Share primary CUDA context on the same device#10
Merged
Conversation
Contributor
Author
|
Looks like |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 PR refactors the code so that the primary CUDA context is shared when multiple
GCMCSamplersare created on the same GPU device, i.e. we usereatain_primary_context()rather thanmake_context(). This reduces GPU memory overhead by roughly ~230 MiB per additional sampler.The kernel code has also been refactored to avoid the use of compile-time constants, meaning that the kernel code now only needs to be compiled once, regardless of the system topology, allowing it to be cached and re-used across samplers.