Fully asynchronous MPI backend #725
Draft
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
Also contains profiling of MPI operations. Signed-off-by: Joseph Schuchart <joseph.schuchart@stonybrook.edu>
Signed-off-by: Joseph Schuchart <joseph.schuchart@stonybrook.edu>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
This is work I did for the SPMM benchmark in TTG. Problem is that many threads push active messages into the communication backend, getting stuck in MPI. The communication thread becomes the bottleneck. In this PR we spawn extra threads that extract messages from the network. Threads pushing messages into the communication backend put them into a queue that is handled by the communication thread.
Putting this out here so it's not lost. Could become a component but I don't have time to make the comm engine an MCA.