Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fast Metal FFT for all N #981

Closed
wants to merge 16 commits into from
Closed

Fast Metal FFT for all N #981

wants to merge 16 commits into from

Commits on Apr 12, 2024

  1. add Metal FFT for powers of 2

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    4460869 View commit details
    Browse the repository at this point in the history

  2. implement rfft, ifft and irfft

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    aaf38ec View commit details
    Browse the repository at this point in the history

  3. implement fftn, ifftn, rfftn, irfftn

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    3d87600 View commit details
    Browse the repository at this point in the history

  4. bluestein's working for n up to 1023

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    b39944b View commit details
    Browse the repository at this point in the history

  5. inv bluestein

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    73a0826 View commit details
    Browse the repository at this point in the history

  6. function constants for radix step sizes

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    f0a2948 View commit details
    Browse the repository at this point in the history

  7. add radix 3 kernel and mixed prime radix decomp

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    251c5db View commit details
    Browse the repository at this point in the history

  8. Mixed radix + bluestein's working together

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    651d448 View commit details
    Browse the repository at this point in the history

  9. batching in threadgroup memory for small n

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    462a897 View commit details
    Browse the repository at this point in the history

  10. add brute force prime radices up to 13

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    3f62f3c View commit details
    Browse the repository at this point in the history

  11. naive four step fft impl

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    6dee569 View commit details
    Browse the repository at this point in the history

  12. fast rfft

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    d7afd42 View commit details
    Browse the repository at this point in the history

  13. RFFT, IRFFT + manual bluestein

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    aa2ddd3 View commit details
    Browse the repository at this point in the history

  14. fixed a few tricky non-deterministic bugs

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    b46601e View commit details
    Browse the repository at this point in the history

  15. More benchmarks

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    c78ad47 View commit details
    Browse the repository at this point in the history

  16. add contiguity tests

    Alex Barron committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    fa8047b View commit details
    Browse the repository at this point in the history