Release: RustFFT 6.1, now with support for AArch64 Neon acceleration!

RustFFT 6.1 has been released!

RustFFT is a high-performance, SIMD-accelerated FFT library written in pure Rust. Version 6.1.0 extends RustFFT's SIMD acceleration support to AArch64's Neon instruction set. With this release, RustFFT supports AVX, AVX2, SSE4.1, and Neon (as well as a non-SIMD fallback path).

This comment on the original PR has some benchmarks comparing RustFFT's scalar code to the new Neon-accelerated code on an Apple M1. To summarize, users computing 32-bit FFTs on a Neon-supporting CPU can expect a 2.5x speedup after upgrading to version 6.1, and users computing 64-bit FFTs can expect 1.5x speedup.

Thanks to Henrik Enquist for doing most of the implementation work and pushing the feature to release!


This topic was automatically closed 90 days after the last reply. We invite you to open a new topic if you have further questions or comments.