Update ShowMemUsage function in XMem.cpp.

2. fix the bug of onehotandindex
3. modify the data initilization of transformer
4. add the DumpFormat (need reimplement)

1. Merge with Huchi branch (replace all requireLink with enableGrad that allows gradient computation for a tensor);
2. Update the global memory size (This may make the memory size a little bit larger than the old version).

1. Enable the isGradEfficient;
2. Adjust global memory size.

Allocating the global memory pool when it is requested.

1. Global mem mode updated;
2. XTensor function updated to v2 interface;
3. Transformer model updated to v2 interface;
4. FNNLM bug fixed;
5. Other little bugs fixed.

2. Merge with Xiao branch.

2. Add MemManager class to manage the memory;
3. Use the new version XList;
4. Add a new interface to create Tensor;
5. Apply MemManager to FNNLM.

1. add gather function 2. add cross entropy forward computation and backward computation 3. code optimization 4. merge with xiaotong-working branch

1. add dropout function 2. add some function in tensor/core/math/unary file 3. merge with xiaotong-working branch