,46963,0,0,64,0x7f04d97fae80,185690,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12216,28600,9466,588,0,46066,262676.0,0.0,188.0,262488.0,64,0x7fa021208e80,0,0,192,0,65536,64426,48,1488,31188,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,512,46763,1702,0,48.0,294.0,0.0,262288.0,64,0x7f0a57764e80,3065523,360448,163840,0,0,180224,114688,0,60135592.0,169786350.0,65689398.0,131072.0,0.0,731236.0,0,0,26752,95968.0,0.0,0.0,95968.0,64,0x7f1eb01bee80,0,3470274,4096,4096,0,2444985,4096,4096,0,4308279,4096,4096,0,4136335,4096,4096,0,3158928,4096,4096,0,2797634,4096,4096,0,2905250,4096,4096,0,2598975,4096,4096,0,2812077,4096,4096,0,2632160,4096,4096,0,3011451,4096,4096,0,3779904,4096,4096,0,4673131,4096,4096,0,3602062,4096,4096,0,2948938,4096,4096,0,3354396,4096,4096,0,3635035,4096,4096,0,5510591,4096,4096,0,2509949,4096,4096,0,3356820,4096,4096,0,2724107,4096,4096,0,2514690,4096,4096,0,3254665,4096,4096,0,3294102,4096,4096,0,2338345,4096,4096,0,2570120,4096,4096,0,4762167,4096,4096,0,2430399,4096,4096,0,2849988,4096,4096,0,2598496,4096,4096,0,3123416,4096,4096,0,2442105,4096,4096,64,0x7ff65c1dce80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8360,4264,8360,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8250,4154,8250,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f0c82278e80,380160,229905,3356941,16384,23833009,144,48,0,47519,47519,3801049.0,2981796.0,7064.0,1235445.0,2014864.0,0.0,2972634.0,2660465.0,378519,239852,47519,0,47519,0,1520608.0,955123.0,0.0,0.0,64,0x7f348ea8ce80,32768,0,0,0,16384,16384,393216,21897956,960.0,513939.0,0.0,524288.0,1162699.0,32768.0,0,0,0,16558,131072.0,131072.0,0.0,131072.0,64,0x7f5614bfce80,4096,0,0,0,4096,0,90,0,4099,0,0,0,4104,0,464,0,4096,0,162,0,4096,0,0,0,4096,0,396,0,4096,0,802,0,4096,0,380,0,4096,0,0,0,4096,0,27,0,4144,0,166,0,4096,0,131,0,4096,0,0,0,4096,0,1871,0,4336,0,2310,0,4096,0,353,0,4096,0,49,0,4096,0,1999,0,4096,0,778,0,4096,0,1227,0,4096,0,0,0,4096,0,1138,0,4096,0,861,0,4096,0,251,0,4144,0,0,0,4096,0,173,0,4096,0,104,0,4097,0,165,0,4096,0,129,0,4096,0,82,0,4096,0,39,0,64,0x7f62a4cdee80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46331,0,131587.0,131072.0,0.0,131104.0,64,0x7f13c2ec8e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,34824.0,126032.0,4881310843226,4881310867386
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_1,obj_1,TCC_EA_ATOMIC_LEVEL_sum,wave_size_2,obj_2,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[Line truncated
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f3220ad8e80,5194,0,0,2068203,1563,0,0,1843585,3890,0,0,2073188,2357,0,0,1838800,2906,0,0,1964866,4123,0,0,2083082,3019,0,0,1980401,1126,0,0,1739217,2116,0,0,1962610,1504,0,0,1795225,1893,0,0,1830723,1209,0,0,1785576,4221,0,0,2003673,1084,0,0,1758536,2170,0,0,1839537,3071,0,0,1989820,2776,0,0,1985830,959,0,0,1670065,2681,0,0,1964489,967,0,0,1717976,4012,0,0,1999840,1581,0,0,1835655,3739,0,0,2092282,4524,0,0,2054051,2952,0,0,1918369,1198,0,0,1720286,5344,0,0,2211346,2601,0,0,1880845,6753,0,0,2217821,1776,0,0,1831363,2655,0,0,1983750,1120,0,0,1715153,64,0x7fb31e25ae80,0.0,64,0x7f9f45336e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8359,4263,8359,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8293,4197,8293,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,64,0x7fc45c54ae80,0,0,192,0,65536,64497,48,1259,31452,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47535,1729,0,48.0,272.0,0.0,262288.0,64,0x7f579ad28e80,2189028,360448,163840,0,0,180224,114688,0,70558815.0,206983996.0,80339137.0,131072.0,0.0,642414.0,0,0,26760,102589.0,0.0,0.0,102589.0,64,0x7f7261662e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47698,0,131602.0,131072.0,0.0,131104.0,64,0x7f088cfe6e80,131072.0,131072.0,0.0,2625172.0,0.0,0.0,131872564.0,62296285.0,64,0x7efc40a26e80,0,2748501,4096,4096,0,3840100,4096,4096,0,4108452,4096,4096,0,2947343,4096,4096,0,3040477,4096,4096,0,3944044,4096,4096,0,2476802,4096,4096,0,5514695,4096,4096,0,2654547,4096,4096,0,3100262,4096,4096,0,2543709,4096,4096,0,3048461,4096,4096,0,2748338,4096,4096,0,3115526,4096,4096,0,2817235,4096,4096,0,2910248,4096,4096,0,3715184,4096,4096,0,2711504,4096,4096,0,5531972,4096,4096,0,3330972,4096,4096,0,2426014,4096,4096,0,2979586,4096,4096,0,2771918,4096,4096,0,4178575,4096,4096,0,2722573,4096,4096,0,2557628,4096,4096,0,3670745,4096,4096,0,2622149,4096,4096,0,2973558,4096,4096,0,2932333,4096,4096,0,3170785,4096,4096,0,3767901,4096,4096,64,0x7f55fbb72e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,62758.0,127852.0,64,0x7f912d192e80,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fbaf9664e80,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,64,0x7f8b1336ae80,388104,236742,3433945,16384,24696797,144,48,0,48512,48512,3903956.0,3037429.0,5449.0,1090465.0,2229924.0,0.0,3027940.0,2718747.0,386391,246680,48512,0,48512,0,1552384.0,960412.0,0.0,0.0,64,0x7f4751190e80,32768,0,0,0,16384,16384,393216,22877477,960.0,513951.0,0.0,524288.0,845849.0,32768