Skip to content

nouveau/nir: Split fewer 64-bit loads

M Henning requested to merge mhenning/mesa:wider_loads into main

Also adjust the lowering pass to handle wide SSBO loads that we now emit for the nir case.

This improves generated code quality since memoryopt can't merge SSBO loads that end up predicated on a bounds check.

This also happens to fix a few test cases, only because the simpler generated IR is less likely to trigger other compiler bugs. Eg on kepler with NV50_PROG_USE_NIR=1, this fixes arb_gpu_shader_fp64-fs-non-uniform-control-flow-ubo

Edited by M Henning

Merge request reports