[PATCH] D38375: [X86] Make use of vpmovwb when possible in LowerMULH

[Craig Topper via Phabricator via llvm-commits]

craig.topper created this revision.

If we have BWI, we can truncate in a bunch simpler way by using vpmovwb. This even works without VLX by using the wider zmm->ymm truncate with a subvector extract.


https://reviews.llvm.org/D38375

Files:
  lib/Target/X86/X86ISelLowering.cpp
  test/CodeGen/X86/vector-idiv-sdiv-128.ll
  test/CodeGen/X86/vector-idiv-sdiv-256.ll
  test/CodeGen/X86/vector-idiv-udiv-128.ll
  test/CodeGen/X86/vector-idiv-udiv-256.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D38375.117033.patch
Type: text/x-patch
Size: 12630 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170928/be8fc122/attachment-0001.bin>