* Use uniform naming for external project prefixes and use INSTALL_DIR instead of SOURCE_DIR for referencing prebuilt external libraries.

* TBB: Use single variable to share path across files.

* pass HostTensor all the way down

* fix distributed build error

* Cleaner API doc reference for compile call

* Add a useful table for nGraph namespaces

* Remove layout namespace

* Show exploding kernel problem on illustration like IEEE preso

* Inplace convert for bitcasting ops

* Dont passthrough blocked layouts

* More checks for types not handled by mkldnn

* IntelGPU backend: Separate backend and executable classes (#2447)

* Add notice to main ToC page about distributed training

* adding quantized convolution builders for ONNX

* fix build error

* fix CMakeLists.txt spacing

* update gcpu to new backend api

* cleanup

* undo change

* add memory header for unique_ptr

* disable test for MLSL as well thows error on centos

* cleanup from new backend api

* more cleanup

* CMake: Only add subdirectories if needed.
CMake: Disable TBB on Windows.

* CMake: mkl-dnn is only needed for CPU backend.

* CMake: Check dependency between options.

* CMake: Eigen is only needed for CPU or GENERIC_CPU backend.

* Enable TBB on Windows.

* Disable tools unit test if nGraph tools are disabled.

* Update docs for PR 2353

* Fix missing flag designator

* Refer to the Intel® MLSL properly as a spelled-out acronym for first instance

* Fix missing compilation designator

* Finalize editing on CPU backend

* Update doc version to be even with what is in master branch

* Removed typo from docu build instruction command line cd command probably accidental

* Add PR feedback to doc

* [ONNX] Add support for ONNX sinh op

* [ONNX] Test the sinh op and improve an error msg about not supported op version

* [ONNX] Fix the failing tests by moving sinh to opset 1

* [ONNX] Apply clang-format to fix failing CI builds

* [ONNX] Add and test ONNX cosh op

* [ONNX] Add and test ONNX cosh op

* [ONNX] Add and test ONNX sign op

* [ONNX] Test the sign operator with more challenging values

* [ONNX] Update of supported ops documentation table

* [ONNX] Add null node.

Optional inputs in ONNX standard are represented by empty string.
We need a placeholder to keep information which inputs are not provided.

* Rename class null_node -> NullNode

* Remove unnecesary validate_and_infer_types method

* Add <memory> header

* Change name != "" -> !name.empty()

* Change constructor

* Little description

* Change node type in NullNode

* Add is_null() method

* Docstring

* Add UT

* Use override

* Style check

* Update null_node.cpp

New Backend API attempt #3

* quick fix to add openmpi as default

* add finalize to distributed class & use unit test

* use intel mlsl github link

* apply style

* address a few comments

* fix test

* update nbench cmake

* remove extras

* fix a bug

* add counter to finalize and cleanup

* test ci error

* address mlsl ci error

* update flag names, as mentioned in pr comment

* revert back the link to mlsl repo and tag

* add flag to finalize

* apply style

* debug with info

* delete when flag is true

* add distributed setup class works, tests pass

* fix style

* remove extra instance

* disable the test due to a bug

* change flag to ompi

* remove the dependency of setting NGRAPH_DISTRIBUTED_ENABLE flag

* cleanup

* change extern to static

* remove the option NGRAPH_DISTRIBUTED_ENABLE setting this flag

* formatting

* update flags not catched by ci

* make unique pointer

* remove unused bool, fix clang error

* CPUQuantFusion pass and some usions for converting mixed precision sub-graphs to int8 fused ops

* - Added unit tests and misc bug fixes for mixed-precision fusions
- Adjust fused sum_scale in quantization builders instead of mkldnn
  primitive creation

* IntelGPU backend: Slice operation datatypes fix

* e correct type for int64_t