* Update introduction.rst

* First commit for PaddlePaddle documentation

* Update paddle_integ.rst

* Update paddle_integ.rst

* Update paddle_integ.rst

* PaddlePaddle design diagram

* Update paddle_integ.rst

* PaddlePaddle nGraph directory structure

* Update paddle_integ.rst

* Update paddle_integ.rst

* Update paddle_integ.rst

* Update paddle_integ.rst

* Update paddle_integ.rst

* Update paddle_integ.rst

* Update paddle_integ.rst

* Update paddle_integ.rst

* Update paddle_integ.rst

* Update paddle_integ.rst

* Update paddle_integ.rst

* Update paddle_integ.rst

* Update paddle_integ.rst

* Update paddle_integ.rst

* Update paddle_integ.rst

* Add edits from PR 2578

* update paddle_integ.rst

* limit user option to one flag

* add space for if

* check if intel cpu only backend

* cosmetic

* make it clear

* Align to look pretty

* docs update

* Update gold release date and features

* Diagram that shows FW & HW support for main md

* Simplified nGraph architecture for CPU

* Complex architecture diagram for all backends

* Replace

* Add ngraph stack diagram with FW and HW support

* relocate

* Relocate

* Replace stack diagram with NNP-L & NNP-I

* Updated copy and removed the disclaimer

* Removed "more detailed" sentence

* Update README.md

* Fixed sentence

* Update README.md

* nGraph logo small version

* Update README.md

* Added logo

* nGraph logo smallest version

* nGraph logo with header

* Update README.md

* Delete ngraph_logo_header.png

* nGraph logo with header

* Update README.md

* nGraph header on the main repo page

* Added header

* nGraph architecture simplified for CPU

* nGraph architecture complex

* Added architecture simple architecture diagram

* Modified the full stack diagram

* nGraph architecture simple diagram with padding

* Added padding to simple architecture image

* Update ABOUT.md

* Updated the sentences with NNP full name

* Handle models in prototxt format.
Signed-off-by: Adam Rogowiec <adam.rogowiec@intel.com>

* Convert Onnx models to text format.

* Tool for conversion between protobuf ONNX models in binary and text format.
Signed-off-by: Adam Rogowiec <adam.rogowiec@intel.com>

* Update ONNX test models text format.

* Convert ONNX LSTM model to text format.

* Rename and make second argument optional.

* Unify models metadata.

* Remove onnx binary models.

* Review: fix comments.

* Fix not yet updated models extension in UTs.

* Add UT with binary protobuf models.

* Clang format.

* Remove failing UT in prototxt since it has problems with CI.

* Inhibit logging protobuf errors.

* Revert "Remove failing UT in prototxt since it has problems with CI."

This reverts commit 94741a8c4594f3cc2ebdca428fa40b94a79240c2.

* Remove LogSilencer from onnx importer api and remove respective UT.

* Conversion script updates

I thought I committed this change to the last PR, but it didn't go through.

* update friendly names to work properly in serialized graphs

* style

* fix compile error

* Fix bug introduced by #2238 on r0.15 (#2515)

* Fix bug introduced by #2238

* style

* Avijit/add diag 4 distributed debugging (#2523)

* Fix bug introduced by #2238

* Added a debug logging macro: NGRAPH_DIST_DEBUG which prints the timestamp and MPI rank for distributed AllReduceops

* Fixed code formatting.

* Moved the logging implementation to log.cpp

* Fixed clang warning

* Don't use namespace in header

* Fix ifdef

* disable warning

* Fix files that had missing headers (#2539) (#2541)

* Update mkl-dnn to v0.18. (#2543)

* Update mkl-dnn to v0.18.

* Update mkl-dnn patch file.

* Fixed Centos build issues (gcc 4.8.5 doesn't implement std::put_time - hence the issue). Also fixed a logical error in the distributed setup for unit tests (#2545)

* Migrate Klocwork issues (#2557)

* Migrate Klocwork fixes

* change to kick off another build

* Fix crash by correcting index (#2561)

* Update build script to fix Windows build issues and add some work tow… (#2531)

* Update build script to fix Windows build issues and add some work towards making codegen work on Windows.

* Use "git apply" instead of "patch". (#2532)

Enable using pre-installed MKLDNN on Window.

* Remove commented out lines.

* Update gold release date and features

* Diagram that shows FW & HW support for main md

* Simplified nGraph architecture for CPU

* Complex architecture diagram for all backends

* Replace

* Add ngraph stack diagram with FW and HW support

* relocate

* Relocate

* Replace stack diagram with NNP-L & NNP-I

* Updated copy and removed the disclaimer

* Removed "more detailed" sentence

* Update README.md

* Fixed sentence

* Update README.md

* nGraph logo small version

* Update README.md

* Added logo

* nGraph logo smallest version

* nGraph logo with header

* Update README.md

* Delete ngraph_logo_header.png

* nGraph logo with header

* Update README.md

* nGraph header on the main repo page

* Added header

* nGraph architecture simplified for CPU

* nGraph architecture complex

* Added architecture simple architecture diagram

* Modified the full stack diagram

* nGraph architecture simple diagram with padding

* Added padding to simple architecture image

* Update ABOUT.md

* Add new logo to doc landpage

* Fix typo

* replace macro with proper function declaration

* fix merge error

* split runtime backend and executable source files

* style

* address one-hot tests

* get backends passing unit tests

* disable OneHot test until it can be fixed

* add ngraph and std namespaces to c++ files

* style

* Extend compile API to take in PassConfig object

* fix override warning

* remove extra semicolon

* cmake fixes to support cases where include_path has multiple directories

* Help pybind find the overloaded compile methods

* Limit compile-api exposed through PyBind (#2530)

* clang-format

* Remove setter for compilation mode to prevent post-init changes. Add compile-mode warning.

* Removed pass_config include

* fix merge

* Fix bug introduced by #2238

* Added a debug logging macro: NGRAPH_DIST_DEBUG which prints the timestamp and MPI rank for distributed AllReduceops

* Fix bug introduced by #2238 on r0.15 (#2515)

* Fix bug introduced by #2238

* style

* Fixed code formatting.

* Moved the logging implementation to log.cpp

* Fixed clang warning

* Don't use namespace in header

* Fix ifdef

* disable warning

* Fixed Centos build issues (gcc 4.8.5 doesn't implement std::put_time - hence the issue). Also fixed a logical error in the distributed setup for unit tests

* Skeleton for faster validation asserts

* Switch to __VA_ARGS__ for compatibility, remove -Wno-variadic-macros

* Add benchmarks for constructing Add and Convolution

* Quick hack to avoid shadowing inside the CHECK macro

* Quick hack to avoid inadvertent capture inside the macro

* Update convolution, and change a bunch of tests to anticipate the new error class

* Fallback to default pooling kernels when mkldnn doesn't support input format

* create default output descriptors

* [ONNX] change [] into .at()

* Update graph.cpp

* Fix bug introduced by #2238

* Apply style.