* staged.

* polish code

* polish code. test=develop

* polish code. test=develop

* api change. test=develop

* fix default value. test=develop

* fix default value. test=develop

* Optimize key creation of INT8 pool kernel to improve the peformance of ResNet-50 and MobileNet, especially for latency.
test=develop

* Optimize key creation of pool fp32 grad.
test=develop

test=develop

test=develop

* refile profiler
test=develop

* follow comment
test=develop

* - Implemented draft of primitive desc keeping in Tensor

test=develop

- TransposeMKLDNNHandler::AcquireSrcMemory was reimplemented

- Added nchw and nc formats setting for sake of compatiblity

Fixed unit tests

- Worakaround to problem with 5D data in conv

- Added 3D and 1D MKL-DNN formats for name handles for tensor

test=develop

- Fix to UTs

test=develop

- Conv fp32 op was updated

Cosmetic fixes

test=develop

- tensor mkldnn cosmetics

test=develop

- Moved most of mkl-dnn specific code from Tensor to mkl-dnn utils

* - Lint fixes

test=develop

* - setting prim dec in Tensor , sets also layout to kMKLDNN

test=develop

* - Moved creation of prim desc totally out of Tensor

test=develop

* - Cosmetic fixes adter review

test=develop

test=develop

reason: dereferencing smart pointer is the same as the underlying pointer
test=develop

* Revert "Optimze Gelu with MKL Erf function (#15770)"

This reverts commit 676995c8.

* test=develop

test=develop

* Optimize for gelu operator

* Set up the low accuracy mode of MKL ERF function.

test=develop

* Only enable MKLML ERF when OS is linux

* Use the speical mklml version included vmsErf function to verify gelu mkl kernel.

test=develop

* Add the CUDA macro to avoid NVCC's compile issue.

test=develop

* Add the TODO comments for mklml library modification.

test=develop

* Clean Code

test=develop

* Add the comment of marco for NVCC compiler.

test=develop

test=develop

test=develop

* refine profiler && add runtime tracer

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* fix bug && test=develop

* add thread id map && test=develop

* test=develop

* testing

* bug fix

* remove cuda event && refine code && test=develop

* test=develop

* test=develop

* test=develop

* fix windows temp file && test=develop

* test=develop

* fix windows bug && test=develop

* fix start up issue && test=develop

* code polish &&  test=develop

* remove unused code && test=develop

* add some cupti cbid && test=develop

* add FLAGS_multiple_of_cupti_buffer_size && test=develop

* fix compile error && test=develop

* add keyword && test=develop

* fix && test=develop

* code polish && test=develop

* Enable momentum operator for a ngraph engine
test=develop

* Update tests
test=develop

* Unnecessary line of the code as intended was removed
test=develop

* fix warnings

test=develop

* fix enforce test

test=develop

test=develop

test=develop

test=develop

test=develop

test=develop

test=develop

* Added accuracy ngraph op test=develop

* fixed name type 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

test=develop

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

test=develop

checkpoint for distributed training.