[PATCH] D36840: [DAG] convert vector select-of-constants to logic/math

[Sanjay Patel via Phabricator via llvm-commits]

spatel updated this revision to Diff 111583.
spatel added a comment.

Patch updated:
Remove the general case fold which actually isn't a win if vselect is fast. We only convert the vselect when there's a clear optimization now.


https://reviews.llvm.org/D36840

Files:
  include/llvm/Target/TargetLowering.h
  lib/CodeGen/SelectionDAG/DAGCombiner.cpp
  lib/Target/PowerPC/PPCISelLowering.h
  lib/Target/X86/X86ISelLowering.cpp
  lib/Target/X86/X86ISelLowering.h
  test/CodeGen/PowerPC/vselect-constants.ll
  test/CodeGen/X86/vselect-avx.ll
  test/CodeGen/X86/vselect-constants.ll
  test/CodeGen/X86/widen_compare-1.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D36840.111583.patch
Type: text/x-patch
Size: 21677 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170817/67a9fd91/attachment.bin>