fix memory leak

source/Main.cpp

@@ -32,25 +32,27 @@
 
 #include "test/Test.h"
 
+//#define CRTDBG_MAP_ALLOC
+//#include <stdlib.h>  
+//#include <crtdbg.h> 
+
 using namespace nts;
 using namespace samplefnnlm;
 
-//#define CRTDBG_MAP_ALLOC    
-//#include <stdlib.h>    
-//#include <crtdbg.h> 
-
 int main( int argc, const char ** argv )
 {
-    srand((unsigned)time(0));
     if(argc > 1 && !strcmp(argv[1], "-test"))
         Test();
-    if(argc > 1 && !strcmp(argv[1], "-fnnlm"))
-        return FNNLMMain(argc - 1, argv + 1);
+    else if(argc > 1 && !strcmp(argv[1], "-fnnlm"))
+        FNNLMMain(argc - 1, argv + 1);
     else{
         fprintf(stderr, "Thanks for using NiuTrans.Tensor! This is a library that eases the\n");
         fprintf(stderr, "use of tensors. All you need is to ... \n\n");
         fprintf(stderr, "Run this program with \"-test\" for unit test!\n");
         fprintf(stderr, "Or run this program with \"-fnnlm\" for sample FNNLM!\n");
     }
+
+    //_CrtDumpMemoryLeaks();
+
     return 0;
 }

source/core/arithmetic/MatrixMul.cpp

@@ -94,9 +94,9 @@ void MatrixMul(XTensor * a, MATRIX_TRANS_TYPE transposedA,
     XList * aList = new XList(10);
     XList * bList = new XList(10);
     XList * cList = new XList(10);
-    int aDimSize[2] = { a->dimSizeRDI[1], a->dimSizeRDI[0] };
-    int bDimSize[2] = { b->dimSizeRDI[1], b->dimSizeRDI[0] };
-    int cDimSize[2] = { c->dimSizeRDI[1], c->dimSizeRDI[0] };
+    int aDimSize[2] = { -a->dimSizeRDI[1], a->dimSizeRDI[0] };
+    int bDimSize[2] = { -b->dimSizeRDI[1], b->dimSizeRDI[0] };
+    int cDimSize[2] = { -c->dimSizeRDI[1], c->dimSizeRDI[0] };
 
     bool isSparseMul = false;
 

source/function/Softmax.cu

@@ -293,7 +293,7 @@ void CudaSoftmaxBackward(XTensor * gold, XTensor * y, XTensor * x,
 
             /* ytmp = dE/dy_j - \beta */
             Unsqueeze(beta, ytmp, leadDim, y->dimSize[leadDim]);
-            Sum(dedy, ytmp, ytmp, -1.0F);
+            _Sum(dedy, ytmp, ytmp, -1.0F);
 
             /* dE/ds_j = y_j * ytmp = y_j * (dE/dy_j - \beta) */
             Multiply(y, ytmp, dedx, 0);

source/test/TSum.cpp

@@ -73,7 +73,7 @@ bool TestSum1()
     bGPU->SetData(bData, unitNum);
 
     /* call sum function */
-    Sum(aGPU, bGPU);
+    _Sum(aGPU, bGPU);
 
     /* check results */
     gpuTest = aGPU->CheckData(answer, unitNum);
@@ -151,7 +151,7 @@ bool TestSum2()
     cGPU->SetZeroAll();
 
     /* call Sum function */
-    Sum(aGPU, bGPU, cGPU, beta);
+    _Sum(aGPU, bGPU, cGPU, beta);
 
     /* check results */
     gpuTest = cGPU->CheckData(answer, unitNum);