Update csv headers, and SystemExit codes

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com> [ROCm/rocprofiler-compute commit: 717a21cf84]
2024-02-02 20:04:11 -06:00
commit 8ecc6dff7f
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,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,"__amd_rocclr_fillBuffer.kd",0,0,0,919533,919538,33554432,256,0,0,8,32,6464,0x0,0x7f539a404180,510905,510905,524288,6291456,791255,101484656,12076299622617100,12076299868527949,12076299868855467,12076299868966179
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,919533,919538,32768,256,0,0,24,24,12480,0x0,0x7f539a435100,29103,29103,512,8192,11024,1421636,12076299883226411,12076299883536030,12076299883542910,12076299883550754
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,919533,919538,4194304,256,0,0,24,24,12928,0x7f54a6102900,0x7f539a435140,214348,214348,65536,917504,141051,18053272,12076299883612759,12076299883846109,12076299883977148,12076299883980823
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
 0,"__amd_rocclr_fillBuffer.kd",0,0,0,921341,921346,33554432,256,0,0,8,32,6464,0x0,0x7f75c7a04180,0,0,0,12076325872059438,12076326117604157,12076326117928636,12076326118038409
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,921341,921346,32768,256,0,0,24,24,12480,0x0,0x7f75c7a35100,0,0,0,12076326132896351,12076326133202573,12076326133209293,12076326133221776
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,921341,921346,4194304,256,0,0,24,24,12928,0x7f76f7c91900,0x7f75c7a35140,0,0,0,12076326133274564,12076326133491052,12076326133626091,12076326133629754
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
 0,"__amd_rocclr_fillBuffer.kd",0,0,0,920962,920967,33554432,256,0,0,8,32,6464,0x0,0x7f7263004180,4194304,3135444,401545944,12076323351077524,12076323592299708,12076323592623867,12076323592733000
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,920962,920967,32768,256,0,0,24,24,12480,0x0,0x7f7263035100,512,24896,3171600,12076323607390380,12076323607684997,12076323607691557,12076323607697111
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,920962,920967,4194304,256,0,0,24,24,12928,0x7f7393007900,0x7f7263035140,65536,199274,25512368,12076323607762212,12076323607972035,12076323608104675,12076323608108936
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
 0,"__amd_rocclr_fillBuffer.kd",0,0,0,921153,921158,33554432,256,0,0,8,32,6464,0x0,0x7fbf7ac04180,1048576,11001658,1408052856,12076324607361092,12076324851578856,12076324851903654,12076324852039846
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,921153,921158,32768,256,0,0,24,24,12480,0x0,0x7fbf7ac35100,4096,113289,14479660,12076324866554932,12076324866851777,12076324866858017,12076324866863235
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,921153,921158,4194304,256,0,0,24,24,12928,0x7fc0aab91900,0x7fbf7ac35140,524288,12401318,1587311276,12076324866927514,12076324867148415,12076324867279615,12076324867283767
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,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,BeginNs,EndNs,CompleteNs
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,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,"__amd_rocclr_fillBuffer.kd",0,0,0,921529,921534,33554432,256,0,0,8,32,6464,0x0,0x7f6f26204180,502695,502695,17046,4021568,524288,372600279,3816924,0,1505167052,12076327135265660,12076327381325743,12076327381649102,12076327381757735
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,921529,921534,32768,256,0,0,24,24,12480,0x0,0x7f6f26235100,27819,27819,20311,222560,512,1122712,74488,0,4504968,12076327396356075,12076327396679513,12076327396685593,12076327396695125
