Add managed-memory advise, prefetch, and discard-prefetch on Buffer#1775
Open
rparolin wants to merge 3 commits intoNVIDIA:mainfrom
Open
Add managed-memory advise, prefetch, and discard-prefetch on Buffer#1775rparolin wants to merge 3 commits intoNVIDIA:mainfrom
rparolin wants to merge 3 commits intoNVIDIA:mainfrom
Conversation
Contributor
|
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. |
rparolin
changed the title
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add managed-memory range controls to
cuda.core.Buffer:Buffer.advise(...)Buffer.prefetch(...)Buffer.discard_prefetch(...)This addresses #1332.
Details
These operations are implemented on
Bufferbecause the CUDA driver APIs apply to a memory range, not specifically toManagedMemoryResource. That allows the new methods to work for both:ManagedMemoryResourceThe implementation adds managed-memory detection for buffers, normalizes device/host/NUMA location inputs, and forwards to the existing
driver bindings for
cuMemAdvise,cuMemPrefetchAsync, andcuMemDiscardAndPrefetchBatchAsync.Tests
Adds coverage for:
cuMemRangeGetAttribute(...)Closes #1332