Files
clang-p2996/llvm/test/CodeGen/AMDGPU/extract-lowbits.ll
Changpeng Fang e3e7c756fb AMDGPU: Update pattern matching from "x&(-1>>(32-y))" to "bfe x, 0, y" (#116115)
It is not correct to lower "x&(-1>>(32-y))" to "bfe x, 0, y". When y
equals 32, "-1" is not shifted, so x&(-1>>(32-32) is still x, but "bfe
x, 0, 32" is 0. However, if we know y is at most of 5 bits (< 32), we
can still do the pattern matching.
2024-11-14 12:21:34 -08:00

8.6 KiB