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,921529,921534,4194304,256,0,0,24,24,12928,0x7f7031f1d900,0x7f6f26235140,219204,219204,20615,1753640,65536,131444628,1582707,0,527592892,12076327396760457,12076327397000951,12076327397134071,12076327397138189
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id
+Dispatch_ID,Kernel_Name,GPU_ID
 0,__amd_rocclr_fillBuffer.kd,0
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0
@@ -1,4 +1,4 @@
-KernelName,Count,Sum(ns),Mean(ns),Median(ns),Pct
+Kernel_Name,Count,Sum(ns),Mean(ns),Median(ns),Pct
 "void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,6055312.0,6055312.0,6055312.0,9.17581889130573
 "void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",1,4527004.0,4527004.0,4527004.0,6.859922135179261
 "void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,3055336.0,3055336.0,3055336.0,4.629853884999894
@@ -1,7 +1,7 @@
 Metric,Count,Unit
 VALU - Vector,,Instr per wave
 VMEM,,Instr per wave
-LDS,0.0,Instr per wave
+LDS_Per_Workgroup,0.0,Instr per wave
 VALU - MFMA,,Instr per wave
 SALU,46.862275449101794,Instr per wave
 SMEM,1.8083832335329342,Instr per wave
@@ -23,4 +23,4 @@ gfx908
 mi100
 48
 1228.8
-SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
+SQ|LDS_Per_Workgroup|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
@@ -1,12 +1,12 @@
 Metric,Avg,Min,Max,Unit
 Wave Cycles,33761.37244470105,2805.687400817871,547941.7736816406,Cycles/wave
-LDS Instrs,0.0,0.0,0.0,Instr per wave
+LDS_Per_Workgroup Instrs,0.0,0.0,0.0,Instr per wave
 Bandwidth,0.0,0.0,0.0,Bytes per wave
 Bank Conficts/Access,,,,Conflicts/access
-Index Accesses,0.0,0.0,0.0,Cycles per wave
+Dispatch_ID Accesses,0.0,0.0,0.0,Cycles per wave
 Atomic Cycles,0.0,0.0,0.0,Cycles per wave
 Bank Conflict,0.0,0.0,0.0,Cycles per wave
 Addr Conflict,0.0,0.0,0.0,Cycles per wave
 Unaligned Stall,0.0,0.0,0.0,Cycles per wave
 Mem Violations,0.0,0.0,0.0, per wave
-LDS Latency,,,,Cycles
+LDS_Per_Workgroup Latency,,,,Cycles
@@ -6,16 +6,16 @@ SMEM,2.0,smem_
 VALU,735.0,valu_
 MFMA,,mfma_
 VMEM,8.0,vmem_
-LDS,0.0,lds_
+LDS_Per_Workgroup,0.0,lds_
 GWS,0.0,gws_
 BR,22.0,br_
 VGPR,24.0,vgpr_
 SGPR,24.0,sgpr_
-LDS Allocation,0.0,lds_alloc_
+LDS_Per_Workgroup Allocation,0.0,lds_alloc_
 Scratch Allocation,0.0,scratch_alloc_
 Wavefronts,67894.0,wavefronts_
 Workgroups,16973.0,workgroups_
-LDS Req,0.0,lds_req_
+LDS_Per_Workgroup Req,0.0,lds_req_
 IL1 Fetch,163.0,il1_fetch_
 IL1 Hit,100.0,il1_hit_
 IL1_L2 Rd,0.0,il1_l2_req_
@@ -46,10 +46,10 @@ Fabric_L2 Wr,0.0,l2_fabric_wr_
 Fabric_l2 Atomic,0.0,l2_fabric_atom_
 HBM Rd,44.0,hbm_rd_
 HBM Wr,0.0,hbm_wr_
-LDS Util,0.0,lds_util_
+LDS_Per_Workgroup Util,0.0,lds_util_
 VL1 Coalesce,70.0,vl1_coales_
 VL1 Stall,30.0,vl1_stall_
-LDS Lat,,lds_lat_
+LDS_Per_Workgroup Lat,,lds_lat_
 vL1D Lat,,sl1_lat_
 IL1 Lat,,il1_lat_
 Wave Occupancy,34.0,wave_occ_
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id
+Dispatch_ID,Kernel_Name,GPU_ID
 0,__amd_rocclr_fillBuffer.kd,0
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0
@@ -12,8 +12,8 @@ VALU Util,59.49293302260621,Pct,100,59.49293302260621
 MFMA Util,,Pct,100,
 VALU Active Threads/Wave,63.96757475781579,Threads,64,99.94933555908717
 IPC - Issue,0.8437242643821745,Instr/cycle,5,16.874485287643488
-LDS BW,0.0,Gb/sec,23070.72,0.0
-LDS Bank Conflict,,Conflicts/access,32,
+LDS_Per_Workgroup BW,0.0,Gb/sec,23070.72,0.0
+LDS_Per_Workgroup Bank Conflict,,Conflicts/access,32,
 Instr Cache Hit Rate,99.99340470515173,Pct,100,99.99340470515173
 Instr Cache BW,1409.2232915418736,Gb/s,4614.144,30.54138083991036
 Scalar L1D Cache Hit Rate,99.35620448528866,Pct,100,99.35620448528866
@@ -6,7 +6,7 @@ Scratch Stall,0.0,0,0,Cycles
 Insufficient SIMD Waveslots,57830.431137724554,0,731049,Simd
