Pytest add mi200 to analyze workloads (#334)

* Updated links in documentation. (#328) Updated to reflect new GitHub organization. Fixed broken links to GitHub pages. Signed-off-by: David Galiffi <David.Galiffi@amd.com> * update branch for 2.x documentation builds Signed-off-by: Karl W. Schulz <karl.schulz@amd.com> * update checkout action and use concurrency instead of cancel-workflow-action Signed-off-by: Karl W. Schulz <karl.schulz@amd.com> * test addition of user option for container launch Signed-off-by: Karl W. Schulz <karl.schulz@amd.com> * remove --user option for container, try chown instead Signed-off-by: Karl W. Schulz <karl.schulz@amd.com> * fixing yaml syntax Signed-off-by: Karl W. Schulz <karl.schulz@amd.com> * reorder job step - start with checkout Signed-off-by: Karl W. Schulz <karl.schulz@amd.com> * restore missing run directive Signed-off-by: Karl W. Schulz <karl.schulz@amd.com> * Update workloads to include log.txt Add missing MI200 workloads Signed-off-by: Jose Santos <josantos@amd.com> * Signed-off-by: Jose Santos <josantos@amd.com> Add vcopy workload for tests * Change exit codes for caught failures Signed-off-by: Jose Santos <josantos@amd.com> * reformat Signed-off-by: Jose Santos <josantos@amd.com> * Add pytest-xdist for pytest -n Signed-off-by: Jose Santos <josantos@amd.com> --------- Signed-off-by: David Galiffi <David.Galiffi@amd.com> Signed-off-by: Karl W. Schulz <karl.schulz@amd.com> Signed-off-by: Jose Santos <josantos@amd.com> Co-authored-by: David Galiffi <David.Galiffi@amd.com> Co-authored-by: Karl W. Schulz <karl.schulz@amd.com>
2024-03-25 10:20:31 -05:00
commit da506ad9b5
@@ -1 +1,4 @@
-Index,KernelName
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
+0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1295056,1295056,1048576,256,0,0,8,8,16,64,0x0,0x7fcafc83cec0,47758,47758,16384,65536,14395,1831576,1414609382362391,1414621055425142,1414621055449622,1414609390882981
+1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1295056,1295056,1048576,256,0,0,8,8,16,64,0x0,0x7fcafc83cec0,46493,46493,16384,65536,8138,1048588,1414609390906726,1414621055537142,1414621055556022,1414609391222231
+2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1295056,1295056,1048576,256,0,0,8,8,16,64,0x0,0x7fcafc83cec0,44994,44994,16384,65536,8169,1048584,1414609391254421,1414621055576182,1414621055595542,1414609391431225
@@ -0,0 +1,4 @@
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
+0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1295257,1295257,1048576,256,0,0,8,8,16,64,0x0,0x7ff0afd60ec0,0,0,0,1414609872531785,1414621055425142,1414621055449622,1414609880166996
+1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1295257,1295257,1048576,256,0,0,8,8,16,64,0x0,0x7ff0afd60ec0,0,0,0,1414609880186282,1414621055537142,1414621055556022,1414609880519821
+2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1295257,1295257,1048576,256,0,0,8,8,16,64,0x0,0x7ff0afd60ec0,0,0,0,1414609880548024,1414621055576182,1414621055595542,1414609880734476
@@ -0,0 +1,4 @@
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
+0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1295459,1295459,1048576,256,0,0,8,8,16,64,0x0,0x7fbaa9898ec0,65536,192926,24614264,1414610346774400,1414621055425142,1414621055449622,1414610354390535
+1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1295459,1295459,1048576,256,0,0,8,8,16,64,0x0,0x7fbaa9898ec0,65536,170544,21889328,1414610354409831,1414621055537142,1414621055556022,1414610354715538
+2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1295459,1295459,1048576,256,0,0,8,8,16,64,0x0,0x7fbaa9898ec0,65536,173974,22234656,1414610354743811,1414621055576182,1414621055595542,1414610354923470
@@ -0,0 +1,4 @@
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
+0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1295661,1295661,1048576,256,0,0,8,8,16,64,0x0,0x7fcdb12dcec0,32768,664178,85014096,1414610810961751,1414621055425142,1414621055449622,1414610818650923
+1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1295661,1295661,1048576,256,0,0,8,8,16,64,0x0,0x7fcdb12dcec0,32768,662767,84821212,1414610818672203,1414621055537142,1414621055556022,1414610818960106
+2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1295661,1295661,1048576,256,0,0,8,8,16,64,0x0,0x7fcdb12dcec0,32768,655809,83963416,1414610818988480,1414621055576182,1414621055595542,1414610819205870
@@ -0,0 +1,4 @@
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
+0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1295847,1295847,1048576,256,0,0,8,8,16,64,0x0,0x7f5c3f6e4ec0,48355,48355,17730,386848,16384,24958385,233718,0,100367700,1414611287019490,1414621055425142,1414621055449622,1414611294707580
+1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1295847,1295847,1048576,256,0,0,8,8,16,64,0x0,0x7f5c3f6e4ec0,43528,43528,13690,348232,16384,25762917,238429,0,103589552,1414611294736925,1414621055537142,1414621055556022,1414611295058863
+2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1295847,1295847,1048576,256,0,0,8,8,16,64,0x0,0x7f5c3f6e4ec0,43639,43639,13971,349120,16384,25009170,233467,0,100574040,1414611295096984,1414621055576182,1414621055595542,1414611295279148
@@ -0,0 +1,702 @@
+Omniperf version: 2.0.0-RC1
+Profiler choice: rocprofv1
+Path: /home1/josantos/omniperf/tests/workloads/kernel/MI100
+Target: MI100
+Command: ./tests/vcopy -n 1048576 -b 256 -i 3
+Kernel Selection: ['vecCopy']
+Dispatch Selection: None
+IP Blocks: All
+
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Collecting Performance Counters
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/SQ_IFETCH_LEVEL.txt
+   |-> [rocprof] RPL: on '240321_170755' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/SQ_IFETCH_LEVEL.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170755_1294896'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170755_1294896/input0_results_240321_170755'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170755_1294896/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 6 metrics
+   |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170755_1294896/input0_results_240321_170755
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/SQ_IFETCH_LEVEL.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_LDS.txt
+   |-> [rocprof] RPL: on '240321_170755' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_LDS.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170755_1295097'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170755_1295097/input0_results_240321_170755'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170755_1295097/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 3 metrics
+   |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170755_1295097/input0_results_240321_170755
