improve the implementation of the overload of =

source/tensor/XTensor.cpp

@@ -38,6 +38,7 @@
 #include "XMem.h"
 #include "XHeap.h"
 #include "XBLAS.h"
+#include "XName.h"
 #include "core/shape/MergeBlockLists.h"
 #include "core/movement/CopyValues.h"
 #include "core/arithmetic/Sum.h"
@@ -45,6 +46,7 @@
 #include "core/arithmetic/Sub.h"
 #include "core/arithmetic/Div.h"
 #include "core/math/ScaleAndShift.h"
+#include "function/Identity.h"
 
 #ifdef USE_CUDA
 
@@ -290,6 +292,7 @@ void XTensor::ShallowCopy(const XTensor &tensor)
 /* overloading of the equal-sign */
 XTensor& XTensor::operator= (const XTensor& tensor)
 {
+    
     /* we must make a hard copy of the tensor if it is the input
        of another node. */
     if(outgo.tailNum > 0){
@@ -312,6 +315,21 @@ XTensor& XTensor::operator= (const XTensor& tensor)
         dataHost = NULL;
     }
 
+    if(false && !tensor.isTmp){
+        /* NOTE: this might lead to additional data copy on Mac machines */
+        /* we make an identity transformation here */
+        
+        if(outgo.tailNum > 0)
+            XLink::ClearOutgoing(this);
+        XLink::ClearIncoming(this);
+        
+        if(!IsSameShaped(this, &tensor))
+            Resize(tensor.order, tensor.dimSize, tensor.dataType, tensor.denseRatio);
+        
+        _Identity(&tensor, this);
+        XLink::MakeLink(&tensor, NULL, this, FUNC_IDENTITY);
+    }
+    else{
         /* hard copy of the data array */
         int size = unitNum * unitSize;
         if( isInit && !isSparse && !tensor.isSparse &&
@@ -344,6 +362,7 @@ XTensor& XTensor::operator= (const XTensor& tensor)
 
         /* create tensor links for the new tensor */
         XLink::Replace(&tensor, this);
+    }
 
     return *this;
 }