Skip to content

Conversation

@artv3
Copy link
Member

@artv3 artv3 commented Jan 9, 2026

Summary

Adds two helper scripts to 1. generate performance data, and 2. plot and study throughput using python tools

Instructions for using this are here: https://rzlc.llnl.gov/confluence/spaces/RD/pages/919896250/Processing+RAJAPerf+data

@artv3 artv3 requested review from a team and rhornung67 January 9, 2026 22:58
## Run all benchmark kernels for GPU, non-lambda variants only
## on 4 MPI ranks and dump the results in the specified directory.

flux alloc -xN1 -t 20 bash -c '
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should we add a slurm version?

--outfile "${KERNEL_NAME}_factor_${factor}" \
--sizefact "$factor" \
--warmup-perfrun-same \
-ev Seq Lambda
Copy link
Member

@MrBurmark MrBurmark Jan 14, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do we want to compare to an mpi everywhere (sequential, rank per core) version?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants