[PATCH] D66290: [clang] Pragma vectorize_width() implies vectorize(enable)

[Florian Hahn via Phabricator via cfe-commits]

fhahn added a comment.

I think it would be slightly better to split off the change to disable vectorization via `llvm.loop.vectorize.enable=false` instead of width=1. This changes the behaviour from "disable vectorization, but allow interleaving in the vectoriser" to "disable the vectoriser". IMO this change makes sense, but it is probably better/safer to do it separately.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D66290/new/

https://reviews.llvm.org/D66290