 Insufficient SIMD VGPRs,568474.6706586826,0,41500307,Simd
 Insufficient SIMD SGPRs,0.0,0,0,Simd
-Insufficient CU LDS,0.0,0,0,Cu
+Insufficient CU LDS_Per_Workgroup,0.0,0,0,Cu
 Insufficient CU Barries,0.0,0,0,Cu
 Insufficient Bulky Resource,0.0,0,0,Cu
 Reach CU Threadgroups Limit,0.0,0,0,Cycles
@@ -6,5 +6,5 @@ Saved Wavefronts,0.0,0,0,Wavefronts
 Restored Wavefronts,0.0,0,0,Wavefronts
 VGPRs,23.976047904191617,8,36,Registers
 SGPRs,24.047904191616766,24,32,Registers
-LDS Allocation,0.0,0,0,Bytes
+LDS_Per_Workgroup Allocation,0.0,0,0,Bytes
 Scratch Allocation,0.0,0,0,Bytes
@@ -1,2 +1,2 @@
 workload_name,host_name,host_cpu,host_distro,host_kernel,host_rocmver,date,gpu_soc,numSE,numCU,numSIMD,waveSize,maxWavesPerCU,maxWorkgroupSize,L1,L2,sclk,mclk,cur_sclk,cur_mclk,L2Banks,name,numSQC,hbmBW,ip_blocks
-dev0,vesuvius,AMD EPYC 7542 32-Core Processor,,4.18.0-240.15.1.el8_3.x86_64,4.2.0-21,Thu Sep 22 11:31:14 2022 (CDT),gfx908,8,120,4,64,40,1024,16,,1502,1200,300,1200,32,mi100,48,1228.8,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
+dev0,vesuvius,AMD EPYC 7542 32-Core Processor,,4.18.0-240.15.1.el8_3.x86_64,4.2.0-21,Thu Sep 22 11:31:14 2022 (CDT),gfx908,8,120,4,64,40,1024,16,,1502,1200,300,1200,32,mi100,48,1228.8,SQ|LDS_Per_Workgroup|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,DispatchNs,BeginNs,EndNs,CompleteNs
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
 0,"__amd_rocclr_fillBuffer.kd",0,0,0,921580,921585,33554432,256,0,0,8,32,6464,0x0,0x7fc0c2804180,12076328266793044,12076328266837802,12076328267160519,12076328267269900
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,921580,921585,32768,256,0,0,24,24,12480,0x0,0x7fc0c2835100,12076328282132912,12076328282246095,12076328282252495,12076328282258235
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,921580,921585,4194304,256,0,0,24,24,12928,0x7fc1ce3b2900,0x7fc0c2835140,12076328282304692,12076328282317774,12076328282452973,12076328282456624
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,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,"__amd_rocclr_fillBufferAligned.kd",0,0,0,223297,223297,33554432,256,0,0,4,32,4160,0x0,0x7fc57a604280,379284,379284,524288,4718592,681163,76310828,17598097140845,17597387743185,17598246526395,17598246639545
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,223297,223297,32768,256,0,0,12,24,13888,0x0,0x7fc57a623f80,33251,33251,512,8192,6010,679448,17598251787224,17598246526395,17598251919198,17598251924230
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,223297,223297,4194304,256,0,0,12,24,14336,0x7fc57d663380,0x7fc57a623fc0,163594,163594,65536,917504,141997,15950860,17598251961259,17598251919198,17598252301279,17598252303751
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
 0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,225145,225145,33554432,256,0,0,4,32,4160,0x0,0x7f6011204280,0,0,0,17617373642292,17616657358066,17617521510730,17617521624110
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,225145,225145,32768,256,0,0,12,24,13888,0x0,0x7f6011223f80,0,0,0,17617526822058,17617521510730,17617526949772,17617526954185
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,225145,225145,4194304,256,0,0,12,24,14336,0x7f601422d380,0x7f6011223fc0,0,0,0,17617526989654,17617526949772,17617527316172,17617527318486
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
 0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,223075,223075,33554432,256,0,0,4,32,4160,0x0,0x7f931ec04280,3670016,2924224,327281248,17597154367976,17588719430319,17597306738811,17597306856651
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,223075,223075,32768,256,0,0,12,24,13888,0x0,0x7f931ec23f80,512,96990,10865032,17597311964571,17597306738811,17597312097854,17597312102767
