* fix throw in cpu_memory_optimization

* add input_tensor back

* more descriptive bail-out msg

* add version.hpp to ngraph install files for external backends

* update date

* update licenses for 2019

* style

* Add broadcasting to variadic OP in opset 8.

* Apply style format.

* Update onnx_import.cpp

* nGraph compat updates

* Simplify op structure

* Add zero-dim elimination pass

* Add logical data conversion pass

* Add graphviz support

* Add implicit broadcast pass

* Elide unnecessary reshape ops

* Merge reshapes into convolutions

* Add winograd convolution support

* Allow three-input maxpool backprop

* Add concat elision

* Combine replication operations

* Elide unneeded replicates

* Style update

* Fix numeric instability in batchnorm bprop

* Another instability

* print llvm build choice and allow cmake arg to override env var

* fix cmake error

* use existing function

* [ONNX] detect automatically value types of TensorProto and AttributeProto
Signed-off-by: Artur Wojcik <artur.wojcik@intel.com>

* onnx: style apply
Signed-off-by: Artur Wojcik <artur.wojcik@intel.com>

* Forward nGraph's C/C++ compiler, build type and generator information to cmake based external projects.

* Fix typo.

* Pass generator related info properly.

* Googletest is using DEBUG_POSTFIX

* TBB uses postfix for debug lib.

* Fix typo.

* Add GPUH hybrid backend

* update manifests

* update node operator<<

* fix GOE

* remove debug

* remove debug

* more cleanup

* add parent support to cpu and intel gpu backend tensors

* cleanup

* fix odd failure when printing node during construction

* fix node output

* address review comments

* style

* update build byproducts to support ninja

* remove unused cmake code

* more cmake cleanup

* display error message if Ninja generator is requested

* fix mkldnn ext project

* revert onnx cmake file

* revert protobuf cmake file

* revert mlsl cmake file

* more fixing

* Support dynamic scales for Qconv's and Dequantize

* Remove constant folding

* add additional dynamic_quantize unittest

* add another mxnet quantize unittest

* add additional dynamic_dequantize tests

* fix shape error

* add dynamic signed_quantize unittest

* Pass correct scale

* Refactoring

* Added dynamic scale support for QCBA and QCBSA

* Refactor to create MKLDNN primitives on the first iteration

* remove stray code

* unused variables

* remove extraneous line

* Graph comparison testing quiet unless problem is detected.

* Fixed file formatting

* Renamed ss => msg

* cleanup and add enum

* new type working

* enum works

* use type enum

* cleanup

* fix errant past to source file

* fix type

* safely construct the type map

* fix get_type_info_map return type

* editing docs

* more doc updates

* Cleanup theme, update backends for PlaidML, remove stale font

* Add PlaidML description and doc update that should have been added with PR 1888

* Add PlaidML description and doc update that should have been added with PR 1888

* Latest release doc updates

* Add PlaidML description and doc update for PR 1888
* Update glossary with tensor description and quantization def
* Refactor landpage with QuickStart guides
* Add better details about nGraph features and roadmap

* Placeholder detail for comparison section

* Add section link

* order sections alphabetically for now

* update compiler illustration

* Address feedback from doc review

* Update illustration wording

* Formatting and final edits

* keep tables consistent

* Clarify doc on bridge and compiler docs

* Clarify doc on bridge and compiler docs

* yay for more feedback and improvements

* edit with built doc

* Fix typo

* Another phase of PR review editing

* Final review comment resolved

* note grammatically-correct wording preferred as often as possible.

* First iteration of shared subgraphs with onnx doc

* Updte onnx wheel install instructions with latest ngraph-0.9.0 versioning

* Updte onnx wheel install instructions with latest ngraph-0.9.0 versioning

* Update section  on subgraphs and shared subgraph docs

* Finalize edit of mxnet tutorial given status of our PR

* Make sure latest conf py is being used

* Update to latest index

* Add link to design doc mentioned by Ashoke and update about for consistent headings

* Update with PR feedback

* Update with new pip install instructions

* add more testing

* Further feedback review included

* Improve descriptions, given the new pip pkg install options

* Add note to onnx_ssg_tutorial

* Links updated to latest correct url

* Improve docs for Beta

* Reorganize TOC

* Better org in sections

* Make heading style consistent across indexes

* Update intro to framework builders

* Update intro to framework builders

* Add feedback from reviewers

* Minor fixes to ToC and editing

* Add section on FMV for miscellaneous use cases

* Update notice on README

* Updte link to howto index

* fix typo

* fix note

* Update glossary

* Fixed the benchmark file to reflect the updated compile function usage.  Compile returns the compiled function now

* Removed redundant compilation

all_close_f error reporting clarification. all_close_f test cases spaced out for easier interpretation. (#2247)

* make validate public

* move compile call outside of call for unit tests

* fix compile error

* one more error

* Move CPU ReshapeSinking to Core pass

* Modify clang compile error

* Fix for style-apply check

* refactor into invidivual sinkerso

* adding individual sinkers

* add a header back

* fix build break

* Enable in place slice when slice's arg is function input.

* Add a corner case.

* Add codegen support.

* Set the correct offset for in-place-slice when there is a chain of in place ops starting from parameter.

* matcher's strict mode

* fix clang warnings

* Pass layouts through where feasible for unary and binary elementwise ops

* compilation fix for leaky relu

* Expose API enabling to get supported ONNX operators set.

* Review comments.

- Don't expose operator function handlers, just return list of names.

* Function rename.