slowness of threading runs in ufs-weather-model #474
Assignees
Labels
bug
Something isn't working
Comments
|
isnt there a PR related to this ? |
|
Dom has an fv3atm PR #258 <NOAA-EMC/fv3atm#258>
ready to fix the issue.
…On Sat, Mar 13, 2021 at 7:45 PM arun chawla ***@***.***> wrote:
isnt there a PR related to this ?
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#474 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AI7D6TM7WS4MREMFHDMAYN3TDP2JRANCNFSM4ZDHHBXA>
.
|
|
Fix was merged in PR #383 |
epic-cicd-jenkins
pushed a commit
that referenced
this issue
Apr 17, 2023
#474) * Export OMP settings in the make_orog ex-script and change the default KMP_AFFINITY for the make_orog task to match WCOSS. * Add export command to all OMP settings in each ex-script.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Description
Provide a clear and concise description of what the bug is.
A slowness was found when using the recent ufs-weather-model develop branch. It was identified that it is from ufs-weather-mode PR #425, so far it only impacts the threading test, it is not seen in the tests with 1 thread. In LAM parallel run when using this revision, the running time is increase from 4800s->7700s. It is also seen in the ufs-weather-model threading test fv3_ccpp_2threads test.
To Reproduce:
What compilers/machines are you seeing this with?
Check out ufs-weather-model, run fv3_ccpp_2threads test, the run time is increased to 49s compared to 42s from previous revision.
The text was updated successfully, but these errors were encountered: