Squash more HtoD copy stream sync issues - #1163
Open
wence- wants to merge 3 commits into
Open
Conversation
pentschev
reviewed
Aug 25, 2026
pentschev
approved these changes
Aug 25, 2026
wence-
force-pushed
the
wence/fix/tests-stream-syncs
branch
from
August 25, 2026 12:50
e903015 to
a4472c0
Compare
nirandaperera
left a comment
nirandaperera
left a comment
Contributor
There was a problem hiding this comment.
Just a small comment
| auto rmm_buffer = std::make_unique<rmm::device_buffer>( | ||
| random_data.data(), buffer_size, stream1, br->device_mr() | ||
| ); | ||
| stream1.synchronize(); |
Contributor
There was a problem hiding this comment.
I think we can drop this, isnt it? random_data stays alive until the end of the test case.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
We previously went round and did an audit of the HtoD copies and inserted stream syncs, but missed a few. These are all the rest I found.
Mostly mechanical, with one notable change. Since
buffer_copyknows the memory type of both the source and destination I chose to explicitly insert the stream synchronisation in the copy when we know the source is in pageable host memory. This is morally the same as thestream_waitcall we already have.