[PATCH] D55935: [X86][SSE] Canonicalize OR(AND(X, C), AND(Y, ~C)) -> OR(AND(X, C), ANDNP(C, Y))

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added a comment.

Exactly - which is why I said only the cases where X and/or Y are loaded: https://godbolt.org/z/2qMqiF has examples where this would reduce loads and improve folding opportunities.

But getting the XOR variant emitted will be painful as DAGCombiner::unfoldMaskedMerge is fighting against us all the way.


Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D55935/new/

https://reviews.llvm.org/D55935