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

1. Use the _CheckData with tolerance in unit test to avoid the bug in "0.0F != -0.0F" case.
2, Clean the codes.

1. CPU Support for Gather function.
2. Fix the bugs in GPU Gather.
2. Minor error fixed.

1. Supporting efficient propagate and gradient accumulation for backward functions.
2. Update the setData functions.
3. Clean the codes.

1. Move the New/Initial/Del Tensor functions from XTensor.* to XElement.*
2. Move IsSameShaped functions from XTensor.* to core/shape/IsSameShaped.*
3. Move CheckData functions from XTensor.* to core/utilities/CheckData.*

1. fixed the bug in the Spread function.  2. add compare and OnehotAndIndex function 3. optimize the code

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