[PATCH] [X86, AVX] adjust tablegen patterns to generate better code for scalar insertion into zero vector (PR23073)

[Sanjay Patel]

Patch updated with additional tests that check that we'll generate a movs[d,s] instead of blendp[d,s] for the exact patterns that I've modified.


http://reviews.llvm.org/D8794

Files:
  lib/Target/X86/X86InstrSSE.td
  test/CodeGen/X86/vector-shuffle-256-v4.ll
  test/CodeGen/X86/vector-shuffle-256-v8.ll

EMAIL PREFERENCES
  http://reviews.llvm.org/settings/panel/emailpreferences/
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D8794.23154.patch
Type: text/x-patch
Size: 5149 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20150402/730cc50d/attachment.bin>