Matt Arsenault 3e53aeae94 AMDGPU: Make frame index folding logic consistent with eliminateFrameIndex (#129633) ...

This adds handling of s_add_u32, which is handled and removes handling of
s_or_b32 and s_and_b32, which are not. I was working on handling them
in #102345, but need to finish that patch. This fixes a regression
exposed by a3165398db where the
final instruction would use two literals.

2025-03-05 10:09:30 +07:00

15 KiB

Raw Blame History

View Raw