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/SQ_INST_LEVEL_LDS.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt
+   |-> [rocprof] RPL: on '240321_170756' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170756_1295299'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170756_1295299/input0_results_240321_170756'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170756_1295299/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 3 metrics
+   |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170756_1295299/input0_results_240321_170756
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/SQ_INST_LEVEL_SMEM.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt
+   |-> [rocprof] RPL: on '240321_170756' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170756_1295501'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170756_1295501/input0_results_240321_170756'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170756_1295501/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 3 metrics
+   |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170756_1295501/input0_results_240321_170756
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/SQ_INST_LEVEL_VMEM.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/SQ_LEVEL_WAVES.txt
+   |-> [rocprof] RPL: on '240321_170757' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/SQ_LEVEL_WAVES.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170757_1295687'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170757_1295687/input0_results_240321_170757'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170757_1295687/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 9 metrics
+   |-> [rocprof] 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
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170757_1295687/input0_results_240321_170757
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/SQ_LEVEL_WAVES.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_0.txt
+   |-> [rocprof] RPL: on '240321_170757' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_0.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170757_1295888'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170757_1295888/input0_results_240321_170757'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170757_1295888/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 28 metrics
+   |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170757_1295888/input0_results_240321_170757
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_0.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_1.txt
+   |-> [rocprof] RPL: on '240321_170758' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_1.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170758_1296091'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170758_1296091/input0_results_240321_170758'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170758_1296091/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 27 metrics
+   |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170758_1296091/input0_results_240321_170758
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_1.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_10.txt
+   |-> [rocprof] RPL: on '240321_170758' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_10.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170758_1296294'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170758_1296294/input0_results_240321_170758'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170758_1296294/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 1 metrics
+   |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170758_1296294/input0_results_240321_170758
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_10.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_11.txt
+   |-> [rocprof] RPL: on '240321_170759' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_11.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170759_1296495'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170759_1296495/input0_results_240321_170759'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170759_1296495/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 128 metrics
+   |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31]
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170759_1296495/input0_results_240321_170759
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_11.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_12.txt
+   |-> [rocprof] RPL: on '240321_170759' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_12.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170759_1296697'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170759_1296697/input0_results_240321_170759'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170759_1296697/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 128 metrics
+   |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31]
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170759_1296697/input0_results_240321_170759
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_12.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_13.txt
+   |-> [rocprof] RPL: on '240321_170800' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_13.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170800_1296901'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170800_1296901/input0_results_240321_170800'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170800_1296901/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 128 metrics
+   |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31]
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170800_1296901/input0_results_240321_170800
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_13.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_14.txt
+   |-> [rocprof] RPL: on '240321_170801' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_14.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170801_1297099'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170801_1297099/input0_results_240321_170801'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170801_1297099/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 128 metrics
+   |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31]
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170801_1297099/input0_results_240321_170801
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_14.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_15.txt
+   |-> [rocprof] RPL: on '240321_170801' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_15.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170801_1297303'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170801_1297303/input0_results_240321_170801'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170801_1297303/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 128 metrics