.0,0,0,0,16973,131072.0,131072.0,0.0,131072.0,64,0x7f151fa60e80,4096,0,36,0,4096,0,243,0,4096,0,2302,0,4099,0,2066,0,4096,0,0,0,4096,0,216,0,4096,0,1178,0,4096,0,3427,0,4096,0,419,0,4096,0,197,0,4096,0,1296,0,4096,0,2326,0,4096,0,0,0,4096,0,119,0,4096,0,1419,0,4096,0,518,0,4096,0,455,0,4096,0,3745,0,4096,0,1585,0,4096,0,1758,0,4096,0,0,0,4096,0,771,0,4096,0,808,0,4096,0,1202,0,4096,0,312,0,4096,0,368,0,4096,0,1749,0,4144,0,1214,0,4096,0,0,0,4096,0,0,0,4096,0,186,0,4383,0,4023,0,64,0x7fc36170ee80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86453.0,44619.0,131111.0,0.0,64,0x7f9891c60e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131343.0,0.0,534.0,131342.0,64,0x7f7894b7ce80,201258,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13158,29542,9936,550,0,46514,262665.0,0.0,188.0,262477.0,2187803983015672,2187803983039992
|
||||
@@ -1,2 +1,2 @@
|
||||
workload_name,command,host_name,host_cpu,sbios,host_distro,host_kernel,host_rocmver,date,gpu_soc,vbios,numSE,numCU,numSIMD,waveSize,maxWavesPerCU,maxWorkgroupSize,L1,L2,sclk,mclk,cur_sclk,cur_mclk,L2Banks,totalL2Banks,LDSBanks,name,numSQC,numPipes,hbmBW,compute_partition,memory_partition,ip_blocks
|
||||
dispatch_0,./tests/vcopy -n 1048576 -b 256 -i 3,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_64,5.7.1-98,Mon Feb 19 12:59:52 2024 (CST),gfx908,113-D3431401-100,8,120,4,64,40,1024,16,8192,1502,1200,1502,1200,32,32,32,MI100,30,4,1200,,,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
|
||||
workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
|
||||
dispatch_0,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:45:11 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1
|
||||
|
@@ -1,2 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,104067,104067,1048576,256,0,0,8,8,16,64,0x0,0x7fb012a3ce80,4881310814096,4881310843226,4881310867386,4881310880141
|
||||
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2847501,2847501,1048576,256,0,0,8,8,16,64,0x0,0x7face032ee80,2187803982990937,2187803983015672,2187803983039992,2187803983054696
|
||||
|
@@ -1,3 +1,3 @@
|
||||
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) ",2,0,0,106306,106306,1048576,256,0,0,8,8,16,64,0x0,0x7f07ca94ee80,47170,47170,16384,65536,14343,1843816,4893155122265,4896137259986,4896137284466,4893162800916
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,106306,106306,1048576,256,0,0,8,8,16,64,0x0,0x7f07ca94ee80,41313,41313,16384,65536,8217,1048584,4893162823870,4896137389586,4896137408466,4893163144176
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2854821,2854821,1048576,256,0,0,8,8,16,64,0x0,0x7fd201bc8e80,48587,48587,16384,65536,13335,1699196,2187825353651312,2187817997797403,2187817997821723,2187825361131083
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2854821,2854821,1048576,256,0,0,8,8,16,64,0x0,0x7fd201bc8e80,43788,43788,16384,65536,8358,1048576,2187825361154758,2187817997919963,2187817997938843,2187825361465401
|
||||
|
@@ -1,3 +1,3 @@
|
||||
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) ",2,0,0,108543,108543,1048576,256,0,0,8,8,16,64,0x0,0x7ffb9d048e80,0,0,0,4903924355712,4896137259986,4896137284466,4903931980111
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,108543,108543,1048576,256,0,0,8,8,16,64,0x0,0x7ffb9d048e80,0,0,0,4903931998325,4896137389586,4896137408466,4903932324242
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2852254,2852254,1048576,256,0,0,8,8,16,64,0x0,0x7fdce63b0e80,0,0,0,2187818435420620,2187817997797403,2187817997821723,2187818443006390
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2852254,2852254,1048576,256,0,0,8,8,16,64,0x0,0x7fdce63b0e80,0,0,0,2187818443027440,2187817997919963,2187817997938843,2187818443325199
|
||||
|
@@ -1,3 +1,3 @@
|
||||
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) ",2,0,0,105885,105885,1048576,256,0,0,8,8,16,64,0x0,0x7f06d787ae80,65536,221164,28292080,4891310211821,4896137259986,4896137284466,4891317996641
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,105885,105885,1048576,256,0,0,8,8,16,64,0x0,0x7f06d787ae80,65536,172286,22054296,4891318015607,4896137389586,4896137408466,4891318319862
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2853357,2853357,1048576,256,0,0,8,8,16,64,0x0,0x7fece8768e80,65536,177888,22849344,2187821117349071,2187817997797403,2187817997821723,2187821124970508
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2853357,2853357,1048576,256,0,0,8,8,16,64,0x0,0x7fece8768e80,65536,167696,21526976,2187821124989614,2187817997919963,2187817997938843,2187821125313562
|
||||
|
@@ -1,3 +1,3 @@
|
||||
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) ",2,0,0,107122,107122,1048576,256,0,0,8,8,16,64,0x0,0x7f8c2ec5ce80,32768,652466,83517588,4897035318717,4896137259986,4896137284466,4897042979986
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,107122,107122,1048576,256,0,0,8,8,16,64,0x0,0x7f8c2ec5ce80,32768,666290,85282176,4897042999433,4896137389586,4896137408466,4897043314900
