[all-commits] [llvm/llvm-project] 49fd2d: [X86] LowerShift - don't prematurely lower to x86 ...

[Simon Pilgrim via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 49fd2dde21655f95309abb17ad1d3392afe4985f
      https://github.com/llvm/llvm-project/commit/49fd2dde21655f95309abb17ad1d3392afe4985f
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2024-12-18 (Wed, 18 Dec 2024)

  Changed paths:
    M llvm/lib/Target/X86/X86ISelLowering.cpp
    M llvm/test/CodeGen/X86/combine-sdiv.ll
    M llvm/test/CodeGen/X86/lower-vec-shift.ll
    M llvm/test/CodeGen/X86/vec_shift6.ll
    M llvm/test/CodeGen/X86/widen_arith-4.ll

  Log Message:
  -----------
  [X86] LowerShift - don't prematurely lower to x86 vector shift imm instructions (#120282)

When splitting 2 unique amount shifts to shuffle(shift(x,c1),shift(x,c2)), don't use getTargetVShiftByConstNode directly to lower, use generic shifts to ensure we make use of any further canonicalization: shl(X,1) to add(X,X) etc. - this can have notably better throughput on some x86 targets.

Noticed on #120270



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