[PATCH] D156532: [Pipelines] Perform hoisting prior to GVN

[Nikita Popov via Phabricator via llvm-commits]

nikic added a comment.

The issue for x264 is that the earlier hoisting reduces the size of the loop body enough for it to be unrolled, and SLP doesn't vectorize this case. This is the IR before slp-vectorize: https://gist.github.com/nikic/6ccde4b5320f7f4a6c5e7bd3ff8db1f6

Quite annoying, because the earlier hoisting would otherwise be a clear improvement for that test case.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D156532/new/

https://reviews.llvm.org/D156532