[PATCH] D41895: [X86] Another attempt at support prefer-vector-width function attribute

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added a comment.

I raised this on D111029 <https://reviews.llvm.org/D111029> - its still not confirmed which avx512 capable targets work better with 512-bit vectors (other than KNL of course).


Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D41895/new/

https://reviews.llvm.org/D41895