Changpeng Fang 9778fc76e3 Revert "AMDGPU: Don't avoid clamp of bit shift in BFE pattern (#115372)" (#116091) ...

Based on the suggestion from
https://github.com/llvm/llvm-project/pull/115543, we should not do the
pattern matching from x << (32-y) >> (32-y) to "bfe x, 0, y" at all.
This reverts commits a2bacf8ab58af4c1a0247026ea131443d6066602 and
bdf8e308b7.

2024-11-13 14:01:21 -08:00

20 KiB

Raw Blame History

View Raw