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
@@ -256,7 +256,7 @@ def test_no_roof_mixbench1_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_no_roof_TA_mi100():
@@ -333,7 +333,7 @@ def test_analyze_K_str_inv3_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_K_str_inv3_mi200():
@@ -344,7 +344,7 @@ def test_K_str_inv3_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_LDS_mi100():
@@ -654,7 +654,7 @@ def test_analyze_no_roof_D_int_inv2_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_no_roof_D_int_inv2_mi200():
@@ -665,7 +665,7 @@ def test_no_roof_D_int_inv2_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_TD_mi100():
@@ -745,7 +745,7 @@ def test_no_roof_mixbench2_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_roof_only_SPI_mi200():
@@ -789,7 +789,7 @@ def test_analyze_K_str_inv1_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_K_str_inv1_mi200():
@@ -800,7 +800,7 @@ def test_K_str_inv1_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_roof_only_TA_mi200():
@@ -1037,7 +1037,7 @@ def test_analyze_K_int_inv2_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_K_int_inv2_mi200():
@@ -1048,7 +1048,7 @@ def test_K_int_inv2_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_roof_only_TCP_mi200():
@@ -1086,7 +1086,7 @@ def test_analyze_D_int_inv2_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_D_int_inv2_mi200():
@@ -1097,7 +1097,7 @@ def test_D_int_inv2_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_roof_only_Axes3_mi200():
@@ -1263,7 +1263,7 @@ def test_analyze_no_roof_K_int_inv1_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_no_roof_K_int_inv1_mi200():
@@ -1274,7 +1274,7 @@ def test_no_roof_K_int_inv1_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_no_roof_Axes1_mi100():
@@ -1365,7 +1365,7 @@ def test_analyze_K_str_inv2_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_K_str_inv2_mi200():
@@ -1376,7 +1376,7 @@ def test_K_str_inv2_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_CPC_mi100():
@@ -1428,7 +1428,7 @@ def test_roof_only_mixbench2_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_Axes4_mi100():
@@ -1572,7 +1572,7 @@ def test_analyze_no_roof_K_str_inv3_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_no_roof_K_str_inv3_mi200():
@@ -1583,7 +1583,7 @@ def test_no_roof_K_str_inv3_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_no_roof_K_str_inv2_mi100():
@@ -1594,7 +1594,7 @@ def test_analyze_no_roof_K_str_inv2_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_no_roof_K_str_inv2_mi200():
@@ -1605,7 +1605,7 @@ def test_no_roof_K_str_inv2_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_D_str_inv2_mi100():
@@ -1679,7 +1679,7 @@ def test_analyze_CMD_INV_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_K_int_inv1_mi100():
@@ -1690,7 +1690,7 @@ def test_analyze_K_int_inv1_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_K_int_inv1_mi200():
@@ -1701,7 +1701,7 @@ def test_K_int_inv1_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_mixbench2_mi100():
@@ -1723,7 +1723,7 @@ def test_mixbench2_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_roof_only_Double_N_flag_mi200():
@@ -1739,7 +1739,7 @@ def test_roof_only_Double_N_flag_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_no_roof_TD_mi100():
@@ -1879,7 +1879,7 @@ def test_no_roof_Double_N_flag_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_Double_N_flag_mi100():
@@ -1901,7 +1901,7 @@ def test_Double_N_flag_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_roof_only_K_int_inv1_mi200():
@@ -1933,7 +1933,7 @@ def test_analyze_no_roof_K_str_valid_1_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_no_roof_K_str_valid_1_mi200():
@@ -1965,7 +1965,7 @@ def test_roof_only_mixbench1_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_dev1_mi100():
@@ -1996,7 +1996,7 @@ def test_analyze_no_roof_K_str_inv1_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_no_roof_K_str_inv1_mi200():
@@ -2007,7 +2007,7 @@ def test_no_roof_K_str_inv1_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_K_str_valid_1_mi100():
@@ -2018,7 +2018,7 @@ def test_analyze_K_str_valid_1_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_K_str_valid_1_mi200():
@@ -2051,7 +2051,7 @@ def test_mixbench1_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_no_roof_CMD_INV_mi100():