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,223075,223075,4194304,256,0,0,12,24,14336,0x7f9321c13380,0x7f931ec23fc0,65536,635542,71138720,17597312138116,17597312097854,17597312468574,17597312471268
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
 0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,224923,224923,33554432,256,0,0,4,32,4160,0x0,0x7f6676804280,524288,5433099,608528124,17616429017287,17614162329648,17616578244180,17616578354430
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,224923,224923,32768,256,0,0,12,24,13888,0x0,0x7f6676823f80,4096,42285,4736872,17616583510399,17616578244180,17616583637143,17616583641776
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,224923,224923,4194304,256,0,0,12,24,14336,0x7f66798a9380,0x7f6676823fc0,524288,10680424,1196193368,17616583675735,17616583637143,17616584007223,17616584009546
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,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,BeginNs,EndNs,CompleteNs
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,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,"__amd_rocclr_fillBufferAligned.kd",0,0,0,223519,223519,33554432,256,0,0,4,32,4160,0x0,0x7f1ce5804280,387094,387094,8680,3096760,524288,245771477,3011216,0,999328548,17599035568236,17598328816642,17599185813205,17599185923274
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,223519,223519,32768,256,0,0,12,24,13888,0x0,0x7f1ce5823f80,33003,33003,29549,264032,512,1739044,167125,0,6969744,17599191082624,17599185813205,17599191227446,17599191232450
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,223519,223519,4194304,256,0,0,12,24,14336,0x7f1ce8890380,0x7f1ce5823fc0,164050,164050,13444,1312408,65536,80869811,1211279,0,325210296,17599191275709,17599191227446,17599191628886,17599191631540
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id
+Dispatch_ID,Kernel_Name,GPU_ID
 0,__amd_rocclr_fillBufferAligned.kd,0
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0
@@ -1,4 +1,4 @@
-KernelName,Count,Sum(ns),Mean(ns),Median(ns),Pct
+Kernel_Name,Count,Sum(ns),Mean(ns),Median(ns),Pct
 "void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",1,3359203.0,3359203.0,3359203.0,7.843408332395092
 "void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1724962.0,1724962.0,1724962.0,4.027616468509019
 "void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",1,1716642.0,1716642.0,1716642.0,4.008190087511643
@@ -1,7 +1,7 @@
 Metric,Count,Unit
 VALU - Vector,494.8622754491018,Instr per wave
 VMEM,7.958083832335329,Instr per wave
-LDS,0.0,Instr per wave
+LDS_Per_Workgroup,0.0,Instr per wave
 VALU - MFMA,0.0,Instr per wave
 SALU,24.520958083832337,Instr per wave
 SMEM,1.8023952095808384,Instr per wave
@@ -23,4 +23,4 @@ gfx90a
 mi200
 56
 1638.4
-roofline|SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
+roofline|SQ|LDS_Per_Workgroup|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
@@ -1,12 +1,12 @@
 Metric,Avg,Min,Max,Unit
 Wave Cycles,18379.615702235056,1876.4345169067383,258464.3599243164,Cycles/wave
-LDS Instrs,0.0,0.0,0.0,Instr per wave
+LDS_Per_Workgroup Instrs,0.0,0.0,0.0,Instr per wave
 Bandwidth,0.0,0.0,0.0,Bytes per wave
 Bank Conficts/Access,,,,Conflicts/access
-Index Accesses,0.0,0.0,0.0,Cycles per wave
+Dispatch_ID Accesses,0.0,0.0,0.0,Cycles per wave
 Atomic Cycles,0.0,0.0,0.0,Cycles per wave
 Bank Conflict,0.0,0.0,0.0,Cycles per wave
 Addr Conflict,0.0,0.0,0.0,Cycles per wave
 Unaligned Stall,0.0,0.0,0.0,Cycles per wave
 Mem Violations,0.0,0.0,0.0, per wave
-LDS Latency,,,,Cycles
+LDS_Per_Workgroup Latency,,,,Cycles
@@ -6,16 +6,16 @@ SMEM,2.0,smem_
 VALU,495.0,valu_
