[all-commits] [llvm/llvm-project] bf468f: [X86][SSE] Canonicalize UNARYSHUFFLE(XOR(X, -1) -> ...

[Simon Pilgrim via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: bf468f4349071f28755ca7ea7a53f21fc8c8ddbf
      https://github.com/llvm/llvm-project/commit/bf468f4349071f28755ca7ea7a53f21fc8c8ddbf
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2020-04-30 (Thu, 30 Apr 2020)

  Changed paths:
    M llvm/lib/Target/X86/X86ISelLowering.cpp
    M llvm/test/CodeGen/X86/avx512-vec-cmp.ll
    M llvm/test/CodeGen/X86/combine-bitselect.ll

  Log Message:
  -----------
  [X86][SSE] Canonicalize UNARYSHUFFLE(XOR(X,-1) -> XOR(UNARYSHUFFLE(X),-1)

This pushes the NOT pattern up the DAG to help expose it for further combines (AND->ANDN in particular).

The PSHUFD/MOVDDUP 'splat' cases are the only ones I've seen in the wild so far, we can further generalize if/when we need to.