@@ -2062,7 +2062,7 @@ def test_analyze_no_roof_CMD_INV_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_roof_only_D_str_inv1_mi200():
@@ -2122,7 +2122,7 @@ def test_analyze_D_int_inv1_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_D_int_inv1_mi200():
@@ -2133,7 +2133,7 @@ def test_D_int_inv1_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_K_str_valid_2_mi100():
@@ -2292,7 +2292,7 @@ def test_analyze_no_roof_D_int_inv1_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_no_roof_D_int_inv1_mi200():
@@ -2303,7 +2303,7 @@ def test_no_roof_D_int_inv1_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_analyze_dispatches_mi100():
@@ -2347,7 +2347,7 @@ def test_analyze_no_roof_K_int_inv2_mi100():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1


 def test_no_roof_K_int_inv2_mi200():
@@ -2358,4 +2358,4 @@ def test_no_roof_K_int_inv2_mi200():
        ):
            omniperf.main()
    assert e.type == SystemExit
-    assert e.value.code == 0
+    assert e.value.code == 1
@@ -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",0,0,0,899514,899519,33554432,256,0,0,8,32,6464,0x0,0x7f1fa6004180,503617,503617,524288,6291456,791394,101370956,12075916066690965,12075916308968012,12075916309291690,12075916309401692
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,899514,899519,32768,256,0,0,24,24,12480,0x0,0x7f1fa6035100,28476,28476,512,8192,8822,1126348,12075916323842971,12075916324149848,12075916324156728,12075916324169417
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,899514,899519,4194304,256,0,0,24,24,12928,0x7f20b1c5c900,0x7f1fa6035140,219068,219068,65536,917504,139994,17933088,12075916324227495,12075916324447606,12075916324581365,12075916324585631
@@ -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",0,0,0,901311,901316,33554432,256,0,0,8,32,6464,0x0,0x7f8ba1604180,0,0,0,12075942327036344,12075942571037950,12075942571360189,12075942571463912
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,901311,901316,32768,256,0,0,24,24,12480,0x0,0x7f8ba1635100,0,0,0,12075942586056261,12075942586355119,12075942586361839,12075942586377678
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,901311,901316,4194304,256,0,0,24,24,12928,0x7f8cad17c900,0x7f8ba1635140,0,0,0,12075942586430637,12075942586646478,12075942586779597,12075942586783532
@@ -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",0,0,0,900933,900938,33554432,256,0,0,8,32,6464,0x0,0x7fde4da04180,4194304,3099050,396455528,12075939814530162,12075940060541623,12075940060866101,12075940060977444
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,900933,900938,32768,256,0,0,24,24,12480,0x0,0x7fde4da35100,512,21834,2778040,12075940075409134,12075940075710667,12075940075716907,12075940075730201
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,900933,900938,4194304,256,0,0,24,24,12928,0x7fdf5971c900,0x7fde4da35140,65536,170266,21950512,12075940075787127,12075940075998985,12075940076129225,12075940076133521
@@ -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",0,0,0,901123,901128,33554432,256,0,0,8,32,6464,0x0,0x7f34bac04180,1048576,11105144,1422096704,12075941073738305,12075941319842027,12075941320166985,12075941320278178
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,901123,901128,32768,256,0,0,24,24,12480,0x0,0x7f34bac35100,4096,114185,14602220,12075941334761004,12075941335062034,12075941335068594,12075941335073605
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,901123,901128,4194304,256,0,0,24,24,12928,0x7f35ead59900,0x7f34bac35140,524288,12413352,1588891204,12075941335135089,12075941335348753,12075941335481872,12075941335485801
@@ -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",0,0,0,901499,901504,33554432,256,0,0,8,32,6464,0x0,0x7f2728204180,503201,503201,16824,4025616,524288,368372692,3819010,0,1488255924,12075943579867225,12075943823748052,12075943824071410,12075943824181973
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,901499,901504,32768,256,0,0,24,24,12480,0x0,0x7f2728235100,27688,27688,20343,221512,512,1099987,74919,0,4414100,12075943838718799,12075943839049613,12075943839056013,12075943839064461
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,901499,901504,4194304,256,0,0,24,24,12928,0x7f2833ec6900,0x7f2728235140,226925,226925,20091,1815408,65536,115632522,1642353,0,464339996,12075943839137166,12075943839377931,12075943839516651,12075943839520970
@@ -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]",1,6051952.0,6051952.0,6051952.0,9.136726903467284
