[SYCL][CUDA] Add managed mem check to enqueue prefetch #5446
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
AidanBeltonS
force-pushed
the
cuda-prefetch-check-managed
branch
from
772e725 to
57eb60e
Compare
Contributor
Author
|
@smaslov-intel would you be able to review this change? |
smaslov-intel
approved these changes
May 10, 2022
Contributor
Author
|
@pvchupin would you be able to tell me what is failing in the Jenkins/Precommit? Many thanks |
Contributor
|
@AidanBeltonS, it's older issue addressed in #6133 |
steffenlarsen
pushed a commit
that referenced
this pull request
Jul 29, 2022
This PR adds the mem_advise reset case and a managed memory check in cuda_piextUSMEnqueueMemAdvise. cuMemAdvise only works on managed memory and returns an error if host or device memory is passed. The SYCL-CTS tests mem_advise with host and device memory, which are not managed. This PR prevents an error from being thrown in the cts usm test. In addition, the sycl spec specifies for mem_advise `A value of 0 reverts the advice for ptr to the default behavior`, currently a value of 0 is treated as unknown and throws an error in the cts as well. This reset case is added to mem_advise. This patch along with #5446 resolves issue #5209 This change breaks the ABI
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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.
This PR adds a managed memory check in
cuda_piextUSMEnqueuePrefetch.cuMemPrefetchAsynconly works on managed memory and returns an error if host or device memory is passed.This check ignores the prefetch hint if the memory provided is not managed.
A warning is emitted to the user if the prefetch is ignored.
This is a partial fix to: #5209