[llvm] [flang][cuda] Use the provided stream in kernel launch (PR #135267)

[Zhen Wang via llvm-commits]

================
@@ -212,9 +217,10 @@ void RTDEF(CUFLaunchCooperativeKernel)(const void *kernel, intptr_t gridX,
     Fortran::runtime::Terminator terminator{__FILE__, __LINE__};
     terminator.Crash("Too many invalid grid dimensions");
   }
-  cudaStream_t cuStream = 0; // TODO stream managment
-  CUDA_REPORT_IF_ERROR(cudaLaunchCooperativeKernel(
-      kernel, gridDim, blockDim, params, smem, cuStream));
+  cudaStream_t deafultStream = 0;
----------------
wangzpgi wrote:

typo: default

https://github.com/llvm/llvm-project/pull/135267