Tests/Cuda: Print asynchronous error messages, if any

As kernel launches are asynchronous, a `cudaGetLastError()` right after
the kernel launch might be executed while the kernel is still running.
Synchronizing the device will ensure that all the work is completed
before progressing further on, and allows to catch errors that were
previously missed.
The `cudaGetLastError()` after the `cudaDeviceSynchronize()` is there
to reset the error variable to `cudaSuccess`.

3 files changed, 20 insertions, 0 deletions

diff --git a/Tests/Cuda/Complex/dynamic.cu b/Tests/Cuda/Complex/dynamic.cu
index fc22c8b..0206bb4 100644
--- a/Tests/Cuda/Complex/dynamic.cu
+++ b/Tests/Cuda/Complex/dynamic.cu
@@ -31,4 +31,10 @@ EXPORT void cuda_dynamic_lib_func()
     std::cerr << "DetermineIfValidCudaDevice [SYNC] failed: "
               << cudaGetErrorString(err) << std::endl;
     }
+  err = cudaDeviceSynchronize();
+  if(err != cudaSuccess)
+    {
+    std::cerr << "DetermineIfValidCudaDevice [ASYNC] failed: "
+              << cudaGetErrorString(cudaGetLastError()) << std::endl;
+    }
 }
diff --git a/Tests/Cuda/Complex/file3.cu b/Tests/Cuda/Complex/file3.cu
index 1daf47e..912105a 100644
--- a/Tests/Cuda/Complex/file3.cu
+++ b/Tests/Cuda/Complex/file3.cu
@@ -26,5 +26,12 @@ int file3_launch_kernel(int x)
               << cudaGetErrorString(err) << std::endl;
     return x;
     }
+  err = cudaDeviceSynchronize();
+  if(err != cudaSuccess)
+    {
+    std::cerr << "file3_kernel [ASYNC] failed: "
+              << cudaGetErrorString(cudaGetLastError()) << std::endl;
+    return x;
+    }
   return r.sum;
 }
diff --git a/Tests/Cuda/Complex/mixed.cu b/Tests/Cuda/Complex/mixed.cu
index 429f1f3..a7bcd4e 100644
--- a/Tests/Cuda/Complex/mixed.cu
+++ b/Tests/Cuda/Complex/mixed.cu
@@ -38,5 +38,12 @@ EXPORT int mixed_launch_kernel(int x)
               << cudaGetErrorString(err) << std::endl;
     return x;
     }
+  err = cudaDeviceSynchronize();
+  if(err != cudaSuccess)
+    {
+    std::cerr << "mixed_kernel [ASYNC] failed: "
+              << cudaGetErrorString(cudaGetLastError()) << std::endl;
+    return x;
+    }
   return r.sum;
 }