Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>

Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
Co-authored-by: Robert Kimball <robert.kimball@intel.com>

* Helper function get_axes_mapping.

* Enhance Broadcast:v1 NUMPY broadcasting.

- Enable NUMPY broadcasting mechanism to work in bothdirections:
    target_shape <-> arg_shape

* Add opset1:squeeze and fix bug in reading squeezed axis idx.

* Fix and enhance downgrade pass for Broadcast:v1

* Use Broadcast:v1 in ONNX Expand operator.

* Replace Broadcast:v0 with v1 in some helper functions.

* Remove call to deprecated legacy_broadcasting helper function.

* Add helper get_axes_mapping_output function.

* Use directly Broadcast:v1 instead of helper function.

* Get back operators from v0 in helper function.

* Use helper function and some refactoring.

* Add legacy style broadcast helper function for opset1.

* User helper broadcasting function for arithmetic operators.

* Add empty axis only if its size is equal to one.

* Aplly review remarks:

- Rename broadcasting function deleting _values_ infix
- Remove variables used only once.
- Use STL library where possible.
- Remove unnecessary conditions.

* Add helper for Broadcast:v1.

* Fix merge artifact and force unsigned type for argument.

* Review. Add additional check for static output.

* Apply clang-format.

* Fix: call v0 ops in ngraph::builder namespace.
Co-authored-by: Robert Kimball <robert.kimball@intel.com>

* Address warnings generated when compiled with gcc 4.8 and -Wall

* Don't set -Wall for external projects

* Pass CMAKE_ORIGINAL_CXX_FLAGS not CMAKE_CXX_FLAGS to external projects.

* Fix pragmas for gcc 4.8

* fix windows build
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

This reverts commit 90a1f581.

Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Printing cleanup

Add Input/Output
Simplify element type
Simplfy Node printing  implementation, try to de-noise it a bit
Enable printing of Node*

* Adjust printing

* Add doc note

* Update src/ngraph/node.cpp
Co-Authored-By: Robert Kimball <robert.kimball@intel.com>

* Update src/ngraph/node.hpp
Co-Authored-By: Robert Kimball <robert.kimball@intel.com>

* Cleanup

* typo
Co-authored-by: Robert Kimball <robert.kimball@intel.com>

Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Switch to PartialShape in onnx_importer ValueInfo

* Construct dynamic dimensions out of ONNX dimensions defined as dim_param

* Validate the PartialShape of inputs created from an ONNX model with dynamic shapes

* Validate the output shape inference for a dynamic ONNX model

* Test the execution of an ONNX model with dynamic dimensions

* Test the Ax+B with more than one batch size

* Provenance tagging adjustments - PartialShape instead of Shape

* Correct translation of ONNX shapes to nG shapes

* Test the shape of Constant produced by scalar initializers

* Review comments & more strict assertions in UT

* UT checking a dynamic rank input

* Fully dynamic input inference test

* first dynamic version

* modified UTs

* Added assert checks

* Added specialised methods

* first verion of AvgPool

* code review remarks introduced

* Changed tests to use default BackendMode value

* Reverted not related changes

* code review remarks introduced

* Set static backend as default
Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>

* Move non-templated constructor implementation to the source file

* Optimize constant constructor for uniform constant

* Cleanup

* Much faster deserialize constant

* Adding unit tests

* Unit tests

* Update unit test

* Cleanup

* style

* Cleanup nbench output

* wip

* Fix specializations

* Change from unique to shared_ptr internally

* Enable copy of Constant

* cleanup Constant ctors

* Fix copy contructor

* Fix compile error
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Add folder to keep helper classes for PyTorch.

* Add basic build structure.

* Disable ATen support by default.

* Style.

* Add provenance tag in opset0 downgrade pass

* Add provenance tag in opset1 upgrade pass

* Type name as string

* Change op_cast to return replacement_node instead of bool

* Add provenance tags to all nodes created while downgrade

* Add provenance tags to all nodes created while upgrade

* Comments

* Style apply

* Update ONNX import provenance test function

* Add const statement

* Add upgrade/downgrade provenance tag tests

* Update tests

* Style apply

* Provenance enabled check

* Removed redundant add_tag

* Test for add_provenance_tags above

* Add graph test for provenance tags in transformation pass

* Use EXPECT_TRUE and EXPECT_FALSE instead of EXPECT_EQ

* Return replacement node directly

* Style apply

* Test downgrade provenance tag with ONNX importer

* Update test/onnx/onnx_import_provenance.in.cpp
Co-Authored-By: Michał Karzyński <postrational@users.noreply.github.com>