 "void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",1,4525565.0,4525565.0,4525565.0,6.832316497039289
 "void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,3050056.0,3050056.0,3050056.0,4.604717405604309
@@ -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,33669.99006456386,2852.8163681030273,547920.7350463867,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,35.0,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,59.58449821812784,Pct,100,59.58449821812784
 MFMA Util,,Pct,100,
 VALU Active Threads/Wave,63.967830830447085,Threads,64,99.94973567257357
 IPC - Issue,0.8437266214800547,Instr/cycle,5,16.874532429601096
-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,99.99343846471189,Pct,100,99.99343846471189
 Instr Cache BW,1402.474168265396,Gb/s,4614.144,30.39511051812418
 Scalar L1D Cache Hit Rate,99.35620448529356,Pct,100,99.35620448529356
@@ -6,7 +6,7 @@ Scratch Stall,0.0,0,0,Cycles
 Insufficient SIMD Waveslots,65959.77844311377,0,728283,Simd
 Insufficient SIMD VGPRs,582374.6826347306,0,30915166,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
-Axes1,vesuvius,AMD EPYC 7542 32-Core Processor,,4.18.0-240.15.1.el8_3.x86_64,4.2.0-21,Thu Sep 22 11:24:51 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
+Axes1,vesuvius,AMD EPYC 7542 32-Core Processor,,4.18.0-240.15.1.el8_3.x86_64,4.2.0-21,Thu Sep 22 11:24:51 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",0,0,0,901550,901555,33554432,256,0,0,8,32,6464,0x0,0x7f38b4604180,12075944713040777,12075944713091723,12075944713416199,12075944713499991
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,901550,901555,32768,256,0,0,24,24,12480,0x0,0x7f38b4635100,12075944728070880,12075944728173211,12075944728179771,12075944728183740
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,901550,901555,4194304,256,0,0,24,24,12928,0x7f39c020d900,0x7f38b4635140,12075944728232350,12075944728248250,12075944728379609,12075944728383171
@@ -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",0,0,0,200200,200200,33554432,256,0,0,4,32,4160,0x0,0x7f3043a04280,380449,380449,524288,4718592,680823,76291444,17230491852189,17229803716158,17230639935378,17230640050298
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,200200,200200,32768,256,0,0,12,24,13888,0x0,0x7f3043a23f80,33388,33388,512,8192,6035,679208,17230645228208,17230639935378,17230645362261,17230645367004
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,200200,200200,4194304,256,0,0,12,24,14336,0x7f304aaf0380,0x7f3043a23fc0,164997,164997,65536,917504,142337,15939976,17230645404843,17230645362261,17230645745301,17230645747704
@@ -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",0,0,0,202048,202048,33554432,256,0,0,4,32,4160,0x0,0x7ff18ec04280,0,0,0,17249839171366,17249136551505,17249986734818,17249986848227
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,202048,202048,32768,256,0,0,12,24,13888,0x0,0x7ff18ec23f80,0,0,0,17249992035347,17249986734818,17249992162336,17249992165533
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,202048,202048,4194304,256,0,0,12,24,14336,0x7ff191cc5380,0x7ff18ec23fc0,0,0,0,17249992202162,17249992162336,17249992490176,17249992492374
@@ -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",0,0,0,199978,199978,33554432,256,0,0,4,32,4160,0x0,0x7fe1d2a04280,3670016,3040452,340321896,17229574411755,17224026851585,17229723837237,17229723948727
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,199978,199978,32768,256,0,0,12,24,13888,0x0,0x7fe1d2a23f80,512,97598,10948992,17229729109777,17229723837237,17229729235641,17229729240263
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,199978,199978,4194304,256,0,0,12,24,14336,0x7fe1d5a50380,0x7fe1d2a23fc0,65536,619714,69394784,17229729274252,17229729235641,17229729595641,17229729597774
@@ -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",0,0,0,201826,201826,33554432,256,0,0,4,32,4160,0x0,0x7f4602604280,524288,5464894,612004276,17248909572510,17246651988621,17249056201395,17249056314154
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,201826,201826,32768,256,0,0,12,24,13888,0x0,0x7f4602623f80,4096,40146,4496804,17249061450266,17249056201395,17249061580271,17249061585092
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,201826,201826,4194304,256,0,0,12,24,14336,0x7f4605631380,0x7f4602623fc0,524288,10522350,1178437788,17249061620532,17249061580271,17249061951471,17249061954023