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2852991,2852991,1048576,256,0,0,8,8,16,64,0x0,0x7f100dc28e80,32768,657746,84179812,2187820219055599,2187817997797403,2187817997821723,2187820226818161
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2852991,2852991,1048576,256,0,0,8,8,16,64,0x0,0x7f100dc28e80,32768,678033,86771904,2187820226837949,2187817997919963,2187817997938843,2187820227160915
|
||||
|
@@ -1,3 +1,3 @@
|
||||
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) ",2,0,0,105274,105274,1048576,256,0,0,8,8,16,64,0x0,0x7f5a39766e80,48042,48042,17103,384344,16384,24957228,232500,0,100356280,4888569436024,4896137259986,4896137284466,4888577137587
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,105274,105274,1048576,256,0,0,8,8,16,64,0x0,0x7f5a39766e80,41327,41327,12734,330624,16384,23699957,225369,0,95346784,4888577166532,4896137389586,4896137408466,4888577502207
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2851521,2851521,1048576,256,0,0,8,8,16,64,0x0,0x7fa106240e80,47947,47947,16547,383584,16384,24538596,231412,0,98657844,2187816647872285,2187817997797403,2187817997821723,2187816655447195
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2851521,2851521,1048576,256,0,0,8,8,16,64,0x0,0x7fa106240e80,42133,42133,13660,337072,16384,24431973,228800,0,98212048,2187816655475638,2187817997919963,2187817997938843,2187816655805868
|
||||
|
@@ -1,3 +0,0 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2
|
||||
|
@@ -1,3 +1,3 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_1,obj_1,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_Line truncated
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fa60a0bee80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8197,4101,8197,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8242,4146,8242,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8360,4264,8360,64,0x7fa20f0d0e80,1702,0,0,1719740,7962,0,0,2367356,1813,0,0,1682111,4174,0,0,2059977,1812,0,0,1735455,2059,0,0,1820882,2228,0,0,1826548,1503,0,0,1832663,2208,0,0,1673719,3022,0,0,2011650,849,0,0,1676750,1486,0,0,1754130,884,0,0,1602921,1369,0,0,1692083,1511,0,0,1760530,978,0,0,1690457,567,0,0,1537905,891,0,0,1608514,2211,0,0,1855600,550,0,0,1576614,1147,0,0,1678056,1111,0,0,1713498,919,0,0,1679103,7020,0,0,2300285,1662,0,0,1775975,862,0,0,1635212,1516,0,0,1721473,4543,0,0,2101876,2041,0,0,1729683,2149,0,0,1839403,835,0,0,1673472,760,0,0,1686898,64,0x7fadad946e80,32768,0,0,0,16384,16384,393216,22494614,960.0,513961.0,0.0,524288.0,902516.0,32768.0,0,0,0,14994,131072.0,131072.0,0.0,131072.0,64,0x7fc9e4f16e80,188575,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,10586,26970,9373,588,0,44803,262515.0,0.0,188.0,262327.0,64,0x7f8939bd2e80,1600702,360448,163840,0,0,180224,114688,0,69084961.0,191566858.0,77600155.0,131072.0,0.0,605821.0,0,0,25901,89611.0,0.0,0.0,89611.0,64,0x7fae20506e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46178,0,131495.0,131072.0,0.0,131104.0,64,0x7faf71fbce80,0,0,192,0,65536,64518,48,1273,31071,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,512,47162,1764,0,48.0,338.0,0.0,262288.0,64,0x7fcda68c2e80,0.0,64,0x7f553c3bae80,0,2583434,4096,4096,0,2661632,4096,4096,0,2414679,4096,4096,0,2739437,4096,4096,0,2917313,4096,4096,0,2717546,4096,4096,0,2839271,4096,4096,0,3065063,4096,4096,0,2536506,4096,4096,0,3139740,4096,4096,0,3318271,4096,4096,0,3565532,4096,4096,0,2469848,4096,4096,0,2758141,4096,4096,0,2904332,4096,4096,0,2749662,4096,4096,0,3557031,4096,4096,0,2731188,4096,4096,0,2458290,4096,4096,0,2807379,4096,4096,0,2428993,4096,4096,0,4082071,4096,4096,0,3132549,4096,4096,0,3590082,4096,4096,0,2481396,4096,4096,0,2116688,4096,4096,0,5439048,4096,4096,0,3236710,4096,4096,0,2627301,4096,4096,0,2026385,4096,4096,0,3445322,4096,4096,0,2947862,4096,4096,64,0x7f06658d2e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87096.0,43976.0,131112.0,0.0,64,0x7f8bb3484e80,131072.0,131072.0,0.0,2423296.0,0.0,0.0,113076183.0,63585179.0,64,0x7f08c8c6ee80,377232,230257,3360996,16384,24549122,144,48,0,47153,47153,3806189.0,2991229.0,5194.0,1067106.0,2152951.0,0.0,2982418.0,2671847.0,375519,240188,47153,0,47153,0,1508896.0,959506.0,0.0,0.0,64,0x7f0b41e7ce80,4096,0,2925,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,2346,0,4264,0,728,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,729,0,4144,0,305,0,4096,0,144,0,4096,0,423,0,4096,0,0,0,4097,0,645,0,4096,0,377,0,4096,0,712,0,4096,0,9890,0,4096,0,1819,0,4096,0,0,0,4096,0,681,0,4096,0,0,0,4096,0,335,0,4096,0,876,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,1544,0,4144,0,0,0,4096,0,0,0,64,0x7f61d1a72e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,40142.0,102709.0,64,0x7fc4fb86ae80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131414.0,0.0,676.0,131413.0,64,0x7fa068f46e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f5cf2ffce80,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,0,47380,0,0,4896137259986,4896137284466
