* fix compile issue with_distribute test=develop

* simplified logic test=develop

* use ngraph dependency test=develop

* set cpu only test=develop

* update test and eliminate fp16 test test=develop

test=develop

test=develop

* expose peak gpu memory API to python test=develop

* add unittest for peak gpu memory monitoring test=develop

* add pybind change test=develop

* add mutex to gpu mem usage monitor test=develop

* update benchmark flag definition file test=develop

* tweak unittest for memory monitoring test=develop

test=develop

* enable ngraph_engine_op
test=develop

* merge develop test=develop

* avoid const_cast test=develop

* rm ngraph_operator test=develop

* Added TODO to move EnableNgraph test=develop

* Add TODO to remove const_cast test=develop

* Refine the beam_search op and test.

* A basic CUDA implementation of beam_search for small batch_size.

* Implement CUDA kernel for beam_search_op.

* Use multiple CUDA threads in the same block to select the top beam.

* Update the python api of beam_search op.

* Enable extend function in CPU kernel of beam_search op.

* Unify the CUDA codes.
test=develop

* Unify the CPU kernel of beam_search op.

* Ensure the seletced items of beam_search_op's CPU kernel sorted by scores.

* Update the description of beam_search in API.spec.

* Enable the use of CUDA kernel in beam_search op.

* Exclude the beam_search's CUDA unittest when there is no CUDA gpu, and delete some debuging statements.
test=develop

* Follow comments.
test=develop

* Call the CPU kernel for beam_search op when batch_size > 4.
test=develop

* Remove the except of is_empty op in PrepareData.
test=develop