Fix CUDA synchronization in spatialtf_grid

theano/gpuarray/c_code/spatialtf_grid.c

@@ -86,11 +86,17 @@ spatialtf_grid(PyArrayObject * grid_dimensions,
         return -1;
     }
 
+    cuda_wait( theta->ga.data, GPUARRAY_CUDA_WAIT_READ );
+    cuda_wait( (*grid)->ga.data, GPUARRAY_CUDA_WAIT_WRITE );
+
     const void * theta_data = PyGpuArray_DEV_DATA( theta );
     void * grid_data = PyGpuArray_DEV_DATA( *grid );
 
     err = cudnnSpatialTfGridGeneratorForward( _handle, desc, theta_data, grid_data );
 
+    cuda_record( theta->ga.data, GPUARRAY_CUDA_WAIT_READ );
+    cuda_record( (*grid)->ga.data, GPUARRAY_CUDA_WAIT_WRITE );
+
     if ( CUDNN_STATUS_SUCCESS != err )
     {
         PyErr_Format( PyExc_RuntimeError,