Fix: fix a deadlock bug in CUDA version of gint #5210
Merged
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
caic99
approved these changes
Oct 9, 2024
goodchong
approved these changes
Oct 10, 2024
mohanchen
added
the
Bugs
mohanchen
approved these changes
Oct 10, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.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.
Background
I find that in some examples if the
deviceis set togpuand the number of MPI processes is set too high, the program would hang indefinitely. Upon investigation, it was found that the deadlock was caused by an implicit barrier in MPI.Due to the condition
max_atom > 0, some processes do not execute thegint_vl_gpufunction. However, thegint_vl_gpufunction contains an implicit MPI barrier within theset_device_by_rankfunction, which leads to a deadlock. This PR fixes this bug.