[PATCH] D60150: [DAGCombiner][x86] scalarize splatted vector FP ops

[Sanjay Patel via Phabricator via llvm-commits]

spatel updated this revision to Diff 193738.
spatel added a comment.

Patch updated:
Rather than add an assert that we are splatting from the first operand of the shuffle, I rearranged the order of the folds, so the check is more obvious. 
The fact that we may be peeking through a bitcast for the other transforms always makes me nervous that we may be using a different value than we expected.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D60150/new/

https://reviews.llvm.org/D60150

Files:
  llvm/include/llvm/CodeGen/TargetLowering.h
  llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
  llvm/lib/Target/X86/X86ISelLowering.h
  llvm/test/CodeGen/X86/haddsub-shuf.ll
  llvm/test/CodeGen/X86/scalarize-fp.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D60150.193738.patch
Type: text/x-patch
Size: 18404 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190404/972ba4b7/attachment.bin>