E3SM-Project / E3SM-Project/HOMMEXX

On white, 8 point threads and 64 vertical threads hangs

Open
#121 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
Fortran
Stars
11
Forks
0
PR merge metrics
No merged PRs in 30d

Description

It's not clear what the cause is, but HOMMEXX appears to hang in repro_sum_int when running with 8 point threads and 64 vertical threads. gdb says it's actually called poll from the parallel library (IIRC), so it's potentially another issue with MPI.

Contributor guide

No contributing guide indexed for this repository

Research direction

Reproduce the hang with 8 point threads and 64 vertical threads, then inspect the stack around repro_sum_int and poll in the parallel library. Determine whether the wait is caused by MPI or another parallel-runtime issue; done means the configuration no longer hangs or the responsible external component is documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
fortran
Domain
hpc
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.