This repository has been archived by the owner on Mar 21, 2024. It is now read-only.
reduce cudaDeviceSynchronize calls #1255
Merged
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
9 tasks
|
Launched CI on 28935982. |
alliepiper
added
testing: gpuCI passed
brycelelbach
approved these changes
Aug 17, 2020
alliepiper
added
testing: internal ci passed
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
While profiling RAPIDS cuDF applications, I saw a lot of
cudaDeviceSynchronizecalls, which may be detrimental to multi-threaded clients using per-thread default stream. It seems to be a bug to be making these calls. This PR simply moves the logic inexecute_on_stream_baseto the base entry point so that all callers can benefit. With this change I no longer seecudaDeviceSynchronizecalls in the application I'm profiling.All tests passed locally.
@brycelelbach @allisonvacanti