Use the async gpu kernel call by default.

theano/sandbox/cuda/cuda_ndarray.cu

@@ -88,6 +88,11 @@ int device_free(void *ptr)
     if(!g_gpu_context_active) {
         return 0;
     }
+
+    // We need sync as the Theano's GC could remove intermediate variable that
+    // are still needed as the gpu kernel are running or in the queue.
+    cudaThreadSynchronize();
+
     cudaError_t err =  cudaFree(ptr);
     if (cudaSuccess != err)
     {

theano/sandbox/cuda/cuda_ndarray.cuh

@@ -27,7 +27,7 @@ typedef float real;
 #define NUM_VECTOR_OP_THREADS_PER_BLOCK     256  //Should be read from device properties. (#10)
 #endif
 
-#if 0
+#if 1
 // Do not wait after every kernel & transfer.
 #define CNDA_THREAD_SYNC
 #else