[PATCH] D20780: [AVX512] Fix intrinsic vbroadcast{i32|f32}x2 lowering.

[Igor Breger via llvm-commits]

igorb created this revision.
igorb added reviewers: delena, AsafBadouh.
igorb added a subscriber: llvm-commits.
igorb set the repository for this revision to rL LLVM.

[AVX512] Fix intrinsic vbroadcast{i32|f32}x2 lowering.  
In previous implementation vbroadcastf32x4 was selected ( memory folding)  for the follow example
call <8 x float> @llvm.x86.avx512.mask.broadcastf32x2.256(<4 x float> <float -0.000000e+00, float 0x404155C280000000, float 0xC05155C280000000, float 0x405A00A3E0000000>, <8 x float> <float 1.170000e+02, float 1.170000e+02, float 1.170000e+02, float 1.170000e+02, float 1.170000e+02, float 1.170000e+02, float 1.170000e+02, float 1.170000e+02>, i8 123)

Repository:
  rL LLVM

http://reviews.llvm.org/D20780

Files:
  lib/Target/X86/X86ISelLowering.cpp
  lib/Target/X86/X86InstrAVX512.td
  lib/Target/X86/X86IntrinsicsInfo.h

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D20780.58913.patch
Type: text/x-patch
Size: 6870 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160529/aaba0d72/attachment.bin>