[all-commits] [llvm/llvm-project] e3e7c7: AMDGPU: Update pattern matching from "x&(-1>>(32-y...

[Changpeng Fang via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: e3e7c756fb439f4e92691c6f8c891fecd2c918ed
      https://github.com/llvm/llvm-project/commit/e3e7c756fb439f4e92691c6f8c891fecd2c918ed
  Author: Changpeng Fang <changpeng.fang at amd.com>
  Date:   2024-11-14 (Thu, 14 Nov 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.h
    M llvm/lib/Target/AMDGPU/SIInstructions.td
    M llvm/test/CodeGen/AMDGPU/extract-lowbits.ll

  Log Message:
  -----------
  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.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications