llnl / llnl/RAJAPerf

Kokkos Variant Checksum Differences

Open
#598 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
135
Forks
55
Avg merge
4d 16h
Merged PRs (30d)
5

Description

Some kokkos variants produce a checksum that is significantly different than the other variants.

I compiled with mvapich 2.3.7 gcc 11.2.1 and ran with 36 ranks.

The difference between checksums should be negligible, less than 1e-10. This is printed in the RAJAPerf-checksum.txt output file.

Affected kernels:

  • Basic_ARRAY_OF_PTRS
  • Basic_PI_ATOMIC
  • Basic_REDUCE3_INT
  • Apps_NODAL_ACCUMULATION_3D

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the checksum comparison with the reported MVAPICH 2.3.7, GCC 11.2.1, and 36-rank setup, then inspect RAJAPerf-checksum.txt for the listed affected kernels. Done means determining why the Kokkos variants differ and bringing their checksum differences below 1e-10.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.