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

[Tim Northover via Phabricator via llvm-commits]

t.p.northover updated this revision to Diff 185740.
t.p.northover added a comment.

I was looking at this again and noticed it didn't handle unordered loads & stores properly. It tried to create unordered atomicrmw/cmpxchg, which are illegal and assert. So I updated it to promote unordered to monotonic.


Repository:
  rL LLVM

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

https://reviews.llvm.org/D57820

Files:
  llvm/lib/CodeGen/AtomicExpandPass.cpp
  llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
  llvm/test/Transforms/AtomicExpand/AArch64/expand-atomic-i128.ll
  llvm/test/Transforms/AtomicExpand/AArch64/expand-atomicrmw-nand.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D57820.185740.patch
Type: text/x-patch
Size: 48796 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190207/a4d63916/attachment.bin>