fix the bug of use memory pool in FREE_ON_THE_FLY mode

source/tensor/function/Softmax.cpp

@@ -45,20 +45,17 @@ void _Softmax(const XTensor * x, XTensor * y, int leadDim)
         int * dimSize = new int[x->order - 1];
         for(int i = 0; i < x->order; i++){
             if(i < leadDim)
-                dimSize[i] = -x->dimSize[i];
+                dimSize[i] = x->dimSize[i];
             else if(i > leadDim)
-                dimSize[i - 1] = -x->dimSize[i];
+                dimSize[i - 1] = x->dimSize[i];
         }
 
         XMem * mem = x->mem;
         XTensor * max = NULL;
         XTensor * sum = NULL;
 
-        max = NewTensor(x->order - 1, dimSize, x->dataType, x->denseRatio, x->devID, mem);
-        sum = NewTensor(x->order - 1, dimSize, x->dataType, x->denseRatio, x->devID, mem);
-
-        max->data = mem != NULL ? (char*)mem->AllocBuf(mem->devID, max->unitNum * max->unitSize) : XMemAlloc(max->devID, max->unitNum * max->unitSize);
-        sum->data = mem != NULL ? (char*)mem->AllocBuf(mem->devID, sum->unitNum * sum->unitSize) : XMemAlloc(sum->devID, sum->unitNum * sum->unitSize);
+        max = NewTensorBuf(x->order - 1, dimSize, x->dataType, x->denseRatio, x->devID, mem);
+        sum = NewTensorBuf(x->order - 1, dimSize, x->dataType, x->denseRatio, x->devID, mem);
 
         _ReduceMax(x, max, leadDim);
         _ReduceSum(x, sum, leadDim, max, 1.0F, true);
@@ -114,18 +111,9 @@ void _Softmax(const XTensor * x, XTensor * y, int leadDim)
             }
         }
 
-        if(mem != NULL){
-            mem->ReleaseBuf(mem->devID, max->unitNum * max->unitSize);
-            mem->ReleaseBuf(mem->devID, sum->unitNum * sum->unitSize);
-        }
-        else{
-            XMemFree(max->devID, max->data);
-            XMemFree(sum->devID, sum->data);
-            max->data = NULL;
-            sum->data = NULL;
-        }
-        delete max;
-        delete sum;
+        DelTensorBuf(sum);
+        DelTensorBuf(max);
+
         delete[] dimSize;
     }
     else