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",0,0,0,889519,889524,33554432,256,0,0,8,32,6464,0x0,0x7fade3204180,505329,505329,524288,6291456,792877,101561476,12075726469398590,12075726714802415,12075726715127053,12075726715240096
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,889519,889524,32768,256,0,0,24,24,12480,0x0,0x7fade3235100,28706,28706,512,8192,9185,1175988,12075726729418195,12075726729733214,12075726729739934,12075726729747417
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,889519,889524,4194304,256,0,0,24,24,12928,0x7faf1355c900,0x7fade3235140,213227,213227,65536,917504,139653,17875436,12075726729813149,12075726730045212,12075726730174971,12075726730179210
@@ -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",0,0,0,891318,891323,33554432,256,0,0,8,32,6464,0x0,0x7fc0d7a04180,0,0,0,12075752974042678,12075753221733652,12075753222060211,12075753222176363
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,891318,891323,32768,256,0,0,24,24,12480,0x0,0x7fc0d7a35100,0,0,0,12075753236901319,12075753237218745,12075753237225305,12075753237239437
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,891318,891323,4194304,256,0,0,24,24,12928,0x7fc207c54900,0x7fc0d7a35140,0,0,0,12075753237289390,12075753237550103,12075753237689623,12075753237693862
@@ -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",0,0,0,890939,890944,33554432,256,0,0,8,32,6464,0x0,0x7f8564a04180,4194304,3065390,392527368,12075750428536136,12075750672999908,12075750673325666,12075750673439498
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,890939,890944,32768,256,0,0,24,24,12480,0x0,0x7f8564a35100,512,19888,2551816,12075750688487414,12075750688799270,12075750688805350,12075750688810875
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,890939,890944,4194304,256,0,0,24,24,12928,0x7f86705c7900,0x7f8564a35140,65536,164124,20967296,12075750688875716,12075750689167108,12075750689305348,12075750689309763
@@ -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",0,0,0,891129,891134,33554432,256,0,0,8,32,6464,0x0,0x7f6bf5a04180,1048576,11211256,1434098376,12075751698989828,12075751948059256,12075751948385175,12075751948497607
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,891129,891134,32768,256,0,0,24,24,12480,0x0,0x7f6bf5a35100,4096,110042,14095848,12075751963395575,12075751963698309,12075751963704549,12075751963709468
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,891129,891134,4194304,256,0,0,24,24,12928,0x7f6d01626900,0x7f6bf5a35140,524288,12978555,1661180292,12075751963773006,12075751963993988,12075751964122787,12075751964126553
@@ -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",0,0,0,891508,891513,33554432,256,0,0,8,32,6464,0x0,0x7f3019604180,499350,499350,16307,3994808,524288,366187131,3797807,0,1479546076,12075754251090885,12075754495567939,12075754495889537,12075754496009475
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,891508,891513,32768,256,0,0,24,24,12480,0x0,0x7f3019635100,27998,27998,20958,223992,512,1150884,77352,0,4617544,12075754510868550,12075754511211259,12075754511217979,12075754511227137
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,891508,891513,4194304,256,0,0,24,24,12928,0x7f3125360900,0x7f3019635140,215716,215716,22358,1725736,65536,144148643,1567089,0,578410044,12075754511296295,12075754511540537,12075754511672537,12075754511676271
@@ -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]",1,6055628.0,6055628.0,6055628.0,9.164480938887923
 "void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",1,4526201.0,4526201.0,4526201.0,6.849873009054627
 "void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,3054533.0,3054533.0,3054533.0,4.62267653424288
@@ -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,33917.877889484706,2767.5569458007812,547956.5804443359,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,31.0,vl1_stall_
-LDS Lat,,lds_lat_
+LDS_Per_Workgroup Lat,,lds_lat_
 vL1D Lat,,sl1_lat_
 IL1 Lat,,il1_lat_
 Wave Occupancy,37.0,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,59.59200061950603,Pct,100,59.59200061950603
 MFMA Util,,Pct,100,
 VALU Active Threads/Wave,63.96947733475583,Threads,64,99.95230833555598
 IPC - Issue,0.8437420287965051,Instr/cycle,5,16.8748405759301
-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,99.99342432649306,Pct,100,99.99342432649306
 Instr Cache BW,1407.2673827157548,Gb/s,4614.144,30.49899142106867
 Scalar L1D Cache Hit Rate,99.35620448525918,Pct,100,99.35620448525918
@@ -6,7 +6,7 @@ Scratch Stall,0.0,0,0,Cycles
 Insufficient SIMD Waveslots,61976.520958083835,0,735930,Simd
 Insufficient SIMD VGPRs,542399.497005988,0,29155875,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
-kernels,vesuvius,AMD EPYC 7542 32-Core Processor,,4.18.0-240.15.1.el8_3.x86_64,4.2.0-21,Thu Sep 22 11:21:41 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
+kernels,vesuvius,AMD EPYC 7542 32-Core Processor,,4.18.0-240.15.1.el8_3.x86_64,4.2.0-21,Thu Sep 22 11:21:41 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",0,0,0,891557,891562,33554432,256,0,0,8,32,6464,0x0,0x7fbba9204180,12075755395432052,12075755395473365,12075755395797202,12075755395906163
