Use vector factories for host-device copies. #9806
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
…g cudaMemcpyAsync.
bdice
added
3 - Ready for Review
Codecov Report
@@ Coverage Diff @@
## branch-22.02 #9806 +/- ##
================================================
- Coverage 10.49% 10.47% -0.02%
================================================
Files 119 119
Lines 20305 20368 +63
================================================
+ Hits 2130 2133 +3
- Misses 18175 18235 +60
Continue to review full report at Codecov.
|
karthikeyann
approved these changes
Dec 6, 2021
hyperbolic2346
approved these changes
Dec 6, 2021
davidwendt
approved these changes
Dec 6, 2021
|
@gpucibot merge |
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Outdated suggestions cannot be applied.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.
See: #9588 (comment)
In a recent PR review, @jrhemstad suggested switching to vector factories for one-way host-device data copying (that is, cases where using a
hostdevice_vectorisn't the right choice).This PR applies that suggestion more broadly across the code base, replacing a number of simple cases where a (device) vector was being constructed followed by a call to
CUDA_TRY(cudaMemcpyAsync(...))with the corresponding factory functions. This makes the code a little more concise and encourages broader use of these factory functions in the future.