Fix resize! when pool=none is in use
#2613
Merged
Conversation
This file contains 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
|
Would it be possible to get this fix included in a patch release soon? |
|
Yes, but I want to finalize the cached allocator implementation first. |
avik-pal
pushed a commit
to avik-pal/CUDA.jl
that referenced
this pull request
Jan 11, 2025
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Outdated suggestions cannot be applied.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.
This PR addresses the issue where calling
resize!errors if the CUDA memory pool is disabled. The use case is e.g. when using CUDA-aware MPI, which currently requires to disable the memory pool.This PR replaces the
allocfunction used inresize!bypool_alloc, which now correctly captures the usage of a memory pool and would default to non-asynchronous memory initialisation if the usage of a memory pool is disabled.In addition, this PR also defaults the async keyword argument in
alloctofalseinstead of making ittrueif the target device supports a memory pool.