[flang][cuda][NFC] Add tests for device functions in cuf kernels

Using device function in cuf kernel is allowed but requires an
explicit use of the cudadevice module. The two added tests make
sur it works when the cudadevice module is used and failed when it
is not.

Author: clementval

flang/test/Lower/CUDA/cuda-device-proc.cuf

@@ -87,3 +87,17 @@ end
 ! CHECK: func.func private @llvm.nvvm.barrier0.and(i32) -> i32
 ! CHECK: func.func private @llvm.nvvm.barrier0.popc(i32) -> i32
 ! CHECK: func.func private @llvm.nvvm.barrier0.or(i32) -> i32
+
+subroutine host1()
+  integer, device :: a(32)
+  integer :: i, j
+
+block; use cudadevice
+  !$cuf kernel do(1) <<<*,32>>>
+  do i = 1, 32
+    a(i) = a(i) * 2.0
+    call syncthreads()
+    a(i) = a(i) + a(j) - 34.0
+  end do
+end block
+end 

flang/test/Semantics/cuf09.cuf

@@ -192,3 +192,16 @@ program main
      enddo
   enddo
 end
+
+subroutine host1()
+  integer, device :: a(32)
+  integer :: i, j
+
+  !$cuf kernel do(1) <<<*,32>>>
+  do i = 1, 32
+    a(i) = a(i) * 2.0
+    !ERROR: 'syncthreads' may not be called in device code
+    call syncthreads() ! missing explicit use cudadevice
+    a(i) = a(i) + a(j) - 34.0
+  end do
+end