[clang] [llvm] [Offload][Lang] Add blocking to LaunchKernel and Memcpy (PR #218049)

[Sophia Herrmann via cfe-commits]

================
@@ -8396,6 +8396,7 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
 
   if (IsHIP) {
     CmdArgs.push_back("-fcuda-allow-variadic-functions");
+    /// TODO: Why is this not forwarded when IsCUDA?
----------------
jellytabby wrote:

We discussed that we should leave a comment here since it's unclear why its not forwarded under CUDA but also doesnt belong in the scope of this PR

https://github.com/llvm/llvm-project/pull/218049