better way of memory copy

.gitignore

 NiuTrans.Tensor.vcxproj
 NiuTrans.Tensor.vcxproj.filters
 x64/
+vc140.pdb
+NiuTrans.Tensor.vcxproj.user
+NiuTrans.Tensor.aps

source/tensor/core/arithmetic/Sum.cu

@@ -20,6 +20,7 @@
 */
 
 #include "../../XDevice.h"
+#include "../../XUtility.h"
 #include "Sum.cuh"
 
 namespace nts { // namespace nts(NiuTrans.Tensor)

source/tensor/core/utilities/FlushToMem.cu

@@ -117,7 +117,7 @@ void CudaGPUToCPUFlush(XTensor * tensor)
     else {
         tensor->dataHost = new char[tensor->unitNum * tensor->unitSize];
         if (tensor->data != NULL)
-            cudaMemcpy(tensor->dataHost, tensor->data, tensor->unitNum * tensor->unitSize, cudaMemcpyDeviceToHost);
+            XMemCopy(tensor->dataHost, -1, tensor->data, tensor->devID, tensor->unitNum * tensor->unitSize);
         else
             memset(tensor->dataHost, 0, tensor->unitNum * tensor->unitSize);
     }