[llvm] [OpenMP] Remove hack around missing atomic load (PR #122781)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-offload

Author: Joseph Huber (jhuber6)

<details>
<summary>Changes</summary>

Summary:
We used to do a fetch add of zero to approximate a load. This is because
the NVPTX backend didn't handle this properly. It's not an issue anymore
so simply use the proper atomic builtin.


---
Full diff: https://github.com/llvm/llvm-project/pull/122781.diff


1 Files Affected:

- (modified) offload/DeviceRTL/include/Synchronization.h (+1-1) 


``````````diff
diff --git a/offload/DeviceRTL/include/Synchronization.h b/offload/DeviceRTL/include/Synchronization.h
index e1968675550d49..a4d4fc08837b29 100644
--- a/offload/DeviceRTL/include/Synchronization.h
+++ b/offload/DeviceRTL/include/Synchronization.h
@@ -66,7 +66,7 @@ V add(Ty *Address, V Val, atomic::OrderingTy Ordering) {
 
 template <typename Ty, typename V = utils::remove_addrspace_t<Ty>>
 V load(Ty *Address, atomic::OrderingTy Ordering) {
-  return add(Address, Ty(0), Ordering);
+  return __scoped_atomic_load_n(Address, Ordering, __MEMORY_SCOPE_DEVICE);
 }
 
 template <typename Ty, typename V = utils::remove_addrspace_t<Ty>>

``````````

</details>


https://github.com/llvm/llvm-project/pull/122781