* Rename PlaidML_Executable::save -> save_as_format

* Repair regression in PlaidML tensor impl

This was caused by the recent removal of the offset parameter for tensor read/write operations -- we missed a
spot where read/write were being called for synchronization purposes.

* Disable a few more PlaidML tests pending triage

* Skip elision of reshape->reshape

It turns out this doesn't work, because the downstream reshape's input_order axis vector is incorrect if the
upstream reshape is removed.

* Add element type to PlaidML tensor debug output

* Use nGraph booleans for PlaidML boolean data

We'd previously been using i8; that's been deprecated for boolean data now that we have an explicit boolean
element type.

* Set PlaidML convolution output shapes correctly

We weren't transposing the output shape; we were computing the right data, but the incorrect shape metadata
causes validation to fail.

* Add a PlaidML implicit broadcast op

Better nGraph shape validation was tripping up PlaidML's use of a reshape to replace explicit broadcasts with
implicit NumPy-style broadcasts (since the reshape's output shape would be incorrect for the downstream
elementwise operation).  Adding this implicit broadcast operation lets PlaidML tell nGraph something useful
about the shapes, making validation pass (when it's otherwise correct).

* GenerateMask correction
Add an attribute that controls if the seed should be set on each use
Convert to new virtual method for description implementatin

* Support for switching to dynamic attributes.

* GenerateMask changes in CPU backend (#3042)

* Add CPU builder and kernel for new GenerateMask API

* Remove dead code

* Fix unit-test, PR feedback, file permissions

* Disable new test for non-supporting backends

* Fix CI error

* Codegen support

* Style check

* Fix CI error

* Unit tests for MatMulInteger

* Add ONNX MatMulInteger op

* Add QuantizedLinearMatmulInteger builder

* Additional unit test

* Exclude tests on nVidia GPU backend

* Add 4D test case

* Enable >2D MatMulInteger

* Refactoring to MatMulFactory - step 1

* Refactoring to MatMulFactory - step 2

* Remove `using namespace ngraph` to make `Node` unambiguous.

* Disable quantized ops tests on GPU backend

* Remove unused `includes`

* Remove redundant dynamic_pointer_cast

* Remove redundant `move`

* Add const correctness

* Code review comments

* Style apply

* Add documentation

* Use more complex shapes in tests

* Test messages improvements

* Add comment

* and remove conversion from floating point contexts

* Use friendly_name in visualization

* sytle

* wip

* cleanup

* style

* Add CPU backend support for Tile op using Eigen kernel.

* Emit Tile code for CODEGEN.

* Fix a bug.

* Add one comment and fix error message typo.

* Added build option to disable fast math

* Change option name

* Added float16 support for constant op

* Fix Compilation issue.

* Style.

* Change serializer disable so that it is enabled by default if you do nothing

* fix serializer disable

* fix disabled build

* layout-aware cpu tensor copy_from

* - add unit test case for tensor "copy_from"
- set default layout after copy_from src to destination

* - added test case to copy between two different layouts

* - fix clang error
 - added test case to check copy_from if the two tensor layouts are different
- fix the LayoutDesc comparision

* fix windows build error

* - move "cop_from" unit tests from tensor to cpu_test

* fix compilation error

* Added more unit tests

* fix read and write API in cpu_tensor_view

* Failing conv test case

* Opt for mkldnn::algorithm::convolution_direct if input channel is less than 8

* Comment

* Unified interpolate layer op

* Minor attr name changes

* Use Eigen kernel for Gather when axis is 0.

* Fix style error.

* Rename variables.

Fix bugs.

Use helper function.

* Add one unit test.

* Check if openmp is defined.

* Change unit tests.

* Use Eigen kernel for uint8_t type.

Add one uint8_t unit test.

Address PR feedback.

* Update cpu emitter.

* Use updated reduced-size clDNN

* Remove the obsolete BOOST_VERSION variable

* remove tensor offset from tensor read/write calls because it was never used

* fix build errors

* fix build errors

* fix python test errors

* more python fixes

* revert change

* Make old version of read/write deprecated

* fix python read overload

* one more try to fix python binding

* fix python

* yet another try

* why is this so hard

* fix?