@@ -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",0,0,0,200422,200422,33554432,256,0,0,4,32,4160,0x0,0x7f294c004280,381872,381872,8673,3054984,524288,239943240,2968704,0,976030444,17231436888452,17230723230837,17231579793472,17231579902522
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,200422,200422,32768,256,0,0,12,24,13888,0x0,0x7f294c023f80,33766,33766,29849,270136,512,1763704,170161,0,7068488,17231585064932,17231579793472,17231585197473,17231585201818
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,200422,200422,4194304,256,0,0,12,24,14336,0x7f295a882380,0x7f294c023fc0,163877,163877,13443,1311024,65536,79496243,1203897,0,319710652,17231585245607,17231585197473,17231585576993,17231585579388
@@ -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]",1,3358076.0,3358076.0,3358076.0,7.841553576961169
 "void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1725119.0,1725119.0,1725119.0,4.028382045294292
 "void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",1,1715679.0,1715679.0,1715679.0,4.006338391199949
@@ -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,18370.77323406471,1864.6040878295898,258441.6922607422,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,58.34159376029337,Pct,100,58.34159376029337
 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,99.9925706103068,Pct,100,99.9925706103068
 Instr Cache BW,1672.543170726904,Gb/s,6092.8,27.45114185147886
 Scalar L1D Cache Hit Rate,99.34855886083365,Pct,100,99.34855886083365
@@ -6,7 +6,7 @@ Scratch Stall,0.0,0,0,Cycles
 Insufficient SIMD Waveslots,12537381.628742514,0,378193491,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
-Axes1,06fa5f860366,AMD EPYC 7282 16-Core Processor,Ubuntu 20.04.5 LTS,5.11.0-27-generic,5.1.3-66,Wed Sep 28 20:40:30 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
+Axes1,06fa5f860366,AMD EPYC 7282 16-Core Processor,Ubuntu 20.04.5 LTS,5.11.0-27-generic,5.1.3-66,Wed Sep 28 20:40:30 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",0,0,0,202131,202131,33554432,256,0,0,4,32,4160,0x0,0x7f6701a04280,17250653592721,17250653618423,17250653858583,17250653922762
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,202131,202131,32768,256,0,0,12,24,13888,0x0,0x7f6701a23f80,17250658683504,17250658698896,17250658712016,17250658729223
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,202131,202131,4194304,256,0,0,12,24,14336,0x7f6708902380,0x7f6701a23fc0,17250658734943,17250658782576,17250658874896,17250658877159
@@ -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",0,0,0,904528,904533,33554432,256,0,0,8,32,6464,0x0,0x7f5a30e04180,506681,506681,524288,6291456,792562,101549256,12076012262816271,12076012503553792,12076012503879230,12076012503985002
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,904528,904533,32768,256,0,0,24,24,12480,0x0,0x7f5a30e35100,28104,28104,512,8192,9287,1183436,12076012518518923,12076012518830984,12076012518837384,12076012518847614
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,904528,904533,4194304,256,0,0,24,24,12928,0x7f5b3c9cb900,0x7f5a30e35140,226931,226931,65536,917504,143322,18380728,12076012518910841,12076012519146822,12076012519285861,12076012519290988
@@ -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",0,0,0,906323,906328,33554432,256,0,0,8,32,6464,0x0,0x7fb332204180,0,0,0,12076038461953928,12076038708819104,12076038709143262,12076038709253764
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,906323,906328,32768,256,0,0,24,24,12480,0x0,0x7fb332235100,0,0,0,12076038723915542,12076038724221189,12076038724227589,12076038724233333
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,906323,906328,4194304,256,0,0,24,24,12928,0x7fb43df66900,0x7fb332235140,0,0,0,12076038724298003,12076038724512547,12076038724648707,12076038724652732
@@ -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",0,0,0,905945,905950,33554432,256,0,0,8,32,6464,0x0,0x7fa7a3804180,4194304,3115600,398554112,12076035960858082,12076036205207063,12076036205529621,12076036205637263
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,905945,905950,32768,256,0,0,24,24,12480,0x0,0x7fa7a3835100,512,23496,3012432,12076036220285436,12076036220589739,12076036220596459,12076036220601744
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,905945,905950,4194304,256,0,0,24,24,12928,0x7fa8d3833900,0x7fa7a3835140,65536,168548,21509560,12076036220667026,12076036220889098,12076036221020937,12076036221025311
