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

[John Brawn via Phabricator via llvm-commits]

john.brawn added a comment.

It's a bit hard to know whether to accept this or not, given that you says it's "probably better to avoid LDXR". Do you have any data to say if it is any better or not?

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.


Repository:
  rL LLVM

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

https://reviews.llvm.org/D57820