Sergey "Shnatsel" Davidoff

Yup, it was never shipped. And the latest git is not shippable because #202 is a breaking change. Should we temporarily undo that PR and ship the fixes in a...

We also want to include #210 which is also a fix relevant to Glycin. So we need to either backport that to 0.13.x or make ships a semver-compatible release of...

An initial redesign and rewrite has landed in #1113

On my Zen 4 CPU this is a consistent regression in the default configuration and makes little difference with `-C target-cpu=native`: cargo bench --bench=bit_reversal ``` Running benches/bit_reversal.rs (target/release/deps/bit_reversal-7310e7572d98d06c) cobra_apply/cobra/15 time:...

Hmm. Rust version? Mine is rustc 1.91.1 (ed61e7d7e 2025-11-07)

Tip: to make percentages make sense, you can run `cargo bench --bench=bit_reversal -- --save-baseline=main` followed by `cargo bench --bench=bit_reversal -- --baseline=main` and it will calculate percentages relative to the baseline...

I don't think there's a one-size-fits-all solution. If we want to reap these gains, we'll need to copy FFTW's design and measure the performance of various implementations at runtime, then...

I've looked into COBRA some more and it's highly hardware-dependent: https://github.com/QuState/PhastFT/issues/49 We really do just need to start going down the FFTW route, measure the different variants in the planner...

I'm happy to merge a pull request adding v1.6 support. AFAIK I'm the only active maintainer and I'm already spread very thin, so v1.6 support will only happen if either...

No. That Cargo PR only writes a "sbom precursor" that contains an accurate dependency tree. It is up to external tools like cargo-cyclonedx to collate it with `cargo metadata` output...