@@ -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",0,0,0,906135,906140,33554432,256,0,0,8,32,6464,0x0,0x7f7a6cc04180,1048576,11145971,1426713976,12076037205083380,12076037454134301,12076037454459899,12076037454571422
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,906135,906140,32768,256,0,0,24,24,12480,0x0,0x7f7a6cc35100,4096,113752,14543000,12076037468977485,12076037469293867,12076037469300107,12076037469309622
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,906135,906140,4194304,256,0,0,24,24,12928,0x7f7b7879e900,0x7f7a6cc35140,524288,10196555,1305198640,12076037469370506,12076037469587946,12076037469726985,12076037469731186
@@ -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",0,0,0,906511,906516,33554432,256,0,0,8,32,6464,0x0,0x7f4586e04180,504246,504246,17548,4033976,524288,368605679,3827741,0,1489275812,12076039738087526,12076039982998365,12076039983322204,12076039983431627
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,906511,906516,32768,256,0,0,24,24,12480,0x0,0x7f4586e35100,28708,28708,21209,229672,512,1162927,78755,0,4666036,12076039998516141,12076039998845611,12076039998852011,12076039998860611
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,906511,906516,4194304,256,0,0,24,24,12928,0x7f46b6ef1900,0x7f4586e35140,226140,226140,22430,1809128,65536,121427759,1627144,0,487522204,12076039998932284,12076039999174090,12076039999311369,12076039999315967
@@ -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]",1,6052433.0,6052433.0,6052433.0,9.171253897560876
 "void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",1,4524925.0,4524925.0,4524925.0,6.856620476826534
 "void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,3048937.0,3048937.0,3048937.0,4.620055330586488
@@ -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,33836.997512908754,2849.70556640625,547887.5590209961,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,35.0,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,59.5755905790845,Pct,100,59.5755905790845
 MFMA Util,,Pct,100,
 VALU Active Threads/Wave,63.96707393468963,Threads,64,99.94855302295255
 IPC - Issue,0.8437193943979889,Instr/cycle,5,16.874387887959777
-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,99.99338555945363,Pct,100,99.99338555945363
 Instr Cache BW,1406.7885614971879,Gb/s,4614.144,30.488614171928482
 Scalar L1D Cache Hit Rate,99.3562044853132,Pct,100,99.3562044853132
@@ -6,7 +6,7 @@ Scratch Stall,0.0,0,0,Cycles
 Insufficient SIMD Waveslots,60911.161676646705,0,744296,Simd
 Insufficient SIMD VGPRs,664898.8263473054,0,39547083,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
-Axes2,vesuvius,AMD EPYC 7542 32-Core Processor,,4.18.0-240.15.1.el8_3.x86_64,4.2.0-21,Thu Sep 22 11:26:27 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
+Axes2,vesuvius,AMD EPYC 7542 32-Core Processor,,4.18.0-240.15.1.el8_3.x86_64,4.2.0-21,Thu Sep 22 11:26:27 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",0,0,0,906562,906567,33554432,256,0,0,8,32,6464,0x0,0x7f4385604180,12076040869119418,12076040869166673,12076040869490510,12076040869595163
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,906562,906567,32768,256,0,0,24,24,12480,0x0,0x7f4385635100,12076040884412370,12076040884512411,12076040884519291,12076040884525019
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,906562,906567,4194304,256,0,0,24,24,12928,0x7f44911b4900,0x7f4385635140,12076040884570664,12076040884584411,12076040884719290,12076040884722877
@@ -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",0,0,0,206291,206291,33554432,256,0,0,4,32,4160,0x0,0x7fb354204280,382773,382773,524288,4718592,681263,76371244,17335908726154,17335197539126,17336053148049,17336053256459
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,206291,206291,32768,256,0,0,12,24,13888,0x0,0x7fb354223f80,33913,33913,512,8192,6012,678776,17336058469361,17336053148049,17336058604217,17336058609087
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,206291,206291,4194304,256,0,0,12,24,14336,0x7fb3572f2380,0x7fb354223fc0,164212,164212,65536,917504,142050,15918288,17336058648376,17336058604217,17336058979578,17336058982747
@@ -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",0,0,0,208139,208139,33554432,256,0,0,4,32,4160,0x0,0x7fbdd4604280,0,0,0,17355253900417,17354557238840,17355396879913,17355396996993
