[PATCH] [X86][SSE] Vectorized i8 and i16 shift operators

[Elena Demikhovsky]

Hi,

I think you can commit all shifts v8i16 and v16i16 for AVX2. 
I don't have time to check all other sequences.

- Elena


REPOSITORY
  rL LLVM

http://reviews.llvm.org/D9474

EMAIL PREFERENCES
  http://reviews.llvm.org/settings/panel/emailpreferences/