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

comm_create_from_groups: cherrypick two commits from main to fix mpi4py comm create from group etc tests #12976

Open
wants to merge 2 commits into
base: v5.0.x
Choose a base branch
from

Conversation

hppritcha
Copy link
Member

Turns out we need parts of 95e3323 as well as 46ff698 to address some race conditions brought out by mpi4py comm create from group related tests.

Greatly simplify support for MPI_Comm_create_from_group and
MPI_Intercomm_create_from_group by removing the need to support
the 128-bit excid notion.

Only non-ucx related pieces of this commit where cherry-picked over to v5.0.x

(cherry picked from commit 95e3323)
Signed-off-by: Howard Pritchard <[email protected]>
to avoid potential race conditions between successive calls
to MPI_Comm_create_from_group and MPI_Intercomm_create_from_groups
when using the same tag argument value.

The PMIx group constructor grp string argument has different semantics
from the tag requirements for these MPI constructors, so use
discriminators to avoid potential race conditions when using PMIx group
ops.

Related to open-mpi#10895

Signed-off-by: Howard Pritchard <[email protected]>
(cherry picked from commit 46ff698)
@hppritcha hppritcha requested a review from janjust December 10, 2024 17:58
@github-actions github-actions bot added this to the v5.0.6 milestone Dec 10, 2024
@hppritcha
Copy link
Member Author

@janjust lets see how this does with mpi4py. i didn't want to include the UCX enhancements that went into main, so removed these from the cherry-pick of 95e3323

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant