$ salloc -A <project>-gpu -p gpu-dev --nodes=1 --ntasks=1 --gpus-per-task=1 --cpus-per-task=8
$ module load rocm/<VERSION>
$ module load craype-accel-amd-gfx90a
$ hipcc -o profileme profileme.cpp
$ srun --export=all rocprof ./profileme
RPL: on '230504_160218' from '/opt/rocm-5.0.2/rocprofiler' in '<current_dir>'
RPL: profiling '"./profileme"'
RPL: input file ''
RPL: output dir '/tmp/rpl_data_230504_160218_84697'
RPL: result dir '/tmp/rpl_data_230504_160218_84697/input_results_230504_160218'
ROCProfiler: input from "/tmp/rpl_data_230504_160218_84697/input.xml"
0 metrics
ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_230504_160218_84697/input_results_230504_160218
File '<local_path>/results.csv' is generating |