Jay Foad 16778b19f2 [AMDGPU] Make bfe patterns divergence-aware ...

This tends to increase code size but more importantly it reduces vgpr
usage, and could avoid costly readfirstlanes if the result needs to be
in an sgpr.

Differential Revision: https://reviews.llvm.org/D88580

2020-10-05 09:55:10 +01:00

6.9 KiB

Raw Blame History

View Raw