Use SVE widening loads - Githubissues

ARM-software / astc-encoder

The Arm ASTC Encoder, a compressor for the Adaptive Scalable Texture Compression data format.

https://developer.arm.com/graphics

Apache License 2.0

1.07k stars 241 forks source link

Use SVE widening loads #490

Closed solidpixel closed 3 months ago

solidpixel commented 3 months ago

This change moves from NEON-style post-load widening, to SVE-style load-time widening. On Neoverse V1 this improves performance 1-5% (increasing with block size).

Also fixes a signed/unsigned mismatch warning.