Skip to content

nir/opt_shrink_vectors: shrink memory loads, not just IO

Marek Olšák requested to merge mareko/mesa:nir-shrink-memory-loads into main
nir/opt_shrink_vectors: shrink memory loads, not just IO

The problem with radeonsi+ACO is that UBO loads from vec4 uniforms using
only 1 component always load all 4 components. This fixes that.

We are only interested in shrinking UBO and SSBO loads, but I added more
intrinsics because why not.

This is part of an effort to make UBO loads great again.

Merge request reports