[clang] [llvm] [mlir] [Flang][OpenMP] Enable no-loop kernels (PR #155818)

[Dominik Adamski via llvm-commits]

================
@@ -0,0 +1,96 @@
+! REQUIRES: flang, amdgpu
----------------
DominikAdamski wrote:

Yes, it should be correct with Nvida GPU. I fixed the test case.

https://github.com/llvm/llvm-project/pull/155818