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fa60a0bee80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8197,4101,8197,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8241,4145,8241,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8195,4099,8195,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8242,4146,8242,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8360,4264,8360,64,0x7fa20f0d0e80,703,0,0,1314581,1626,0,0,1411146,1341,0,0,1370964,4836,0,0,1731637,1024,0,0,1309194,1120,0,0,1431475,678,0,0,1348884,4387,0,0,1737711,1,0,0,1088934,3132,0,0,1604634,1043,0,0,1395819,1527,0,0,1499847,544,0,0,1186615,425,0,0,1215867,622,0,0,1287527,4774,0,0,1737759,402,0,0,1142761,1652,0,0,1414273,2670,0,0,1510005,2394,0,0,1536105,1492,0,0,1443618,2538,0,0,1490948,518,0,0,1365797,3729,0,0,1657440,775,0,0,1301207,403,0,0,1315041,711,0,0,1365433,6061,0,0,1791204,1067,0,0,1355112,3143,0,0,1609633,1084,0,0,1371101,4420,0,0,1670890,64,0x7fadad946e80,32768,0,0,0,16384,16384,393216,22837699,960.0,513930.0,0.0,524288.0,873696.0,32768.0,0,0,0,13937,86500.0,86500.0,0.0,86500.0,64,0x7fc9e4f16e80,119145,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13894,30278,7655,588,0,37776,262192.0,0.0,47.0,262145.0,64,0x7f8939bd2e80,1991511,360448,163840,0,0,180224,114688,0,64224164.0,180767688.0,89716576.0,131072.0,0.0,998830.0,0,0,29216,41226.0,0.0,0.0,41226.0,64,0x7fae20506e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3661,39636,0,131376.0,131072.0,0.0,87078.0,64,0x7faf71fbce80,0,0,48,0,65536,65536,0,0,31156,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,456,42855,1676,0,48.0,345.0,0.0,262144.0,64,0x7fcda68c2e80,0.0,64,0x7f553c3bae80,0,2603118,2652,2652,0,3227834,2702,2702,0,4376515,2678,2678,0,4755592,2713,2713,0,3240756,2664,2664,0,2918998,2736,2736,0,3360515,2722,2722,0,3918760,2712,2712,0,3308100,2680,2680,0,2923150,2704,2704,0,3288759,2704,2704,0,4056748,2744,2744,0,2798935,2674,2674,0,3813345,2696,2696,0,3569727,2700,2700,0,3581353,2708,2708,0,3307644,2688,2688,0,3555306,2700,2700,0,4250118,2702,2702,0,4011963,2712,2712,0,3515613,2682,2682,0,3364948,2743,2743,0,3352922,2696,2696,0,2908181,2700,2700,0,2433770,2660,2660,0,2801725,2713,2713,0,3368138,2750,2750,0,4798422,2720,2720,0,2674558,2654,2654,0,2944023,2702,2702,0,3378438,2746,2746,0,4740506,2702,2702,64,0x7f06658d2e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86585.0,0.0,131112.0,0.0,64,0x7f8bb3484e80,131072.0,131072.0,0.0,2507694.0,0.0,0.0,116625128.0,46114905.0,64,0x7f08c8c6ee80,398816,253314,3699536,16384,26617376,0,96,0,49851,49851,4089209.0,3358735.0,5058.0,1371532.0,2528198.0,0.0,3342088.0,3028757.0,398808,263091,49851,0,49851,1133,1595232.0,892934.0,1.0,0.0,64,0x7f0b41e7ce80,4096,0,4109,0,4096,0,2628,0,4096,0,5212,0,4096,0,1096,0,4096,0,3532,0,4264,0,5388,0,4096,0,1527,0,4096,0,1219,0,4096,0,2403,0,4100,0,3629,0,4144,0,1511,0,4096,0,2390,0,4096,0,797,0,4096,0,4377,0,4097,0,1581,0,4097,0,1605,0,4096,0,2137,0,4096,0,3335,0,4096,0,2066,0,4096,0,2114,0,4097,0,5491,0,4096,0,6160,0,4096,0,3235,0,4097,0,2726,0,4096,0,725,0,4096,0,1832,0,4096,0,1195,0,4096,0,1637,0,4096,0,35,0,4096,0,187,0,4144,0,1075,0,4099,0,489,0,64,0x7f61d1a72e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,54656.0,121442.0,64,0x7fc4fb86ae80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131089.0,0.0,32.0,131088.0,64,0x7fa068f46e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f5cf2ffce80,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,0,43156,0,0,4896137389586,4896137408466
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_1,obj_1,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_2,obj_2,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_3,obj_3,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMLine truncated
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f59c6672e80,4096,0,884,0,4096,0,7241,0,4096,0,4793,0,4099,0,2599,0,4096,0,2154,0,4096,0,3136,0,4096,0,288,0,4096,0,2872,0,4096,0,1687,0,4096,0,949,0,4096,0,1226,0,4096,0,3572,0,4096,0,1760,0,4264,0,1550,0,4144,0,8,0,4096,0,641,0,4096,0,1339,0,4096,0,2508,0,4096,0,2977,0,4096,0,974,0,4096,0,4167,0,4096,0,1373,0,4096,0,2383,0,4096,0,0,0,4096,0,499,0,4096,0,891,0,4096,0,1060,0,4144,0,1403,0,4096,0,2641,0,4097,0,0,0,4096,0,0,0,4096,0,6711,0,64,0x7fe07ee12e80,0,0,192,0,65536,64511,48,1360,32092,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48249,1718,0,48.0,383.0,0.0,262288.0,64,0x7fc7d7c6ce80,190381,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14504,30888,9876,550,0,45781,262590.0,0.0,188.0,262402.0,64,0x7f5e935ece80,32768,0,0,0,16384,16384,393216,22024101,960.0,513884.0,0.0,524288.0,1173274.0,32768.0,0,0,0,17442,131072.0,131072.0,0.0,131072.0,64,0x7fe12d8fae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,65337.0,130872.0,64,0x7f0dea7dce80,0.0,64,0x7f724c9fae80,0,3709730,4096,4096,0,2691727,4096,4096,0,4860451,4096,4096,0,4011195,4096,4096,0,4212142,4096,4096,0,2952521,4096,4096,0,4952643,4096,4096,0,3402094,4096,4096,0,3520868,4096