-
Notifications
You must be signed in to change notification settings - Fork 10
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.
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
Add support for f32
, as well as f64
#17
Conversation
It seems like it fails to build on CI with a syntax error? |
Yes. Sorry, I should have converted this to a draft. I have local changes almost ready to check-in. They should address the aforementioned issue, as well as others. |
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #17 +/- ##
==========================================
+ Coverage 94.28% 97.25% +2.96%
==========================================
Files 7 7
Lines 805 765 -40
==========================================
- Hits 759 744 -15
+ Misses 46 21 -25 ☔ View full report in Codecov by Sentry. |
- Make float comparison generic for f32/f64 - Add f32/f64 tests for twiddles using macros
@@ -102,7 +102,7 @@ macro_rules! impl_fft_with_opts_and_plan_for { | |||
if t < n - 1 { | |||
filter_twiddles(twiddles_re, twiddles_im); | |||
} | |||
if chunk_size >= 16 { | |||
if chunk_size >= $lanes * 2 { |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@Shnatsel Now we just use # of lanes * 2
when executing this check
@@ -49,7 +49,7 @@ macro_rules! fft_butterfly_n_simd { | |||
} | |||
|
|||
fft_butterfly_n_simd!(fft_64_chunk_n_simd, f64, 8, f64x8); | |||
fft_butterfly_n_simd!(fft_32_chunk_n_simd, f32, 8, f32x8); | |||
fft_butterfly_n_simd!(fft_32_chunk_n_simd, f32, 16, f32x16); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@Shnatsel Bumped up # of lanes to 16 when using AVX-512
and f32
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@Shnatsel I think this should be good to go now
This PR should address issue #14