[llvm] [NVPTX] Support for memory orderings for cmpxchg (PR #126159)

[Akshay Deodhar via llvm-commits]

================
@@ -324,8 +324,10 @@ bool AtomicExpandImpl::processAtomicInstr(Instruction *I) {
       // failure path. As a result, fence insertion is directly done by
       // expandAtomicCmpXchg in that case.
       FenceOrdering = CASI->getMergedOrdering();
-      CASI->setSuccessOrdering(AtomicOrdering::Monotonic);
-      CASI->setFailureOrdering(AtomicOrdering::Monotonic);
+      auto CASOrdering = TLI->atomicOperationOrderAfterFenceSplit(CASI);
----------------
akshayrdeodhar wrote:

@topperc does the API work? 

https://github.com/llvm/llvm-project/pull/126159