* add text to changes.md

* add BatchMatMul unit test to all builds

* Check that interpreter is available

* fix error

* enable tests for features not yet implemented

* wip

* build works with serialize disabled

* one more try

* disable unit test when json disabled

* handle case where serialize is disabled in python test

* one more fix

* Fix klocwork issues

* Need dynamic cast

* Update to use new backend constructor pattern

* Update PlaidML unit test exclusions

*  Use Eigen kernel for ScatterAdd.

* Emit ScatterAdd Eigen kernel for CODEGEN.

Add comments.

Address PR feedback.

* Add more unit tests.

Fix style error.

Add ScatterAdd to AssignOpMap.

* Combine non-scalar cases together.

* Address PR feedback.

* Fix a bug.

* Use reshape to make the shapes of two slices match.

* Rename variables.

Fix bugs.

Use helper function.

Add one unit test.

* Add reshape back.

* Added getters for dynslice

* Style check fixes

* Combine transpose and reshape pattern into a single reshape

* optimize reshapes only if in/out shapes dont match

* Default to svg format for visualizing graphs and provide an env variable to change it

* Handle 0 and -1 in shape inputs for dynamic reshape op

* Flag to control semantics of zero values in dynreshape op

* Support for no-arg op construction

* Add a-ops.

* Two const init variations to try to solve windows link error

* Try export for windows

* Create outputs as needed, test

* Remove attribute helpers

* another windows try

* windows

* windows

* Partial node cleanup

* Review comments
Node destruction that doesn't blow out the stack on deep graphs

* Review comments

* Update src/ngraph/node.hpp
Co-Authored-By: Adam Procter <adam.m.procter@intel.com>

* Have huge test check that nodes were deleted

* Switch constructors to use Output instead of Node

* Review comments

* Add some comments

Avoid negative values in int64 initialization for cases where int64 parameters are used as indices (#3004)

* handle case where a node's output is connected multiple inputs of another node

* fix creation of the FunctionCall to have the correct outputs

* fix per review comment

* Cleanup how compile flags set and used by nGraph and external projects.
Set C++11 through CMake and pass it down to external projects.
Prefer CMake variables such as CMAKE_POSITION_INDEPENDENT_CODE and
CMAKE_CXX_STANDARD instead of explicitly setting compiler dependent
flags.
Create json compilation database for external projects.
CMAKE_CXX_FLAGS is used as common global options for nGraph and external
projects.
add_compile_options() is used for local options for current and sub
directories.
add_definitions() is used for setting definitions for current and sub
directories.
Note: Global options are not passed down to some external projects.
Note: mkl-dnn resets CMAKE_CXX_FLAGS internally.
Note: TBB and MLSL are not CMake based.
Noet: Eigen and json is header only library.

* Fix error.

* Fix error. (second attempt)

* Cleanup code.

* Allow check for undefined macro.

* Try to fix cldnn issue.

* Set type for CMake arguments.

* Pass C++ standard to protobuf.

* Pass C++ standard down to TBB.

* Change how Clang specific flags are handled.

* Fix error.

* Workaround for compile error on Baidu's PDPD docker.

* Fix windows build error.

* Initial implementation of implicit broadcasting for eltwise ops. Only Add supported

* Addressed PR feedback

* cleanup

* Rename Bcast to Broadcast

* Autobroadcasting support for rest of elementwise ops

* Serializer support for autobroadcast

* Added missing autob serialization for Minimum

* Added execution unit tests and more op types to implicit broadcast elimination

* Addressed PR feedback

* Fixes windows build issue

* RVO optimization per PR feedback

* serialize constant faster

* more speedup

* Draft of FakeQuantize operation along with UTs.

* Add FakeQuantize to implemented operators on IGPU.

* Get back FakeQuantize op case to switch.

* Fix compilation errors.

* Skip test for INTERPRETER backend and disable type_prop tests.

* Initial implementation covering the most basic case

* Cleanup of fake_quantize_with_clip UT

* Reformat the cpu unit tests manifest and unlock anothe fake quant UT

* Handle the clipping case by subtracting input_low from quantization input

* Clip the input data before quantization to avoid Selects

* UT manifest fix

* Obsolete comment removed

* Code formatting

* Broadcast input data for non-scalar in/out params

* Code formatting

* Enable the type prop tests for FakeQuantize

* Dequant the data without using the Dequantize op (fixes an edge case)

* Move reshape from utils to builder.

* Add aliases to functions in old place and describe changes.