llnl / llnl/RAJAPerf

Add kernels broken up over multiple loops

Open
#381 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Add version of some kernels that break the iteration space into multiple subdomains and run a loop over each.
The intention is to compare performance when using a single loop to cover all the data or using multiple loops to cover the data.
Kernels to look at first:
- Stream_TRIAD
- Algorithm_REDUCE_SUM
- Basic_INDEXLIST_3LOOP

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

Locate the implementations and benchmark entry points for Stream_TRIAD, Algorithm_REDUCE_SUM, and Basic_INDEXLIST_3LOOP. First compare how each currently covers its iteration space, then add versions that run across multiple subdomains. Done means the alternate kernels can be benchmarked against the single-loop versions for performance comparison.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
performance
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.