,4096,0,4159150,4096,4096,0,3244782,4096,4096,0,4056625,4096,4096,0,2809991,4096,4096,0,4073468,4096,4096,0,3922681,4096,4096,0,3382407,4096,4096,0,3898405,4096,4096,0,4153605,4096,4096,0,4804191,4096,4096,0,3690606,4096,4096,0,4343774,4096,4096,0,4594981,4096,4096,0,3438943,4096,4096,0,3358847,4096,4096,0,3120617,4096,4096,0,3779821,4096,4096,0,3553386,4096,4096,0,5160416,4096,4096,0,3020076,4096,4096,0,3555842,4096,4096,0,3008008,4096,4096,0,3193964,4096,4096,64,0x7f95e557ae80,392048,239379,3510014,16384,25645719,144,48,0,49005,49005,3943561.0,3022659.0,6796.0,1099135.0,2040815.0,0.0,3013743.0,2702139.0,390527,249332,49005,0,49005,0,1568160.0,960866.0,0.0,0.0,64,0x7ff258422e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131360.0,0.0,568.0,131359.0,64,0x7fad94a7ce80,1904378,360448,163840,0,0,180224,114688,0,69629443.0,202401778.0,73612921.0,131072.0,0.0,599486.0,0,0,26515,80321.0,0.0,0.0,80321.0,64,0x7f349a4bae80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8332,4377,8473,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f225df1ae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86607.0,44465.0,131111.0,0.0,64,0x7f2f5a676e80,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f16d41c6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,48272,0,131631.0,131072.0,0.0,131104.0,64,0x7f6626f04e80,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,64,0x7f403d11ee80,131072.0,131072.0,0.0,2607526.0,0.0,0.0,117494719.0,62120706.0,64,0x7f62ac1dce80,2344,0,0,1827024,744,0,0,1622330,596,0,0,1601570,2730,0,0,1879982,1372,0,0,1719760,302,0,0,1550459,3955,0,0,2126722,2605,0,0,1967050,2520,0,0,1824609,1726,0,0,1798330,554,0,0,1591286,1066,0,0,1633560,5563,0,0,2234365,950,0,0,1624899,978,0,0,1619574,3124,0,0,1872210,1763,0,0,1751192,703,0,0,1703906,937,0,0,1694279,2940,0,0,1954814,6163,0,0,2145181,4104,0,0,2013477,701,0,0,1529111,2101,0,0,1854014,3225,0,0,1869353,984,0,0,1656245,2325,0,0,1881285,3066,0,0,1901849,2960,0,0,2008550,2402,0,0,1895693,3255,0,0,2062674,2492,0,0,1953049,2187817997797403,2187817997821723
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f59c6672e80,4096,0,2641,0,4096,0,0,0,4096,0,1336,0,4096,0,2701,0,4096,0,1401,0,4096,0,0,0,4096,0,6719,0,4096,0,0,0,4096,0,1190,0,4096,0,89,0,4096,0,309,0,4096,0,2630,0,4096,0,4,0,4264,0,706,0,4144,0,811,0,4096,0,1362,0,4096,0,1215,0,4099,0,307,0,4096,0,8221,0,4096,0,1350,0,4096,0,1164,0,4096,0,3894,0,4096,0,867,0,4096,0,337,0,4096,0,0,0,4096,0,2275,0,4097,0,1409,0,4144,0,240,0,4098,0,256,0,4097,0,0,0,4096,0,521,0,4096,0,1302,0,64,0x7fe07ee12e80,0,0,48,0,65536,65536,0,0,30529,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,41873,1726,0,48.0,322.0,0.0,262144.0,64,0x7fc7d7c6ce80,196167,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14313,30697,8572,5470,0,40635,262437.0,0.0,47.0,262390.0,64,0x7f5e935ece80,32768,0,0,0,16384,16384,393216,22183863,964.0,513864.0,0.0,524288.0,1172677.0,32768.0,0,0,0,22082,130992.0,130992.0,0.0,130992.0,64,0x7fe12d8fae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,56514.0,133383.0,64,0x7f0dea7dce80,0.0,64,0x7f724c9fae80,0,3475943,2700,2700,0,4382889,2704,2704,0,2977534,2664,2664,0,4569422,2718,2718,0,2738269,2712,2712,0,2775268,2740,2740,0,3964792,2692,2692,0,2906304,2728,2728,0,3457635,2700,2700,0,3151930,2693,2693,0,3739879,2711,2711,0,4260517,2740,2740,0,3898201,2721,2721,0,4593149,2681,2681,0,2616848,2673,2673,0,3074110,2720,2720,0,3037402,2702,2702,0,5530482,2702,2702,0,4108480,2672,2672,0,5353051,2732,2732,0,4190098,2714,2714,0,4717220,2720,2720,0,3191164,2681,2681,0,3468685,2720,2720,0,4292542,2704,2704,0,3009577,2698,2698,0,2741557,2726,2726,0,2857776,2726,2726,0,2373296,2704,2704,0,4238827,2697,2697,0,5488284,2714,2714,0,3239919,2720,2720,64,0x7f95e557ae80,348432,239263,3499622,16384,25597170,0,48,0,43553,43553,3878498.0,3080142.0,6708.0,1065910.0,2076089.0,0.0,3071098.0,2758670.0,348424,248715,43553,0,43553,0,1393696.0,818678.0,0.0,0.0,64,0x7ff258422e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131320.0,0.0,494.0,131319.0,64,0x7fad94a7ce80,1110653,360448,163840,0,0,180224,114688,0,73690187.0,193422943.0,77064220.0,131072.0,0.0,659148.0,0,0,25286,61768.0,0.0,0.0,61768.0,64,0x7f349a4bae80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8333,4237,8333,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8196,4100,8196,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f225df1ae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86597.0,0.0,131112.0,0.0,64,0x7f2f5a676e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f16d41c6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3893,39971,0,131594.0,131072.0,0.0,87139.0,64,0x7f6626f04e80,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,64,0x7f403d11ee80,131072.0,131072.0,0.0,2710148.0,0.0,0.0,131479249.0,48074288.0,64,0x7f62ac1dce80,2100,0,0,1486400,864,0,0,1219538,3353,0,0,1549735,2177,0,0,1508442,626,0,0,1306394,310,0,0,1335577,996,0,0,1292534,2422,0,0,1589674,624,0,0,1225109,488,0,0,1203448,3802,0,0,1664761,1714,0,0,1403540,2208,0,0,1515917,317,0,0,1195163,412,0,0,1259761,1985,0,0,1468103,1928,0,0,1486998,820,0,0,1231013,3271,0,0,1616855,2749,0,0,1567529,1081,0,0,1284094,1090,0,0,1373760,1415,0,0,1459118,4070,0,0,1697843,614,0,0,1203830,1130,0,0,1251547,1308,0,0,1359676,2857,0,0,1567353,1577,0,0,1327309,5217,0,0,1745689,6647,0,0,1887934,2853,0,0,1539207,2187817997919963,2187817997938843
