Jay Foad e55d6f5ea2 [AMDGPU] Simplify and improve codegen for llvm.amdgcn.set.inactive (#107889) ...

Always generate v_cndmask_b32 instead of modifying exec around
v_mov_b32. This is expected to be faster because
modifying exec generally causes pipeline stalls.

2024-09-11 17:16:06 +01:00

267 KiB

Raw Blame History

View Raw