+   |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31]
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170801_1297303/input0_results_240321_170801
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_15.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_16.txt
+   |-> [rocprof] RPL: on '240321_170802' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_16.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170802_1297506'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170802_1297506/input0_results_240321_170802'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170802_1297506/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 96 metrics
+   |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31]
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170802_1297506/input0_results_240321_170802
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_16.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_2.txt
+   |-> [rocprof] RPL: on '240321_170803' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_2.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170803_1297703'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170803_1297703/input0_results_240321_170803'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170803_1297703/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 26 metrics
+   |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170803_1297703/input0_results_240321_170803
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_2.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_3.txt
+   |-> [rocprof] RPL: on '240321_170803' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_3.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170803_1297890'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170803_1297890/input0_results_240321_170803'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170803_1297890/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 23 metrics
+   |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170803_1297890/input0_results_240321_170803
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_3.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_4.txt
+   |-> [rocprof] RPL: on '240321_170804' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_4.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170804_1298091'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170804_1298091/input0_results_240321_170804'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170804_1298091/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 22 metrics
+   |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170804_1298091/input0_results_240321_170804
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_4.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_5.txt
+   |-> [rocprof] RPL: on '240321_170804' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_5.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170804_1298276'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170804_1298276/input0_results_240321_170804'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170804_1298276/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 21 metrics
+   |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170804_1298276/input0_results_240321_170804
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_5.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_6.txt
+   |-> [rocprof] RPL: on '240321_170805' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_6.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170805_1298477'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170805_1298477/input0_results_240321_170805'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170805_1298477/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 20 metrics
+   |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170805_1298477/input0_results_240321_170805
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_6.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_7.txt
+   |-> [rocprof] RPL: on '240321_170805' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_7.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170805_1298679'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170805_1298679/input0_results_240321_170805'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170805_1298679/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 20 metrics
+   |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170805_1298679/input0_results_240321_170805
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_7.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_8.txt
+   |-> [rocprof] RPL: on '240321_170806' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_8.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170806_1298868'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170806_1298868/input0_results_240321_170806'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170806_1298868/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 17 metrics
+   |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170806_1298868/input0_results_240321_170806
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_8.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_9.txt
+   |-> [rocprof] RPL: on '240321_170806' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_9.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170806_1299070'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170806_1299070/input0_results_240321_170806'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170806_1299070/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 8 metrics
+   |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170806_1299070/input0_results_240321_170806
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_9.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/timestamps.txt
+   |-> [rocprof] RPL: on '240321_170807' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/timestamps.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170807_1299273'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170807_1299273/input0_results_240321_170807'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170807_1299273/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 0 metrics
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170807_1299273/input0_results_240321_170807
+   |-> [rocprof] File 'tests/workloads/kernel/MI100/timestamps.csv' is generating
+   |-> [rocprof] 
@@ -2,4 +2,4 @@ pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL  SQ_ACCUM_PRE

