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).

Fix bugs of FNNLM when isGradEfficient is on.

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.

CPU code update for Windows.

# Conflicts:
#	source/tensor/XDevice.cpp
#	source/tensor/XMem.cpp
#	source/tensor/XTensor.cpp

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.