|
||||
@@ -1,2 +1,2 @@
|
||||
workload_name,command,host_name,host_cpu,sbios,host_distro,host_kernel,host_rocmver,date,gpu_soc,vbios,numSE,numCU,numSIMD,waveSize,maxWavesPerCU,maxWorkgroupSize,L1,L2,sclk,mclk,cur_sclk,cur_mclk,L2Banks,totalL2Banks,LDSBanks,name,numSQC,numPipes,hbmBW,compute_partition,memory_partition,ip_blocks
|
||||
dispatch_0_1,./tests/vcopy -n 1048576 -b 256 -i 3,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_64,5.7.1-98,Mon Feb 19 13:00:17 2024 (CST),gfx908,113-D3431401-100,8,120,4,64,40,1024,16,8192,1502,1200,1502,1200,32,32,32,MI100,30,4,1200,,,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
|
||||
workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
|
||||
dispatch_0_1,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:45:25 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
|
||||
|
@@ -1,3 +1,3 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,106919,106919,1048576,256,0,0,8,8,16,64,0x0,0x7f8475eece80,4896137232330,4896137259986,4896137284466,4896137296401
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,106919,106919,1048576,256,0,0,8,8,16,64,0x0,0x7f8475eece80,4896137297253,4896137389586,4896137408466,4896137410026
|
||||
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2852071,2852071,1048576,256,0,0,8,8,16,64,0x0,0x7f0f1fe14e80,2187817997771027,2187817997797403,2187817997821723,2187817997835769
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2852071,2852071,1048576,256,0,0,8,8,16,64,0x0,0x7f0f1fe14e80,2187817997834266,2187817997919963,2187817997938843,2187817997944092
|
||||
|
@@ -1,2 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,95615,95615,1048576,256,0,0,8,8,16,64,0x0,0x7f8cc503ee80,38738,38738,16384,65536,8147,1048608,4839256684968,4855077119856,4855077138416,4839264410295
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2845401,2845401,1048576,256,0,0,8,8,16,64,0x0,0x7fcadc3dce80,38565,38565,16384,65536,8226,1048620,2187796746637903,2187794678392809,2187794678412009,2187796754235446
|
||||
|
@@ -1,2 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,95412,95412,1048576,256,0,0,8,8,16,64,0x0,0x7f9b7976ee80,0,0,0,4838332549840,4855077119856,4855077138416,4838340188534
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2843019,2843019,1048576,256,0,0,8,8,16,64,0x0,0x7febe3572e80,0,0,0,2187790583277714,2187794678392809,2187794678412009,2187790590832306
|
||||
|
@@ -1,2 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,96834,96834,1048576,256,0,0,8,8,16,64,0x0,0x7feee7c56e80,65536,86724,11090536,4845394358857,4855077119856,4855077138416,4845401906929
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2843570,2843570,1048576,256,0,0,8,8,16,64,0x0,0x7f59f3376e80,65536,89910,11518096,2187791957065822,2187794678392809,2187794678412009,2187791964652224
|
||||
|
@@ -1,2 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,98257,98257,1048576,256,0,0,8,8,16,64,0x0,0x7feaac5dce80,32768,648935,83060448,4851859046316,4855077119856,4855077138416,4851866625217
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2842271,2842271,1048576,256,0,0,8,8,16,64,0x0,0x7fd8069d0e80,32768,639748,81911640,2187788268757096,2187794678392809,2187794678412009,2187788276577677
|
||||
|
@@ -1,2 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,96022,96022,1048576,256,0,0,8,8,16,64,0x0,0x7f9cc9a4ae80,39238,39238,12449,313912,16384,21856220,212342,0,87959476,4841278994784,4855077119856,4855077138416,4841286607339
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2844302,2844302,1048576,256,0,0,8,8,16,64,0x0,0x7f98b83bee80,39353,39353,12306,314832,16384,22386567,216458,0,90050164,2187793773743550,2187794678392809,2187794678412009,2187793781232750
|
||||
|
@@ -1,2 +0,0 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2
|
||||
|
@@ -1,2 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_2,obj_2,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],wave_size_3,obj_3,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_4,obj_4,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_suLine truncated