 gpu:
 range:
-kernel: "vecCopy(double*,,double*,,double*,,int,,int),[clone,.kd]"
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS  SQ_ACCUM_PREV_HIRES

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc: SQ_INSTS_SMEM  SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc: SQ_INSTS_VMEM  SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVE

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  TCC_EA_ATOMIC_LEVEL_sum

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATO

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_R

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] T

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VMEM_WR SQ_INSTS_VMEM

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH S

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_A

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYC

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_W

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -0,0 +1,4 @@
+Dispatch_ID,Kernel_Name,GPU_ID
+0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2
+1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2
+2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2
@@ -0,0 +1,2 @@
+workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
+kernel,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 05:07:54 PM  (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1
@@ -0,0 +1,4 @@
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
+0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1299433,1299433,1048576,256,0,0,8,8,16,64,0x0,0x7fc619c60ec0,1414621055400032,1414621055425142,1414621055449622,1414621055460846
+1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1299433,1299433,1048576,256,0,0,8,8,16,64,0x0,0x7fc619c60ec0,1414621055462319,1414621055537142,1414621055556022,1414621055557449
+2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1299433,1299433,1048576,256,0,0,8,8,16,64,0x0,0x7fc619c60ec0,1414621055567848,1414621055576182,1414621055595542,1414621055596913
@@ -1 +1,4 @@
-Index,KernelName
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
+0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4190428,4190428,1048576,256,0,0,8,0,16,64,0x0,0x7f94512c0ec0,27378,27378,16384,65536,13161,1467220,1414432756404789,1414445656659785,1414445656680105,1414432772257328
+1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4190428,4190428,1048576,256,0,0,8,0,16,64,0x0,0x7f94512c0ec0,40627,40627,16384,65536,9359,1048624,1414432772278037,1414445656699625,1414445656715145,1414432772686309
+2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4190428,4190428,1048576,256,0,0,8,0,16,64,0x0,0x7f94512c0ec0,40747,40747,16384,65536,9106,1048600,1414432772715755,1414445656774345,1414445656790665,1414432772875517
@@ -0,0 +1,4 @@
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
+0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4190642,4190642,1048576,256,0,0,8,0,16,64,0x0,0x7f6c840ecec0,0,0,0,1414433244984736,1414445656659785,1414445656680105,1414433261546075
+1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4190642,4190642,1048576,256,0,0,8,0,16,64,0x0,0x7f6c840ecec0,0,0,0,1414433261564100,1414445656699625,1414445656715145,1414433261863666
+2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4190642,4190642,1048576,256,0,0,8,0,16,64,0x0,0x7f6c840ecec0,0,0,0,1414433261890016,1414445656774345,1414445656790665,1414433262043226
@@ -0,0 +1,4 @@
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
+0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4190847,4190847,1048576,256,0,0,8,0,16,64,0x0,0x7f19e81d0ec0,65536,187730,20996312,1414433732354835,1414445656659785,1414445656680105,1414433748542708
+1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4190847,4190847,1048576,256,0,0,8,0,16,64,0x0,0x7f19e81d0ec0,65536,281018,31378144,1414433748560412,1414445656699625,1414445656715145,1414433748861932
+2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4190847,4190847,1048576,256,0,0,8,0,16,64,0x0,0x7f19e81d0ec0,65536,258024,28932200,1414433748888122,1414445656774345,1414445656790665,1414433749041842
@@ -0,0 +1,4 @@
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
+0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4191050,4191050,1048576,256,0,0,8,0,16,64,0x0,0x7fcf14168ec0,32768,306417,34321340,1414434204510803,1414445656659785,1414445656680105,1414434220573068
+1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4191050,4191050,1048576,256,0,0,8,0,16,64,0x0,0x7fcf14168ec0,32768,580620,65031856,1414434220596282,1414445656699625,1414445656715145,1414434220884157
+2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4191050,4191050,1048576,256,0,0,8,0,16,64,0x0,0x7fcf14168ec0,32768,586983,65717864,1414434220910687,1414445656774345,1414445656790665,1414434221039700
@@ -0,0 +1,4 @@
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
+0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4191237,4191237,1048576,256,0,0,8,0,16,64,0x0,0x7ffbe6b9cec0,27648,27648,11103,221192,16384,10666434,128024,0,43180252,1414434690769320,1414445656659785,1414445656680105,1414434706762735
+1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4191237,4191237,1048576,256,0,0,8,0,16,64,0x0,0x7ffbe6b9cec0,41673,41673,14419,333392,16384,19327058,223251,0,77801560,1414434706790227,1414445656699625,1414445656715145,1414434707222514
+2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4191237,4191237,1048576,256,0,0,8,0,16,64,0x0,0x7ffbe6b9cec0,41027,41027,13871,328224,16384,18889841,217781,0,76050388,1414434707257661,1414445656774345,1414445656790665,1414434707434395
@@ -0,0 +1,764 @@
+Omniperf version: 2.0.0-RC1
+Profiler choice: rocprofv1
+Path: /home1/josantos/omniperf/tests/workloads/kernel/MI200
+Target: MI200
+Command: ./tests/vcopy -n 1048576 -b 256 -i 3
+Kernel Selection: ['vecCopy']
+Dispatch Selection: None
+IP Blocks: All
+
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Collecting Performance Counters
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt
+   |-> [rocprof] RPL: on '240321_170500' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170500_4190268'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170500_4190268/input0_results_240321_170500'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170500_4190268/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 6 metrics
+   |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170500_4190268/input0_results_240321_170500
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/SQ_IFETCH_LEVEL.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt
+   |-> [rocprof] RPL: on '240321_170501' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170501_4190482'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170501_4190482/input0_results_240321_170501'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170501_4190482/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 3 metrics
+   |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170501_4190482/input0_results_240321_170501
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/SQ_INST_LEVEL_LDS.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt
+   |-> [rocprof] RPL: on '240321_170501' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170501_4190684'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170501_4190684/input0_results_240321_170501'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170501_4190684/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 3 metrics
+   |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170501_4190684/input0_results_240321_170501
