Support fp16 data type for more operations and fix the minor errors.  (Don't use this! It's an incomplete version)

1. Support scalar tensor for Multiply and Div operation;
2. Fix backward bugs in Multiply and Div function;
3. Minor bugs fixed.

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).

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. Bug fixed; 2. Support abs, sign, convert data type(float <->int) ;3. Merge with xu and xiao branch