Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

could use runtime detection of problematic hwloc with Intel Ponte Vecchio accelerators #2893

Closed
hppritcha opened this issue Dec 23, 2022 · 2 comments

Comments

@hppritcha
Copy link
Contributor

It appears that hwloc 2.7.x and older don't work right with Intel processors sporting Ponte Vecchio accelerators. For example, lstopo segfaults. prte also segfaults in a similar way.

It would be useful to have some runtime check in either prte or pmix to see if the hwloc version it is linked against is too old for such processors.

I do not know a good way to do this runtime check at the moment.

@rhc54
Copy link
Contributor

rhc54 commented Dec 23, 2022

I know how to do it (or at least, I believe I do) - I'll take a crack at it.

@rhc54
Copy link
Contributor

rhc54 commented Jan 11, 2023

I believe we concluded on the OMPI ticket that we won't do this as (per discussion on the PMIx telecon) other subsystems will be segfaulting when using HWLOC, so our trying to provide a "canary" really doesn't help enough to justify the amount of effort it would require.

@rhc54 rhc54 closed this as completed Jan 11, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants