[Feature] Add Batch FFT for CUDA #6512
Draft
Conversation
This file contains hidden or 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
|
I'm not sure if the batch size should be a input parameter or merely a function parameter that can be differently decided when developers use batch FFT to do different things. As for me, this parameter might be a situation-specific one. |
I've added it as a function parameter in FFT module. But according to previous test, setting batch_size to different size leads to different caculation speed. I cannot easily figure out which size is the best so maybe leave this problem to user is an option😤 |
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Outdated suggestions cannot be applied.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.
According to tests from 沐曦's engineers, using batch fft on GPU to replace some FFT loop may make caculation faster in some cases. This PR added a input parameter which allows users to choose whether to use batch fft.