[PATCH] D57820: [AArch64] Use CAS loops for all atomic operations when available.

[JF Bastien via Phabricator via llvm-commits]

jfb added a comment.

> Incidentally the handling of volatile atomic operations here is probably wrong as I don't think we can have any kind of repeated loading, but that's nothing to do with this change (both LDXR/STXR loop and CAS loop have this problem) and doesn't need to be fixed by it.

`volatile atomic` is generally a bit of a minefield. If we don't have an instruction that does a straight load then there's not much we can do...


Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D57820/new/

https://reviews.llvm.org/D57820