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/SQ_INST_LEVEL_SMEM.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt
+   |-> [rocprof] RPL: on '240321_170502' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170502_4190890'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170502_4190890/input0_results_240321_170502'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170502_4190890/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 3 metrics
+   |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170502_4190890/input0_results_240321_170502
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/SQ_INST_LEVEL_VMEM.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt
+   |-> [rocprof] RPL: on '240321_170502' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170502_4191077'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170502_4191077/input0_results_240321_170502'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170502_4191077/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 9 metrics
+   |-> [rocprof] 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
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170502_4191077/input0_results_240321_170502
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/SQ_LEVEL_WAVES.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_0.txt
+   |-> [rocprof] RPL: on '240321_170502' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_0.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170502_4191279'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170502_4191279/input0_results_240321_170502'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170502_4191279/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 28 metrics
+   |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170502_4191279/input0_results_240321_170502
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_0.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_1.txt
+   |-> [rocprof] RPL: on '240321_170503' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_1.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170503_4191481'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170503_4191481/input0_results_240321_170503'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170503_4191481/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 27 metrics
+   |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170503_4191481/input0_results_240321_170503
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_1.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_10.txt
+   |-> [rocprof] RPL: on '240321_170503' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_10.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170503_4191685'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170503_4191685/input0_results_240321_170503'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170503_4191685/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 8 metrics
+   |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170503_4191685/input0_results_240321_170503
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_10.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_11.txt
+   |-> [rocprof] RPL: on '240321_170504' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_11.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170504_4191871'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170504_4191871/input0_results_240321_170504'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170504_4191871/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 8 metrics
+   |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170504_4191871/input0_results_240321_170504
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_11.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_12.txt
+   |-> [rocprof] RPL: on '240321_170504' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_12.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170504_4192073'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170504_4192073/input0_results_240321_170504'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170504_4192073/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 3 metrics
+   |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170504_4192073/input0_results_240321_170504
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_12.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_13.txt
+   |-> [rocprof] RPL: on '240321_170505' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_13.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170505_4192275'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170505_4192275/input0_results_240321_170505'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170505_4192275/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 128 metrics
+   |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31]
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170505_4192275/input0_results_240321_170505
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_13.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_14.txt
+   |-> [rocprof] RPL: on '240321_170506' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_14.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170506_4192465'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170506_4192465/input0_results_240321_170506'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170506_4192465/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 128 metrics
+   |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31]
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170506_4192465/input0_results_240321_170506
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_14.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_15.txt
+   |-> [rocprof] RPL: on '240321_170506' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_15.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170506_4192664'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170506_4192664/input0_results_240321_170506'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170506_4192664/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 128 metrics
+   |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31]
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170506_4192664/input0_results_240321_170506
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_15.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_16.txt
+   |-> [rocprof] RPL: on '240321_170507' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_16.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170507_4192866'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170507_4192866/input0_results_240321_170507'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170507_4192866/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 128 metrics
+   |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31]
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170507_4192866/input0_results_240321_170507
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_16.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_17.txt
+   |-> [rocprof] RPL: on '240321_170508' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_17.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170508_4193068'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170508_4193068/input0_results_240321_170508'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170508_4193068/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 128 metrics
