Speedup make_blobs by up to 2x by fixing inefficient kernel launch configuration
#1100
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
|
This is a before/after benchmark:
|
Nyrio
added
3 - Ready for Review
improvement
cjnolet
approved these changes
Dec 14, 2022
|
@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Outdated suggestions cannot be applied.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.
The kernel generates two elements per iteration and attempts to write the second element with an offset equal to the grid stride. However, the grid stride is currently computed to be greater than the length of the generated array, so this second value is never used. By using a grid stride of half the array size, we speed up the kernel by nearly 2x in some cases (see perf charts in the PR comments).
Note: this will effectively modify many test inputs, so be aware of that when comparing results prior to and following the change.