[PATCH] D15477: [X86][AVX] Only shuffle the lower half of vectors if the upper half is undefined

[Simon Pilgrim via llvm-commits]

RKSimon updated this revision to Diff 43391.
RKSimon added a comment.

Disabled v4f64/v4i64 lowering on AVX2 - VPPERMQ/VPERMPD are faster.

Made the referencing of the half vectors clearer - the code is capable of referencing any 2 of the 4 half vectors, but we only permit the use of the lower halves as there is a definite perf gain there.


Repository:
  rL LLVM

http://reviews.llvm.org/D15477

Files:
  lib/Target/X86/X86ISelLowering.cpp
  test/CodeGen/X86/avx-splat.ll
  test/CodeGen/X86/vector-shuffle-256-v16.ll
  test/CodeGen/X86/vector-shuffle-256-v32.ll
  test/CodeGen/X86/vector-shuffle-256-v4.ll
  test/CodeGen/X86/vector-shuffle-256-v8.ll
  test/CodeGen/X86/vector-zext.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D15477.43391.patch
Type: text/x-patch
Size: 30951 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20151221/237f3904/attachment.bin>