 MFMA,0.0,mfma_
 VMEM,8.0,vmem_
-LDS,0.0,lds_
+LDS_Per_Workgroup,0.0,lds_
 GWS,0.0,gws_
 BR,10.0,br_
 VGPR,12.0,vgpr_
 SGPR,24.0,sgpr_
-LDS Allocation,0.0,lds_alloc_
+LDS_Per_Workgroup Allocation,0.0,lds_alloc_
 Scratch Allocation,0.0,scratch_alloc_
 Wavefronts,67894.0,wavefronts_
 Workgroups,16973.0,workgroups_
-LDS Req,0.0,lds_req_
+LDS_Per_Workgroup Req,0.0,lds_req_
 IL1 Fetch,128.0,il1_fetch_
 IL1 Hit,100.0,il1_hit_
 IL1_L2 Rd,0.0,il1_l2_req_
@@ -46,10 +46,10 @@ Fabric_L2 Wr,0.0,l2_fabric_wr_
 Fabric_l2 Atomic,0.0,l2_fabric_atom_
 HBM Rd,44.0,hbm_rd_
 HBM Wr,0.0,hbm_wr_
-LDS Util,0.0,lds_util_
+LDS_Per_Workgroup Util,0.0,lds_util_
 VL1 Coalesce,70.0,vl1_coales_
 VL1 Stall,2.0,vl1_stall_
-LDS Lat,,lds_lat_
+LDS_Per_Workgroup Lat,,lds_lat_
 vL1D Lat,,sl1_lat_
 IL1 Lat,,il1_lat_
 Wave Occupancy,26.0,wave_occ_
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id
+Dispatch_ID,Kernel_Name,GPU_ID
 0,__amd_rocclr_fillBufferAligned.kd,0
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0
@@ -12,8 +12,8 @@ VALU Util,58.32499961405379,Pct,100,58.32499961405379
 MFMA Util,0.0,Pct,100,0.0
 VALU Active Threads/Wave,64.0,Threads,64,100.0
 IPC - Issue,1.0,Instr/cycle,5,20.0
-LDS BW,0.0,Gb/sec,22630.4,0.0
-LDS Bank Conflict,,Conflicts/access,32,
+LDS_Per_Workgroup BW,0.0,Gb/sec,22630.4,0.0
+LDS_Per_Workgroup Bank Conflict,,Conflicts/access,32,
 Instr Cache Hit Rate,99.99250938551732,Pct,100,99.99250938551732
 Instr Cache BW,1673.2474012593727,Gb/s,6092.8,27.46270025701439
 Scalar L1D Cache Hit Rate,99.34855886013408,Pct,100,99.34855886013408
@@ -6,7 +6,7 @@ Scratch Stall,0.0,0,0,Cycles
 Insufficient SIMD Waveslots,16255612.035928143,0,427277590,Simd
 Insufficient SIMD VGPRs,0.0,0,0,Simd
 Insufficient SIMD SGPRs,0.0,0,0,Simd
-Insufficient CU LDS,0.0,0,0,Cu
+Insufficient CU LDS_Per_Workgroup,0.0,0,0,Cu
 Insufficient CU Barries,0.0,0,0,Cu
 Insufficient Bulky Resource,0.0,0,0,Cu
 Reach CU Threadgroups Limit,0.0,0,0,Cycles
@@ -6,5 +6,5 @@ Saved Wavefronts,0.0,0,0,Wavefronts
 Restored Wavefronts,0.0,0,0,Wavefronts
 VGPRs,11.784431137724551,4,16,Registers
 SGPRs,24.047904191616766,24,32,Registers
-LDS Allocation,0.0,0,0,Bytes
+LDS_Per_Workgroup Allocation,0.0,0,0,Bytes
 Scratch Allocation,0.0,0,0,Bytes
@@ -1,2 +1,2 @@
 workload_name,host_name,host_cpu,host_distro,host_kernel,host_rocmver,date,gpu_soc,numSE,numCU,numSIMD,waveSize,maxWavesPerCU,maxWorkgroupSize,L1,L2,sclk,mclk,cur_sclk,cur_mclk,L2Banks,name,numSQC,hbmBW,ip_blocks
-dev0,06fa5f860366,AMD EPYC 7282 16-Core Processor,Ubuntu 20.04.5 LTS,5.11.0-27-generic,5.1.3-66,Wed Sep 28 20:46:37 2022 (),gfx90a,8,104,4,64,32,1024,16,8192,1700,1600,800,1600,32,mi200,56,1638.4,roofline|SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
+dev0,06fa5f860366,AMD EPYC 7282 16-Core Processor,Ubuntu 20.04.5 LTS,5.11.0-27-generic,5.1.3-66,Wed Sep 28 20:46:37 2022 (),gfx90a,8,104,4,64,32,1024,16,8192,1700,1600,800,1600,32,mi200,56,1638.4,roofline|SQ|LDS_Per_Workgroup|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
@@ -1,4 +1,4 @@
-Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,DispatchNs,BeginNs,EndNs,CompleteNs
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
 0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,225228,225228,33554432,256,0,0,4,32,4160,0x0,0x7f9f58604280,17618191082395,17618191108316,17618191348476,17618191437046
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,225228,225228,32768,256,0,0,12,24,13888,0x0,0x7f9f58623f80,17618196106138,17618196121120,17618196134240,17618196153037
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,225228,225228,4194304,256,0,0,12,24,14336,0x7f9f770e3380,0x7f9f58623fc0,17618196155947,17618196205120,17618196297920,17618196300333