llnl / llnl/dataracebench

a possible new pattern from NPB LU

Open
#130 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C
Stars
80
Forks
33
PR merge metrics
No merged PRs in 30d

Description

For LU, two tools (Intel Inspector and Archer)can analyze it without crashes or timeout. Both tools report that a function named blts has data races. Our investigation finds that blts has two parallel loops using nowait, combined with a flush directive to synchronize memory operations. None of the two tools can recognize this complicated code pattern.

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 locating the NPB LU `blts` function and reviewing its two parallel loops with `nowait` and the `flush` directive. Compare the reported behavior from Intel Inspector and Archer, then determine whether this pattern should be represented in the benchmark suite; completion requires a clear scope and decision for the proposed benchmark pattern.

Written by the indexing model from the issue text.

Assessment

Tech stack
c
Domain
testing-qa
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.