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,208139,208139,32768,256,0,0,12,24,13888,0x0,0x7fbdd4623f80,0,0,0,17355402176137,17355396879913,17355402306797,17355402311693
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,208139,208139,4194304,256,0,0,12,24,14336,0x7fbdf30f6380,0x7fbdd4623fc0,0,0,0,17355402345302,17355402306797,17355402676558,17355402679014
@@ -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",0,0,0,206069,206069,33554432,256,0,0,4,32,4160,0x0,0x7fd4d7204280,3670016,3108234,348352984,17334968515481,17329900548710,17335117324819,17335117440069
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,206069,206069,32768,256,0,0,12,24,13888,0x0,0x7fd4d7223f80,512,95104,10667584,17335122621942,17335117324819,17335122750907,17335122755808
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,206069,206069,4194304,256,0,0,12,24,14336,0x7fd4da170380,0x7fd4d7223fc0,65536,625284,70022568,17335122790767,17335122750907,17335123118748,17335123121248
@@ -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",0,0,0,207917,207917,33554432,256,0,0,4,32,4160,0x0,0x7ff54c204280,524288,5490003,614888704,17354329285041,17352075152262,17354476649922,17354476742662
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,207917,207917,32768,256,0,0,12,24,13888,0x0,0x7ff54c223f80,4096,38964,4359388,17354481900826,17354476649922,17354482028645,17354482033612
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,207917,207917,4194304,256,0,0,12,24,14336,0x7ff56a9d1380,0x7ff54c223fc0,524288,10857982,1216044208,17354482068181,17354482028645,17354482412005,17354482414992
@@ -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",0,0,0,206513,206513,33554432,256,0,0,4,32,4160,0x0,0x7fd82ca04280,381343,381343,8981,3050752,524288,239919456,2962542,0,975899640,17336850338375,17336133839148,17336997386761,17336997497271
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,206513,206513,32768,256,0,0,12,24,13888,0x0,0x7fd82ca23f80,34251,34251,30792,274016,512,1814325,172534,0,7270928,17337002664734,17336997386761,17337002807885,17337002812960
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,206513,206513,4194304,256,0,0,12,24,14336,0x7fd82f967380,0x7fd82ca23fc0,164673,164673,13486,1317392,65536,85192702,1215418,0,342501352,17337002856539,17337002807885,17337003204845,17337003207389
@@ -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]",1,3357121.0,3357121.0,3357121.0,7.844852680402149
 "void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1725121.0,1725121.0,1725121.0,4.031227978040719
 "void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",1,1715680.0,1715680.0,1715680.0,4.009166439551139
@@ -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,18358.228336128646,1845.9439010620117,258547.47912597656,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,58.438695311565574,Pct,100,58.438695311565574
 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,99.99262226771893,Pct,100,99.99262226771893
 Instr Cache BW,1674.3011342593545,Gb/s,6092.8,27.479994981935306
 Scalar L1D Cache Hit Rate,99.34855885867488,Pct,100,99.34855885867488
@@ -6,7 +6,7 @@ Scratch Stall,0.0,0,0,Cycles
 Insufficient SIMD Waveslots,12167920.431137724,0,375186637,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
-Axes2,06fa5f860366,AMD EPYC 7282 16-Core Processor,Ubuntu 20.04.5 LTS,5.11.0-27-generic,5.1.3-66,Wed Sep 28 20:42:15 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
+Axes2,06fa5f860366,AMD EPYC 7282 16-Core Processor,Ubuntu 20.04.5 LTS,5.11.0-27-generic,5.1.3-66,Wed Sep 28 20:42:15 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",0,0,0,208222,208222,33554432,256,0,0,4,32,4160,0x0,0x7f3476804280,17356069269547,17356069295347,17356069536147,17356069651727
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,208222,208222,32768,256,0,0,12,24,13888,0x0,0x7f3476823f80,17356074343033,17356074359028,17356074372468,17356074389822
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,208222,208222,4194304,256,0,0,12,24,14336,0x7f34797dd380,0x7f3476823fc0,17356074394882,17356074454708,17356074547348,17356074549478
@@ -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",0,0,0,909520,909525,33554432,256,0,0,8,32,6464,0x0,0x7fe829004180,503321,503321,524288,6291456,793537,101537344,12076108055286022,12076108302996961,12076108303320479,12076108303432952