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f1d8c15ee80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,38058,0,131120.0,131072.0,0.0,86666.0,64,0x7f7344748e80,316552,217305,3164765,16384,22802950,0,48,0,39568,39568,3548909.0,2953421.0,6333.0,1143383.0,1920174.0,0.0,2943829.0,2632025.0,314839,225366,39568,0,39568,0,1266176.0,803963.0,0.0,0.0,64,0x7fe9644bce80,0,5222995,2682,2682,0,3392075,2734,2734,0,3756922,2702,2702,0,4271945,2722,2722,0,4163839,2680,2680,0,3733566,2727,2727,0,3781930,2710,2710,0,5226561,2722,2722,0,2922815,2693,2693,0,5120054,2696,2696,0,3169518,2720,2720,0,4835632,2728,2728,0,3195743,2684,2684,0,3687677,2688,2688,0,4623675,2708,2708,0,3783480,2708,2708,0,3381916,2659,2659,0,3821247,2732,2732,0,3517105,2698,2698,0,4983992,2726,2726,0,3292152,2680,2680,0,4115210,2741,2741,0,4127291,2668,2668,0,3662849,2726,2726,0,2898666,2664,2664,0,4099866,2725,2725,0,3485860,2744,2744,0,3590091,2708,2708,0,4445905,2692,2692,0,4517792,2709,2709,0,4868968,2720,2720,0,3131958,2712,2712,64,0x7f7dee84ee80,113445,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12112,28496,7653,588,0,37317,262192.0,0.0,47.0,262145.0,64,0x7f7054060e80,232735,360448,163840,0,0,180224,114688,0,72780046.0,215262519.0,82111247.0,131072.0,0.0,561955.0,0,0,23176,85311.0,0.0,0.0,85311.0,64,0x7f5a5a6bae80,32768,0,0,0,16384,16384,393216,22039488,0.0,524288.0,0.0,524288.0,740876.0,32768.0,0,0,0,11985,86563.0,86563.0,0.0,86563.0,64,0x7f1b2c53ce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131073.0,0.0,0.0,131072.0,64,0x7fa720d58e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,26071.0,99136.0,64,0x7f05f0f54e80,1817,0,0,1465710,1225,0,0,1347096,1601,0,0,1328810,1773,0,0,1448741,1292,0,0,1334314,463,0,0,1284833,3676,0,0,1675403,803,0,0,1376596,1023,0,0,1331919,1355,0,0,1364751,2601,0,0,1568619,625,0,0,1363566,1373,0,0,1409928,782,0,0,1305101,812,0,0,1209792,726,0,0,1261650,1443,0,0,1398748,1779,0,0,1496283,357,0,0,1118800,5005,0,0,1754840,308,0,0,1124542,1979,0,0,1459692,698,0,0,1380954,1104,0,0,1343945,453,0,0,1245581,1294,0,0,1424018,2422,0,0,1495284,4014,0,0,1668796,2033,0,0,1439203,907,0,0,1295852,722,0,0,1296558,2365,0,0,1511383,64,0x7f6069bb2e80,4096,0,2290,0,4096,0,880,0,4096,0,789,0,4096,0,427,0,4097,0,4003,0,4096,0,573,0,4096,0,1851,0,4096,0,535,0,4096,0,5726,0,4096,0,1981,0,4096,0,4482,0,4096,0,183,0,4096,0,1570,0,4096,0,3036,0,4096,0,3194,0,4096,0,1713,0,4096,0,2348,0,4096,0,3235,0,4096,0,2424,0,4096,0,2633,0,4096,0,503,0,4096,0,3667,0,4096,0,4279,0,4096,0,1518,0,4096,0,1682,0,4096,0,889,0,4096,0,589,0,4096,0,862,0,4096,0,1454,0,4096,0,435,0,4096,0,2009,0,4096,0,111,0,64,0x7fb601d70e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86737.0,0.0,131110.0,0.0,64,0x7f4c9939ae80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fe83f9ece80,0.0,64,0x7f95399eae80,0,0,48,0,65536,65536,0,0,28472,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,435,38030,1753,0,48.0,0.0,0.0,262144.0,64,0x7f6a01166e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fc0cfb26e80,131072.0,131072.0,0.0,2689705.0,0.0,0.0,120492860.0,44290488.0,64,0x7f1f59a4ae80,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,0,38643,0,0,4855077119856,4855077138416
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_1,obj_1,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_2,obj_2,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_3,obj_3,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_4,obj_4,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_5,obj_5,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],wave_size_6,obj_6,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_7,obj_7,SQ_ACLine truncated
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8236e3ce80,32768,0,0,0,16384,16384,393216,22241342,0.0,524288.0,0.0,524288.0,719375.0,32768.0,0,0,0,12013,86583.0,86583.0,0.0,86583.0,64,0x7fac5c1fce80,136682,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13329,29713,7604,1462,0,36927,262194.0,0.0,47.0,262147.0,64,0x7fc0c15ece80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,56341.0,126058.0,64,0x7ff9bc0e4e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,38044,0,131120.0,131072.0,0.0,86505.0,64,0x7f5afe336e80,0,0,48,0,65536,65536,0,0,28348,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,436,37902,1745,0,48.0,0.0,0.0,262144.0,64,0x7f0614fdce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fde1eda0e80,131072.0,131072.0,0.0,2611243.0,0.0,0.0,127446147.0,47598095.0,64,0x7f0a74f6ee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131073.0,0.0,0.0,131072.0,64,0x7f93da470e80,0,4733576,2698,2698,0,4950371,2718,2718,0,3343062,2660,2660,0,4991429,2702,2702,0,3814454,2673,2673,0,4827291,2716,2716,0,3802294,2710,2710,0,4550844,2712,2712,0,4653501,2690,2690,0,4533577,2692,2692,0,3784597,2692,2692,0,4495445,2730,2730,0,4357469,2693,2693,0,3624396,2680,2680,0,4607537,2694,2694,0,3314040,2680,2680,0,4364060,2666,2666,0,4878204,2726,2726,0,3991236,2666,2666,0,4773393,2712,2712,0,3896694,2704,2704,0,3887271,2741,2741,0,4288052,2676,2676,0,4492545,2690,2690,0,3336323,2690,2690,0,4847770,2682,2682,0,4614927,2722,2722,0,4009045,2708,2708,0,3916086,2706,2706,0,4042568,2693,2693,0,4519454,2698,2698,0,3888336,2682,2682,64,0x7fd8e037ce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86550.0,0.0,131110.0,0.0,64,0x7f82c9fdce80,309840,214878,3145099,16384,22497534,0,48,0,38729,38729,3513076.0,2970065.0,5756.0,1077804.0,1946413.0,0.0,2960237.0,2648110.0,308319,222962,38729,0,38729,0,1239