+   |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31]
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170508_4193068/input0_results_240321_170508
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_17.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_18.txt
+   |-> [rocprof] RPL: on '240321_170508' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_18.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170508_4193269'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170508_4193269/input0_results_240321_170508'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170508_4193269/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 96 metrics
+   |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31]
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170508_4193269/input0_results_240321_170508
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_18.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_2.txt
+   |-> [rocprof] RPL: on '240321_170509' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_2.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170509_4193471'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170509_4193471/input0_results_240321_170509'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170509_4193471/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 26 metrics
+   |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170509_4193471/input0_results_240321_170509
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_2.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_3.txt
+   |-> [rocprof] RPL: on '240321_170510' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_3.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170510_4193673'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170510_4193673/input0_results_240321_170510'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170510_4193673/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 24 metrics
+   |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170510_4193673/input0_results_240321_170510
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_3.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_4.txt
+   |-> [rocprof] RPL: on '240321_170510' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_4.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170510_4193875'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170510_4193875/input0_results_240321_170510'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170510_4193875/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 22 metrics
+   |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170510_4193875/input0_results_240321_170510
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_4.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_5.txt
+   |-> [rocprof] RPL: on '240321_170510' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_5.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170510_4194077'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170510_4194077/input0_results_240321_170510'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170510_4194077/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 21 metrics
+   |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170510_4194077/input0_results_240321_170510
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_5.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_6.txt
+   |-> [rocprof] RPL: on '240321_170511' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_6.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170511_4194261'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170511_4194261/input0_results_240321_170511'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170511_4194261/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 20 metrics
+   |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170511_4194261/input0_results_240321_170511
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_6.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_7.txt
+   |-> [rocprof] RPL: on '240321_170511' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_7.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170511_672'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170511_672/input0_results_240321_170511'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170511_672/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 20 metrics
+   |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170511_672/input0_results_240321_170511
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_7.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_8.txt
+   |-> [rocprof] RPL: on '240321_170512' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_8.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170512_894'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170512_894/input0_results_240321_170512'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170512_894/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 17 metrics
+   |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170512_894/input0_results_240321_170512
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_8.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_9.txt
+   |-> [rocprof] RPL: on '240321_170512' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_9.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170512_1097'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170512_1097/input0_results_240321_170512'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170512_1097/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 12 metrics
+   |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170512_1097/input0_results_240321_170512
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_9.csv' is generating
+   |-> [rocprof] 
+
+[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/timestamps.txt
+   |-> [rocprof] RPL: on '240321_170513' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
+   |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
+   |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/timestamps.txt'
+   |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170513_1301'
+   |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170513_1301/input0_results_240321_170513'
+   |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170513_1301/input0.xml"
+   |-> [rocprof] gpu_index =
+   |-> [rocprof] kernel = vecCopy
+   |-> [rocprof] range =
+   |-> [rocprof] 0 metrics
+   |-> [rocprof] vcopy testing on GCD 0
+   |-> [rocprof] Finished allocating vectors on the CPU
+   |-> [rocprof] Finished allocating vectors on the GPU
+   |-> [rocprof] Finished copying vectors to the GPU
+   |-> [rocprof] sw thinks it moved 1.000000 KB per wave
+   |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
+   |-> [rocprof] Launching the  kernel on the GPU
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished executing kernel
+   |-> [rocprof] Finished copying the output vector from the GPU to the CPU
+   |-> [rocprof] Releasing GPU memory
+   |-> [rocprof] Releasing CPU memory
+   |-> [rocprof] 
+   |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170513_1301/input0_results_240321_170513
+   |-> [rocprof] File 'tests/workloads/kernel/MI200/timestamps.csv' is generating
+   |-> [rocprof] 
+[roofline] Checking for roofline.csv in tests/workloads/kernel/MI200
+[roofline] No roofline data found. Generating...
@@ -2,4 +2,4 @@ pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL  SQ_ACCUM_PRE