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,909520,909525,32768,256,0,0,24,24,12480,0x0,0x7fe829035100,28673,28673,512,8192,8944,1142220,12076108317782961,12076108318107515,12076108318114555,12076108318122752
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,909520,909525,4194304,256,0,0,24,24,12928,0x7fe934bda900,0x7fe829035140,226268,226268,65536,917504,141153,18044408,12076108318186060,12076108318412154,12076108318550713,12076108318555196
@@ -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",0,0,0,911318,911323,33554432,256,0,0,8,32,6464,0x0,0x7fd3d5804180,0,0,0,12076134384262348,12076134622186182,12076134622511940,12076134622624233
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,911318,911323,32768,256,0,0,24,24,12480,0x0,0x7fd3d5835100,0,0,0,12076134637155819,12076134637454058,12076134637461418,12076134637466817
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,911318,911323,4194304,256,0,0,24,24,12928,0x7fd4e1490900,0x7fd3d5835140,0,0,0,12076134637527059,12076134637740777,12076134637880296,12076134637884283
@@ -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",0,0,0,910940,910945,33554432,256,0,0,8,32,6464,0x0,0x7fbb29204180,4194304,3072326,393422784,12076131878204691,12076132121676698,12076132122000377,12076132122110910
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,910940,910945,32768,256,0,0,24,24,12480,0x0,0x7fbb29235100,512,21876,2797384,12076132136823112,12076132137121587,12076132137127667,12076132137132998
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,910940,910945,4194304,256,0,0,24,24,12928,0x7fbc34dd9900,0x7fbb29235140,65536,180780,23110632,12076132137192027,12076132137407986,12076132137546225,12076132137550373
@@ -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",0,0,0,911130,911135,33554432,256,0,0,8,32,6464,0x0,0x7fce0e804180,1048576,11191210,1432779132,12076133128428015,12076133372836595,12076133373159633,12076133373271216
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,911130,911135,32768,256,0,0,24,24,12480,0x0,0x7fce0e835100,4096,139531,17848416,12076133387891056,12076133388179520,12076133388186400,12076133388191895
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,911130,911135,4194304,256,0,0,24,24,12928,0x7fcf1a4b7900,0x7fce0e835140,524288,13108593,1678007364,12076133388256235,12076133388466559,12076133388596478,12076133388600154
@@ -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",0,0,0,911507,911514,33554432,256,0,0,8,32,6464,0x0,0x7f1631e04180,502997,502997,16972,4023984,524288,370817117,3823622,0,1498078928,12076135631582317,12076135876277375,12076135876600893,12076135876709715
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,911507,911514,32768,256,0,0,24,24,12480,0x0,0x7f1631e35100,27681,27681,20333,221456,512,1086316,73178,0,4359244,12076135891263753,12076135891585458,12076135891591698,12076135891600299
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,911507,911514,4194304,256,0,0,24,24,12928,0x7f173da09900,0x7f1631e35140,219780,219780,20940,1758248,65536,130207192,1588334,0,522643840,12076135891675879,12076135891912816,12076135892046576,12076135892050806
@@ -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]",1,6051953.0,6051953.0,6051953.0,9.186186363820095
 "void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",1,4526685.0,4526685.0,4526685.0,6.871000488653658
 "void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,3049736.0,3049736.0,3049736.0,4.629157439995196
@@ -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,33594.84124093427,2833.155448913574,547895.4530029297,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,28.0,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,59.26121204471573,Pct,100,59.26121204471573
 MFMA Util,,Pct,100,
 VALU Active Threads/Wave,63.96764040562569,Threads,64,99.94943813379014
 IPC - Issue,0.8437242718470235,Instr/cycle,5,16.874485436940468
-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,99.99349012530601,Pct,100,99.99349012530601
 Instr Cache BW,1412.884356723283,Gb/s,4614.144,30.62072524661742
 Scalar L1D Cache Hit Rate,99.35620448527392,Pct,100,99.35620448527392
@@ -6,7 +6,7 @@ Scratch Stall,0.0,0,0,Cycles
 Insufficient SIMD Waveslots,60134.077844311374,0,622478,Simd
 Insufficient SIMD VGPRs,601408.7185628742,0,40245662,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