328.0,804950.0,0.0,0.0,64,0x7fab341e8e80,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,64,0x7f29c3e04e80,4137,0,0,1636048,2067,0,0,1435641,1065,0,0,1297932,1785,0,0,1428162,1967,0,0,1530501,2415,0,0,1523447,808,0,0,1393467,796,0,0,1285312,1258,0,0,1320082,2453,0,0,1403696,1134,0,0,1375485,1140,0,0,1285513,3047,0,0,1572917,1062,0,0,1327053,1736,0,0,1478458,1681,0,0,1487434,2035,0,0,1460776,2120,0,0,1508369,2571,0,0,1511321,1734,0,0,1389877,420,0,0,1197709,901,0,0,1261289,3420,0,0,1673728,5642,0,0,1775752,3028,0,0,1583374,1358,0,0,1382535,3126,0,0,1626562,1167,0,0,1332831,1751,0,0,1448080,5578,0,0,1842878,1881,0,0,1446346,1003,0,0,1339746,64,0x7f7bf4c16e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,64,0x7f3e474d6e80,224643,360448,163840,0,0,180224,114688,0,71268791.0,213987650.0,80373920.0,131072.0,0.0,577044.0,0,0,23408,78640.0,0.0,0.0,78640.0,64,0x7fcaf3f3ce80,4096,0,1506,0,4096,0,515,0,4096,0,4904,0,4096,0,3332,0,4096,0,2278,0,4096,0,116,0,4096,0,1952,0,4096,0,715,0,4096,0,1612,0,4096,0,135,0,4096,0,2300,0,4096,0,2405,0,4097,0,152,0,4096,0,2199,0,4096,0,3233,0,4096,0,0,0,4096,0,2088,0,4096,0,4368,0,4096,0,3726,0,4096,0,1080,0,4096,0,661,0,4096,0,6546,0,4096,0,2081,0,4096,0,0,0,4096,0,2265,0,4096,0,6117,0,4096,0,376,0,4096,0,133,0,4096,0,1164,0,4096,0,1080,0,4096,0,509,0,4096,0,892,0,64,0x7fedc8430e80,0.0,2187794678392809,2187794678412009
|
||||
@@ -1,2 +1,2 @@
|
||||
workload_name,command,host_name,host_cpu,sbios,host_distro,host_kernel,host_rocmver,date,gpu_soc,vbios,numSE,numCU,numSIMD,waveSize,maxWavesPerCU,maxWorkgroupSize,L1,L2,sclk,mclk,cur_sclk,cur_mclk,L2Banks,totalL2Banks,LDSBanks,name,numSQC,numPipes,hbmBW,compute_partition,memory_partition,ip_blocks
|
||||
dispatch_2,./tests/vcopy -n 1048576 -b 256 -i 3,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_64,5.7.1-98,Mon Feb 19 12:59:27 2024 (CST),gfx908,113-D3431401-100,8,120,4,64,40,1024,16,8192,1502,1200,1502,1200,32,32,32,MI100,30,4,1200,,,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
|
||||
workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
|
||||
dispatch_2,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:44:58 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
|
||||
|
@@ -1,2 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
|
||||
1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,98866,98866,1048576,256,0,0,8,8,16,64,0x0,0x7fc716e2ee80,4855077106740,4855077119856,4855077138416,4855077149110
|
||||
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2844668,2844668,1048576,256,0,0,8,8,16,64,0x0,0x7f3fa4688e80,2187794678379498,2187794678392809,2187794678412009,2187794678425044
|
||||
|
@@ -1,2 +1,2 @@
|
||||
workload_name,command,host_name,host_cpu,sbios,host_distro,host_kernel,host_rocmver,date,gpu_soc,vbios,numSE,numCU,numSIMD,waveSize,maxWavesPerCU,maxWorkgroupSize,L1,L2,sclk,mclk,cur_sclk,cur_mclk,L2Banks,totalL2Banks,LDSBanks,name,numSQC,numPipes,hbmBW,compute_partition,memory_partition,ip_blocks
|
||||
dispatch_6_8,"./tests/vcopy -n 1048576 -b 256 -i 3",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_64,5.7.1-98,Mon Feb 19 13:26:04 2024 (CST),gfx908,113-D3431401-100,8,120,4,64,40,1024,16,8192,1502,1200,1502,1200,32,32,32,MI100,30,4,1200,NA,NA,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
|
||||
workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
|
||||
dispatch_6_8,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:48:07 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
|
||||
|
@@ -1,2 +1,2 @@
|
||||
workload_name,command,host_name,host_cpu,sbios,host_distro,host_kernel,host_rocmver,date,gpu_soc,vbios,numSE,numCU,numSIMD,waveSize,maxWavesPerCU,maxWorkgroupSize,L1,L2,sclk,mclk,cur_sclk,cur_mclk,L2Banks,totalL2Banks,LDSBanks,name,numSQC,numPipes,hbmBW,compute_partition,memory_partition,ip_blocks
|
||||
dispatch_7,"./tests/vcopy -n 1048576 -b 256 -i 3",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_64,5.7.1-98,Mon Feb 19 13:24:53 2024 (CST),gfx908,113-D3431401-100,8,120,4,64,40,1024,16,8192,1502,1200,1502,1200,32,32,32,MI100,30,4,1200,NA,NA,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
|
||||
workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
|
||||
dispatch_7,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:44:46 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
|
||||
|
+1
-1
@@ -1,2 +1,2 @@
|
||||
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,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) ",2,0,0,196371,196371,1048576,256,0,0,8,8,16,64,0x0,0x7f741569ee80,48123,48123,16384,65536,13130,1706668,6474031491551,6478590216987,6478590240667,6474038988830
|
||||
0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2802076,2802076,1048576,256,0,0,8,8,16,64,0x0,0x7f75dfc16e80,49408,49408,16384,65536,14474,1839408,2187670903710904,2187670460808016,2187670460832816,2187670911232314
|
||||
|
500 Internal Server Error
Si è verificato un errore: Si è verificato un errore Versione Gitea: 28.2.0 |