[clang] [AMDGPU] Add sema check for global_atomic_fadd_v2f16 builtin (PR #158145)

[Matt Arsenault via cfe-commits]

================
@@ -0,0 +1,46 @@
+// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -verify %s
----------------
arsenm wrote:

Can you verify we have test coverage using OpenCL plus one of the C/C++/HIP variants 

https://github.com/llvm/llvm-project/pull/158145