 gpu:
 range:
-kernel: "vecCopy(double*,,double*,,double*,,int,,int),[clone,.kd]"
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS  SQ_ACCUM_PREV_HIRES

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc: SQ_INSTS_SMEM  SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc: SQ_INSTS_VMEM  SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVE

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_IN

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VA

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_D

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMI

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATO

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_R

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] T

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INS

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_IN

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:  SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -2,4 +2,4 @@ pmc:

 gpu:
 range:
-kernel:
+kernel: vecCopy
@@ -0,0 +1,4 @@
+Dispatch_ID,Kernel_Name,GPU_ID
+0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2
+1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2
+2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2
@@ -0,0 +1,5 @@
+device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh
+0,1388.8003,1388.2018,1389.3988,5018.0034,5014.9653,5021.0415,9227.3828,9226.832,9227.9336,17715.787,17712.695,17718.879,20942.057,20881.729,21002.385,20273.387,20272.754,20274.02,170490.59,170486.83,170494.36,164905.91,164902.36,164909.45,41435.109,41434.566,41435.652,41490.23,41489.523,41490.938,166390.95,165895.59,166886.31
+1,1389.1022,1388.6135,1389.5908,5028.1416,5026.2451,5030.0381,9235.0059,9234.3955,9235.6162,18231.234,18229.113,18233.355,20975.01,20907.771,21042.248,20293.785,20293.287,20294.283,170865.64,170860.17,170871.11,165134.81,165131.06,165138.56,41491.012,41490.277,41491.746,41546.773,41546.109,41547.438,166891.17,166888.8,166893.55
+2,1388.7727,1388.2306,1389.3148,5035.6616,5033.3149,5038.0083,9261.2324,9260.5088,9261.9561,18217.076,18216.133,18218.02,21049.338,21048.953,21049.723,20351.391,20350.875,20351.906,171111.95,171108.86,171115.05,165494.22,165491.36,165497.08,41585.855,41584.934,41586.777,41643.219,41642.5,41643.938,166984.53,166391.91,167577.16
+3,1389.2549,1388.5906,1389.9192,5032.6069,5031.0239,5034.1899,9239.5078,9238.6982,9240.3174,18329.676,18328.783,18330.568,21036.42,21036.109,21036.73,20313.297,20312.844,20313.75,171033,171029.09,171036.91,165165.02,165160.69,165169.34,41426.988,41272.484,41581.492,41573.762,41572.508,41575.016,166972.52,166968.34,166976.69
@@ -0,0 +1,2 @@
+workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd
+kernel,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 05:04:59 PM  (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1
@@ -0,0 +1,4 @@
+Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
+0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1463,1463,1048576,256,0,0,8,0,16,64,0x0,0x7f09a4408ec0,1414445656634195,1414445656659785,1414445656680105,1414445656694409
+1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1463,1463,1048576,256,0,0,8,0,16,64,0x0,0x7f09a4408ec0,1414445656691093,1414445656699625,1414445656715145,1414445656771244
+2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1463,1463,1048576,256,0,0,8,0,16,64,0x0,0x7f09a4408ec0,1414445656725698,1414445656774345,1414445656790665,1414445656791793