Bug fixed and clean codes. (IMPORTANT)

1. Fix the bugs for MatrixMul functions which may cause nan in some cases. (IMPORTANT)
2. Fix the minor errors.

source/tensor/core/arithmetic/MatrixMul.cpp

@@ -159,6 +159,10 @@ void _MatrixMul(const XTensor * a, MATRIX_TRANS_TYPE transposedA,
                       "The code must be run on the same GPU!");
         
         int devIDBackup;
+
+        if (beta == 0)
+            c->SetZeroAll();
+
         ProtectCudaDev(a->devID, devIDBackup);
 
         cublasHandle_t * handle = a->mem != NULL ? a->mem->GetCublasHandle() : GDevs.GetCudaHandle(a->devID);

source/tensor/core/arithmetic/MatrixMul2D.cpp

@@ -50,7 +50,7 @@ void _MatrixMul2D(const XTensor * a, MATRIX_TRANS_TYPE transposedA,
                   XPRunner * parallelRunner, XStream * stream)
 {
     CheckNTErrors((a && b && c), "Empty input tensors!");
-    CheckNTErrors((a->dataType == b->dataType), "Input tensors should                have the same data type!");
+    CheckNTErrors((a->dataType == b->dataType), "Input tensors should have the same data type!");
     CheckNTErrors((a->order == 2 && b->order == 2 && c->order == 2),
                   "Input tensors must have a order = 2!");
 
@@ -83,9 +83,9 @@ void _MatrixMul2D(const XTensor * a, MATRIX_TRANS_TYPE transposedA,
             c->dataType == DEFAULT_DTYPE)
         {
 #if defined(USE_BLAS)
-                _MatrixMULCPU(a, transposedA, b, transposedB, c, alpha, beta);
+            _MatrixMULCPU(a, transposedA, b, transposedB, c, alpha, beta);
 #else
-                _MatrixMul2DParallel(a, transposedA, b, transposedB, c, alpha, beta, parallelRunner);
+            _MatrixMul2DParallel(a, transposedA, b, transposedB, c, alpha, beta, parallelRunner);
 #endif
         }
         else {

source/tensor/core/arithmetic/MatrixMul2D.cu

@@ -156,6 +156,9 @@ void _CudaMatrixMul2D(const XTensor * a, MATRIX_TRANS_TYPE transposedA,
         if (stream != NULL)
             cublasSetStream(*handle, stream->stream);
 
+        if (beta == 0)
+            c->SetZeroAll();
+
         if (a->dataType == X_FLOAT && b->dataType == X_FLOAT && c->dataType == X_FLOAT) {
             _CudaBLASMatrixMUL(handle, a->data, transposedA, a->dataType, 
                                b->data, transposedB, a->dataType, c->data, c->dataType,

source/tensor/core/arithmetic/MatrixMul2DParallel.cpp

@@ -54,6 +54,9 @@ void _MatrixMul2DParallel(const XTensor * a, MATRIX_TRANS_TYPE transposedA,
     int aColNum = am;
     int bColNum = bm;
 
+    if (beta == 0)
+        c->SetZeroAll();
+
     /* a * b */
     if (transposedA == X_NOTRANS && transposedB == X_NOTRANS) {
         RunParallel2D(parallelRunner, (void*)_MatrixMul2DMultiTheading, an * am * bm,

source/tensor/core/arithmetic/MatrixMulBatched.cpp

@@ -118,6 +118,9 @@ void _MatrixMulBatchedGPU(const XTensor * a, MATRIX_TRANS_TYPE transposedA,
         blockNum *= a->dimSize[i];
     }
 
+    if (beta == 0)
+        c->SetZeroAll();
+
     int devIDBackup = 0;
     ProtectCudaDev(a->devID, devIDBackup);
 
@@ -260,7 +263,7 @@ void _MatrixMulBatchedCPU(const TensorList * a, MATRIX_TRANS_TYPE transposedA,
         CheckNTErrors((bi->order == 2), "2d tensor (i.e., matrix) is required!");
         CheckNTErrors((ci->order == 2), "2d tensor (i.e., matrix) is required!");
 #ifdef USE_BLAS
-            _MatrixMULCPU(ai, transposedA, bi, transposedB, ci, alpha, beta);
+        _MatrixMULCPU(ai, transposedA, bi, transposedB, ci, alpha, beta);
 #else
         _MatrixMul2D(ai, transposedA, bi, transposedB, ci, alpha, beta);
 #endif