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,891557,891562,32768,256,0,0,24,24,12480,0x0,0x7fbba9235100,12075755411537444,12075755411649045,12075755411655605,12075755411661073
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,891557,891562,4194304,256,0,0,24,24,12928,0x7fbcb4f48900,0x7fbba9235140,12075755411717368,12075755411733204,12075755411873363,12075755411876484
@@ -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",0,0,0,188020,188020,33554432,256,0,0,4,32,4160,0x0,0x7ff003604280,381872,381872,524288,4718592,680045,76238404,17018811649857,17018099819752,17018955121694,17018955231973
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,188020,188020,32768,256,0,0,12,24,13888,0x0,0x7ff003623f80,32726,32726,512,8192,7488,835840,17018960426954,17018955121694,17018960558647,17018960563330
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,188020,188020,4194304,256,0,0,12,24,14336,0x7ff0066f6380,0x7ff003623fc0,165172,165172,65536,917504,152878,17126672,17018960599629,17018960558647,17018960927606,17018960930139
@@ -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",0,0,0,189868,189868,33554432,256,0,0,4,32,4160,0x0,0x7f8aad404280,0,0,0,17038275188179,17037561541743,17038422398116,17038422510425
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,189868,189868,32768,256,0,0,12,24,13888,0x0,0x7f8aad423f80,0,0,0,17038427681418,17038422398116,17038427809460,17038427814184
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,189868,189868,4194304,256,0,0,12,24,14336,0x7f8ab035f380,0x7f8aad423fc0,0,0,0,17038427847943,17038427809460,17038428182419,17038428185163
@@ -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",0,0,0,187798,187798,33554432,256,0,0,4,32,4160,0x0,0x7fdf25a04280,3670016,2898156,324749792,17017871486203,17004563619503,17018017050409,17018017164238
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,187798,187798,32768,256,0,0,12,24,13888,0x0,0x7fdf25a23f80,512,100390,11234352,17018022229652,17018017050409,17018022366561,17018022371497
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,187798,187798,4194304,256,0,0,12,24,14336,0x7fdf28a16380,0x7fdf25a23fc0,65536,646794,72359192,17018022406216,17018022366561,17018022736641,17018022739477
@@ -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",0,0,0,189646,189646,33554432,256,0,0,4,32,4160,0x0,0x7f9d56804280,524288,5490901,614983748,17037332490146,17034965056754,17037481413903,17037481526322
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,189646,189646,32768,256,0,0,12,24,13888,0x0,0x7f9d56823f80,4096,35384,3967344,17037486684195,17037481413903,17037486810049,17037486814861
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,189646,189646,4194304,256,0,0,12,24,14336,0x7f9d5979f380,0x7f9d56823fc0,524288,10971179,1228733104,17037486847540,17037486810049,17037487179488,17037487182511
@@ -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",0,0,0,188242,188242,33554432,256,0,0,4,32,4160,0x0,0x7fd4a6804280,388284,388284,8778,3106280,524288,244967804,3019488,0,996171404,17019739890511,17019036428116,17019885027682,17019885140781
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,188242,188242,32768,256,0,0,12,24,13888,0x0,0x7fd4a6823f80,33728,33728,30230,269832,512,1693019,164026,0,6785384,17019890314053,17019885027682,17019890453268,17019890458139
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,188242,188242,4194304,256,0,0,12,24,14336,0x7fd4a9882380,0x7fd4a6823fc0,164607,164607,14285,1316864,65536,82622429,1217167,0,332218900,17019890502057,17019890453268,17019890848147,17019890850967
@@ -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]",1,3356953.0,3356953.0,3356953.0,7.844214293382022
 "void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1724636.0,1724636.0,1724636.0,4.02996835585163
 "void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",1,1715197.0,1715197.0,1715197.0,4.007912182078797
@@ -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,18383.545308552817,1896.5850219726562,258014.9185180664,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,58.383802523427974,Pct,100,58.383802523427974
 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,99.9926058738864,Pct,100,99.9926058738864
 Instr Cache BW,1674.7745445510106,Gb/s,6092.8,27.487764977531032
 Scalar L1D Cache Hit Rate,99.34855886084364,Pct,100,99.34855886084364
@@ -6,7 +6,7 @@ Scratch Stall,0.0,0,0,Cycles
 Insufficient SIMD Waveslots,12620403.994011976,0,383533081,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
-kernels,06fa5f860366,AMD EPYC 7282 16-Core Processor,Ubuntu 20.04.5 LTS,5.11.0-27-generic,5.1.3-66,Wed Sep 28 20:36:58 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
+kernels,06fa5f860366,AMD EPYC 7282 16-Core Processor,Ubuntu 20.04.5 LTS,5.11.0-27-generic,5.1.3-66,Wed Sep 28 20:36:58 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",0,0,0,189951,189951,33554432,256,0,0,4,32,4160,0x0,0x7fefa1004280,17039094299446,17039094324187,17039094564027,17039094645986
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,189951,189951,32768,256,0,0,12,24,13888,0x0,0x7fefa1023f80,17039099396231,17039099412016,17039099425136,17039099444229
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,189951,189951,4194304,256,0,0,12,24,14336,0x7fefa40a4380,0x7fefa1023fc0,17039099447889,17039099497936,17039099590576,17039099592655