Fix synchronization before testing cublasXt calls. #577
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
Codecov Report
@@ Coverage Diff @@
## master #577 +/- ##
=======================================
Coverage 80.20% 80.20%
=======================================
Files 116 116
Lines 6900 6900
=======================================
Hits 5534 5534
Misses 1366 1366
Continue to review full report at Codecov.
|
kshyatt
approved these changes
Nov 27, 2020
maleadt
added a commit
that referenced
this pull request
Jan 5, 2021
Fix synchronization before testing cublasXt calls.
maleadt
added a commit
that referenced
this pull request
Jan 6, 2021
Fix synchronization before testing cublasXt calls.
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Outdated suggestions cannot be applied.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.
Fixes #124, fixes #536
cc @kshyatt this was a fun one; cuBLASXt doesn't respect stream semantics, so we need to make sure data is actually ready before calling the API. Similarly, the API is actually blocking, so we don't need to sync afterwards. I wonder if something similar is happening with some of the sporadic failures in the -MG PRs.