Merge with XU Chen branch (Don't use this! It's an incomplete version)

1. Clean the codes.
2. Fix minor errors.

source/Main.cpp

@@ -63,155 +63,3 @@ int main( int argc, const char ** argv )
     
     return 0;
 }
-
-void BackwardTest()
-{
-    XNet net;
-
-    XTensor a;
-    XTensor b;
-    XTensor c;
-    a.enableGrad = true;
-    b.enableGrad = false;
-    c.enableGrad = false;
-    XTensor mean;
-    XTensor origin;
-    InitTensor2DV2(&a, 2, 3);
-    InitTensor1DV2(&b, 2);
-
-    a.SetZeroAll();
-    b.SetZeroAll();
-    a.Set2D(1.0F, 0, 0);
-    a.Set2D(2.0F, 0, 1);
-    a.Set2D(3.0F, 0, 2);
-    a.Set2D(4.0F, 1, 0);
-    a.Set2D(5.0F, 1, 1);
-    a.Set2D(6.0F, 1, 2);
-
-    b.Set1D(2.0F, 0);
-    b.Set1D(1.0F, 1);
-
-    DivDim(a, b, c, 0);
-    c.Dump(stderr, "c:");
-    auto loss = CrossEntropy(c, a);
-
-    //XLink::ShowNetwork(stderr, &c);
-
-    net.Backward(loss);
-
-    a.grad->Dump(stderr);
-
-}
-
-void TransposeTest()
-{
-#ifdef USE_CUDA
-    XMem mem0(0, UNI_FREE, MILLION * 64, 1024, MILLION * 64);
-    //XMem mem1(1, UNI_FREE, MILLION * 64, 1024, MILLION * 64);
-    XTensor x;
-    XTensor y;
-    XTensor z;
-
-    int loops = 2000;
-
-    int B = 3 * 2 * 4;
-    int K = 8 * 1;
-    int N = 50;
-    int H = 512 * 4;
-
-    int nnn = GDevs.nGPU;
-
-    InitTensor3DV2(&x, B, N, H, X_FLOAT, 0);
-    InitTensor4DV2(&y, K, B, N, H/K, X_FLOAT, 0);
-    InitTensor3DV2(&z, B, N, H, X_FLOAT, 0);
-
-    cudaEvent_t ctime0;
-    cudaEvent_t ctime1;
-    cudaEvent_t ctime2;
-    cudaEvent_t ctime3;
-    cudaEvent_t ctime4;
-    cudaEvent_t ctime5;
-
-    float elapsedSplit = 0.0;
-    float elapsedMerge = 0.0;
-    float elapsedSum = 0.0;
-
-    cudaEventCreate(&ctime0);
-    cudaEventCreate(&ctime1);
-    cudaEventCreate(&ctime2);
-    cudaEventCreate(&ctime3);
-    cudaEventCreate(&ctime4);
-    cudaEventCreate(&ctime5);
-
-    cudaEventRecord(ctime0, 0);
-
-    double time0 = GetClock();
-    for(int i = 0; i < loops; i++)
-        _Split(&x, &y, 2, K);
-    double time1 = GetClock();
-    
-    cudaEventRecord(ctime1, 0);
-    cudaEventSynchronize(ctime1);
-    cudaEventElapsedTime(&elapsedSplit, ctime0, ctime1);
-
-    cudaEventRecord(ctime2, 0);
-
-    double time2 = GetClock();
-    for(int i = 0; i < loops; i++)
-        _Merge(&y, &x, 3);
-    double time3 = GetClock();
-
-    cudaEventRecord(ctime3, 0);
-    cudaEventSynchronize(ctime3);
-    cudaEventElapsedTime(&elapsedMerge, ctime2, ctime3);
-
-    cudaEventRecord(ctime4, 0);
-
-    double time4 = GetClock();
-    for(int i = 0; i < loops; i++)
-        _Sum(&x, &z, &x);
-    double time5 = GetClock();
-
-    cudaEventRecord(ctime5, 0);
-    cudaEventSynchronize(ctime5);
-    cudaEventElapsedTime(&elapsedSum, ctime4, ctime5);
-
-    fprintf(stderr, "split:%f merge:%f sum:%f\n", time1 - time0, time3 - time2, time5 - time4);
-    fprintf(stderr, "split:%f merge:%f sum:%f\n", elapsedSplit, elapsedMerge, elapsedSum);
-#endif
-}
-
-void SumDimTest()
-{
-    XTensor x;
-    XTensor y;
-    XTensor z;
-
-    int a = 5;
-    int b = 7;
-    int c = 3;
-
-    InitTensor3DV2(&x, a, b, c, X_FLOAT, -1);
-    InitTensor1DV2(&y, c, X_FLOAT, -1);
-    InitTensor3DV2(&z, a, b, c, X_FLOAT, -1);
-
-    x.SetZeroAll();
-    y.SetZeroAll();
-    z.SetZeroAll();
-
-    DTYPE * data = new DTYPE[x.unitNum];
-
-    for(int i = 0; i < x.unitNum; i++)
-        data[i] = (DTYPE)i;
-    x.SetData(data, x.unitNum);
-
-    for(int i = 0; i < y.unitNum; i++)
-        data[i] = -(DTYPE)i;
-    y.SetData(data, y.unitNum);
-
-    _SumDim(&x, &y, &z, 2);
-
-    z.Dump(stderr, "z:");
-
-    delete[] data;
-}

source/tensor/XCall.cpp

@@ -842,7 +842,7 @@ XTensor * NewTensor5D(const int d0, const int d1, const int d2, const int d3, co
 XTensor * NewTensorRange(int lower, int upper, int step, const TENSOR_DATA_TYPE myDataType, const int myDevID, const bool isEnableGrad)
 {
     int size = abs(upper - lower);
-    int unitNum = ceil(1.0 * size / abs(step));
+    int unitNum = (int)ceil(1.0 * size / abs(step));
 
     XTensor * tensor = NewTensor1D(unitNum, myDataType, myDevID, isEnableGrad);
     tensor->Range(lower, upper, step);