* speedup split_op
test=develop

* speedup split_op
test=develop

* rename ConcatGrad to Split

* refine concat and split
test=develop

* fix compile error

* Fix CPPLint errors in operators

* Fix cast in softmax

* Fix softmax_mkldnn

* Fix send_recv_op_test

* Send_recv

* Fix softmax mkldnn

There are mainly following fixes:

- take `DeviceContext` as the template parameter of math functors and OpKernel instead of `Place`
- remove `eigen_device` interface in base class  `DeviceContext`
- remove `GetEigenDevice` interface in `ExecutionContext` and base class `DeviceContext`
- remove unused `platform::EigenDeviceConverter`
- rename `REGISTER_OP_GPU_KERNEL` to `REGISTER_OP_CUDA_KERNEL`
- rename `USE_GPU_ONLY_OP` to `USE_CUDA_ONLY_OP`

* fix seq_concat with refactaring LoD

* fix failed unit test

* rename function name

* Remove template parameter for Tensor methods

* Also check the type is correct when data()
* Simplize holder_

* Fix accuracy_op

* Register Code