Refactor device capability checks, fix prefetching bug on WSL #2014
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
…ks to skip prefetching tests on WSL.
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
|
/ok to test b6a1242 |
bdice
added
non-breaking
2 tasks
TomAugspurger
approved these changes
Aug 21, 2025
Matt711
approved these changes
Aug 21, 2025
harrism
approved these changes
Aug 21, 2025
|
/merge |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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Outdated suggestions cannot be applied.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.
Description
Refactors device capability checks, add concurrent managed access checks to skip prefetching tests on WSL (not supported).
One motivation for this refactoring is that the previous names really didn't make much sense. We created the
runtime_async_alloc::is_supported()to check for CUDA 11.2+ support for runtime async allocation. However, we tacked on other features likeis_export_handle_type_supported(cudaMemAllocationHandleType)andis_hwdecompress_supported()into the same struct. Those should have been their own features, not tied toruntime_async_alloc. Most of the changes in this PR are structurally similar to that.Closes #2023.
Checklist