-Axes3,vesuvius,AMD EPYC 7542 32-Core Processor,,4.18.0-240.15.1.el8_3.x86_64,4.2.0-21,Thu Sep 22 11:28:03 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
+Axes3,vesuvius,AMD EPYC 7542 32-Core Processor,,4.18.0-240.15.1.el8_3.x86_64,4.2.0-21,Thu Sep 22 11:28:03 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",0,0,0,911558,911563,33554432,256,0,0,8,32,6464,0x0,0x7f7f1e004180,12076136765385269,12076136765433491,12076136765754608,12076136765859220
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,911558,911563,32768,256,0,0,24,24,12480,0x0,0x7f7f1e035100,12076136780811589,12076136780918025,12076136780924425,12076136780930219
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,911558,911563,4194304,256,0,0,24,24,12928,0x7f8029b71900,0x7f7f1e035140,12076136780976144,12076136780988904,12076136781126183,12076136781129860
@@ -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",0,0,0,211749,211749,33554432,256,0,0,4,32,4160,0x0,0x7f820be04280,388008,388008,524288,4718592,680254,76306380,17414252801873,17413542112156,17414401629608,17414401745256
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,211749,211749,32768,256,0,0,12,24,13888,0x0,0x7f820be23f80,33769,33769,512,8192,6030,677892,17414406916492,17414401629608,17414407048166,17414407053268
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,211749,211749,4194304,256,0,0,12,24,14336,0x7f821a71d380,0x7f820be23fc0,166703,166703,65536,917504,144491,16197228,17414407090447,17414407048166,17414407430086,17414407432618
@@ -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",0,0,0,213597,213597,33554432,256,0,0,4,32,4160,0x0,0x7f841a404280,0,0,0,17433664805251,17432957069157,17433807278554,17433807370573
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,213597,213597,32768,256,0,0,12,24,13888,0x0,0x7f841a423f80,0,0,0,17433812524319,17433807278554,17433812649591,17433812654015
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,213597,213597,4194304,256,0,0,12,24,14336,0x7f841d3ae380,0x7f841a423fc0,0,0,0,17433812688524,17433812649591,17433813013911,17433813016086
@@ -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",0,0,0,211527,211527,33554432,256,0,0,4,32,4160,0x0,0x7f4688204280,3670016,3054154,341857152,17413315644610,17404579624633,17413463333343,17413463447223
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,211527,211527,32768,256,0,0,12,24,13888,0x0,0x7f4688223f80,512,96322,10800192,17413468616208,17413463333343,17413468744548,17413468748994
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,211527,211527,4194304,256,0,0,12,24,14336,0x7f468b1cd380,0x7f4688223fc0,65536,621694,69634176,17413468781314,17413468744548,17413469103109,17413469105425
@@ -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",0,0,0,213375,213375,33554432,256,0,0,4,32,4160,0x0,0x7f594ea04280,524288,5456862,611187468,17432727256629,17430416272901,17432876170783,17432876284272
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,213375,213375,32768,256,0,0,12,24,13888,0x0,0x7f594ea23f80,4096,47128,5279028,17432881448727,17432876170783,17432881577657,17432881582104
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,213375,213375,4194304,256,0,0,12,24,14336,0x7f5951a95380,0x7f594ea23fc0,524288,10541605,1180657360,17432881616473,17432881577657,17432881946617,17432881949174
@@ -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",0,0,0,211971,211971,33554432,256,0,0,4,32,4160,0x0,0x7fd3c5604280,387706,387706,8932,3101656,524288,245392945,3014196,0,997841304,17415188858019,17414483478312,17415335506950,17415335618980
 1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,211971,211971,32768,256,0,0,12,24,13888,0x0,0x7fd3c5623f80,33327,33327,29902,266624,512,1689948,155440,0,6773228,17415340755436,17415335506950,17415340894791,17415340899472
 2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,211971,211971,4194304,256,0,0,12,24,14336,0x7fd3c85c9380,0x7fd3c5623fc0,165887,165887,13893,1327104,65536,70614185,1216513,0,284194924,17415340943411,17415340894791,17415341281992,17415341284272
@@ -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]",1,3357122.0,3357122.0,3357122.0,7.843415692980662
 "void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1724161.0,1724161.0,1724161.0,4.028245456860141
 "void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",1,1715521.0,1715521.0,1715521.0,4.008059383316388
@@ -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
--- a/Ver más
+++ b/Ver más