[PATCH] D57854: [InstCombine] Optimize `atomicrmw <op>, 0` into `load atomic` when possible

[JF Bastien via Phabricator via llvm-commits]

jfb added inline comments.


================
Comment at: lib/Transforms/InstCombine/InstCombineAtomicRMW.cpp:36
+    Load->setVolatile(RMWI.isVolatile());
+    Load->setAtomic(Ordering, RMWI.getSyncScopeID());
+    return Load;
----------------
qcolombet wrote:
> jfb wrote:
> > This drops SyncScope.
> What do you mean?
Oops ignore me on this one! I misread.


Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D57854/new/

https://reviews.llvm.org/D57854