[STF] Implement a reduce algorithm over CUB #3122
Draft
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
…s a low level approach so that we can improve the existing one
|
/ok to test |
|
/ok to test |
miscco
reviewed
Dec 17, 2024
| @@ -602,7 +602,7 @@ public: | |||
| } | |||
| } | |||
|
|
|||
| private: | |||
| // private: | |||
There was a problem hiding this comment.
Indeed this is a temporary hack, we need to get rid of that to make the implementation compatible with CUDA graphs anyway.
miscco
approved these changes
Dec 17, 2024
caugonnet
commented
Dec 17, 2024
| // This will be the ultimate result of the transform followed by reduce | ||
| auto result = ctx.logical_data(shape_of<scalar_view<OutT>>()); | ||
| // Create a typed task eagerly that we'll use throughout | ||
| auto t = ctx.task(result.write(), args.read()...); |
There was a problem hiding this comment.
Need to move this creation of the task in the inner most lambda
|
/ok to test |
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Outdated suggestions cannot be applied.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.
Description
This explores how we can implement C++ algorithms over CUDASTF by the means of CUB, starting from the reduce algorithm
Checklist