test MPI GPU awareness using Send/Recv instead of MPI_Allreduce #310
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
For some obscure reason, MPI_AllReduce with openmpi is broken when using cuda arrays on OpenMPI 4.1.5. This led idefix to think that it is not running a cuda-aware library on JeanZay with H100 GPUs (for which only openmpi 4.1.5 is available).
This issue might be related to open-mpi/ompi#9845
Since Idefix does not use reduction operations on GPUs, but only Send/Recv, this PR patch this problem by testing the MPI library with Send/Recv instead of AllReduce to detect non-Cuda Aware libraries.