[PATCH] D56011: [x86] lower extracted fadd/fsub to horizontal vector math

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added inline comments.


================
Comment at: lib/Target/X86/X86ISelLowering.cpp:18324
+  return !IsSingleSource || IsOptimizingSize || HasFastHOps;
+}
+
----------------
spatel wrote:
> RKSimon wrote:
> > We already have shouldCombineToHorizontalOp 
> Right - I’m moving/renaming it here because it’s used in both combining and lowering after this patch. I can make that an NFC pre-commit.
Yes, please do the NFC pre-commit first


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D56011/new/

https://reviews.llvm.org/D56011