Implemented small Metal abstractions and make the FFT POC usable #193
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
IAvecilla
approved these changes
Apr 10, 2023
IAvecilla
reviewed
Apr 10, 2023
IAvecilla
requested changes
Apr 10, 2023
mpaulucci
approved these changes
Apr 11, 2023
IAvecilla
approved these changes
Apr 11, 2023
MauroToscano
approved these changes
Apr 11, 2023
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Outdated suggestions cannot be applied.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.
Implemented small Metal abstractions and make the FFT POC usable
Description
This is a follow-up for #190 aiming to structure the
gpucrate and to implement a small set of Metal abstractions and a API that wraps around these for creating all the necessary parallel operations for FFT (FFT itself, twiddle factors generation in different orders and bit-reversed permutation). Our FFT implementation is templated and can work with multiple prime field classes, currently only a u256 FP class was implemented in MSL which corresponds to theStark252PrimeFieldin Rust.This also paves the way for implementing parallel FFT in CUDA.
NOTE: right now the CI won't compile the
metalmodule because the host doesn't support Metal. You will need to run tests locally.Type of change
Checklist