main/mesa: add more recent blake3, arm/aarch64 speedup around 1.3x
This is must have for postmarketOS phones with low-end ARM CPUs.
blake3 changelog:
- Improved performance in the ARM NEON implementation for both C and Rust callers. This affects AArch64 targets by default and ARMv7 targets that explicitly enable (and support) NEON. The size of the improvement depends on the microarchitecture, but I've benchmarked ~1.3x on a Cortex-A53 and ~1.2x on an Apple M1. Contributed by @sdlyyxy in #319 (closed).
- ~1% performance improvement on Arm NEON contributed by @divinity76 (#384 (closed)).
Upstream MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29687
Signed-off-by: David Heidelberg david@ixit.cz
Edited by David Heidelberg