* Test update

* Update provenance test to check node type occurence

* Style apply
Co-authored-by: Michał Karzyński <postrational@users.noreply.github.com>
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Add provenance tag in fused decomposition pass

* Add and update test for decomposition tag

* Style apply

* Style apply
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

Co-authored-by: aslepko <44713115+aslepko@users.noreply.github.com>

* v1 Subtract Constant Folding

* Code style fix
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

Co-authored-by: Michał Karzyński <postrational@users.noreply.github.com>

* Update sitemap to not use a page title

* Release notes for 0.29

* New min Sphinx version for python3-sphinx

* style apply

* update CPUTensorView with memory_pointers

* add wait_to_read and wait_to_write

* remove nullptr default and add second set of APIs

* fix int_executable APIs
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Add env_util files and update getenv_bool

* More getenv cleanup

* More env cleanup

* Add env var file

* fix doc file

* cleanup

* Update doc string

* Fix compile errors

* Fix compile error

* Fix compile error

* Fix one more

* Fix compile error

* Revert MLIR changes due to failing test

* Revert MLIR changes due to failing test

* Fix compile error

* Fix env var usage
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Switch to PartialShape in onnx_importer ValueInfo

* Construct dynamic dimensions out of ONNX dimensions defined as dim_param

* Validate the PartialShape of inputs created from an ONNX model with dynamic shapes

* Validate the output shape inference for a dynamic ONNX model

* Test the execution of an ONNX model with dynamic dimensions

* Test the Ax+B with more than one batch size

* Provenance tagging adjustments - PartialShape instead of Shape

* Correct translation of ONNX shapes to nG shapes

* Test the shape of Constant produced by scalar initializers

* Review comments & more strict assertions in UT

* UT checking a dynamic rank input

* Fully dynamic input inference test

* ONNX provenance tags adjustments and back to get_shape

* Remove an obsolete space in provenance tags
Co-Authored-By: Michał Karzyński <postrational@users.noreply.github.com>

* Remove an obsolete space in provenance tests
Co-authored-by: Michał Karzyński <postrational@users.noreply.github.com>
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Fix compilation warnings

* Camels

* Add simpler API to get input node

* style check

* Change shr_ to shared_
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* LRU cache for caching graphs

* static

* LRU Cache

* Cache graph

* Make data members static

* Temp test case functional

* Temp test case functional

* Fix shape

* Make lru local to dynamic wrapper

* Make cache thread safe

* Remove static copies of data members

* Add a separator  between shapes of different inputs

* Clear list and map in destructor

* Caching on values of shape relevant inputs

* Replace cout's by NGRAPH_INFO

* Add a environment variable for cache size

* Add mutex header

* style

* change to int64_t

* Save the cloned function to get the output shape to allocate output storage

* Pass inputs without wrapping

* Fix conv shape relevant inputs

* gcc 4.8 doesnt support ostring stream as a copyable object

* Pass key by reference

* PR feedback

* Apply suggestions from code review

* Replace malloc
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
Co-authored-by: Robert Kimball <robert.kimball@intel.com>

Co-authored-by: asemx <998264+asemx@users.noreply.github.com>
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

Co-authored-by: Jayaram Bobba <jayaram.bobba@intel.com>
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Added FP32 to FP16 conversion transformation

* Update src/ngraph/pass/convert_fp32_to_fp16.cpp
Co-Authored-By: Robert Kimball <robert.kimball@intel.com>

* Update src/ngraph/pass/convert_fp32_to_fp16.hpp
Co-Authored-By: Robert Kimball <robert.kimball@intel.com>

* Added NGRAPH_API for fp32 to fp16 conversion
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
Co-authored-by: Robert Kimball <robert.kimball@intel.com>

* [ LSTMCell ] Setting number of outputs for LSTMCell op

* Fixed comments
Co-authored-by: Evgenya Stepyreva <evgenya.stepyreva@intel.com>

* Make pattern matcher node-based

Simplify implementation
Add support for Or, Branch
Start of support for recurrent pattern

* Only save state at branch points

* Factor Or out of label

* Documentation

* Review

* Only ops need to match on shape/output index