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

* [MLIR] Use sane utilities to handle environment variables.

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

* get_data boolean support

* compare_values for boolean char

* Register comparator boolean

* Bool type model prototxt

* Test debug

* Test debug cleaning

* Pass output test

* Style apply

* Test update

* Exclude LogicalAnd test on GPU

* Make ng constan for bool

* Style apply

* Copy data for bool

* Tests update

* Style apply

* GPU manifest update

* Test bool constant op

* Store bool as char vector

* Comment update
Co-authored-by: Michał Karzyński <postrational@users.noreply.github.com>
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Remove distributed

* Remove mlsl as external project
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>
Co-authored-by: raramer01 <rebecca.a.ramer@gmail.com>

[SPEC][ONNX] Handle negative axis for TopK:v1, add dynamic shape support for ONNX Arg Min/Max ops (#4291)

* First version

* Added support to no_keep_dims

* Excluded tests for PlaidML

* Code review remarks introduced

* Reduced TopK axis restrictions

* Added assert to TopK get_axis

* Added missing EOF

* Style applied

* Code review suggestions introduced

* Disable tests for GPU

* Code review remarks introduced
Co-authored-by: Scott Cyphers <diyessi@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>

* Disable adding ONNX tags if Provenance disabled globally

* Improve Provenance tests

* Change where get_provenance_enabled is checked.

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

* set NGRAPH_TAG when no TAG file present

* use default build version with custom-build tag
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>

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

* [ONNX] Add new ConstatntOfShape operator

* Fix a bug in op implementation

* Modify downgrade pass to support broadcast scalars

* Style-fix

* Use at instead of []

* Use onnx helper instead of ngraph builder

* Add some UT

* Style fix

* Limit range of DynBroadcast in downgrade pass

* Move tests to better location

* Rewrite tests to test_case

* Add check if arg_pshape is static

* Added unit tests

* finished impl, added tests

* Added missing EOF

* Make tests fully dynamic

* disabled tests for gpu

* Changed file names

* styles applied

* code review remarks introduced
Co-authored-by: Tomasz Socha <tomasz.socha@intel.com>
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Replace arithmetic operators and builders into v1 ops

* Code review remarks introduced

* code review remarks introduced

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

* Add set_config option to python backend

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

* [MLIR] Add a flag to control ngraph dialect fusion pass.

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

* Start finishing cloning with outputs

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

* Review comments, compilation
Co-authored-by: Robert Kimball <robert.kimball@intel.com>

This reverts commit 35d50450.

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

* Defining opset2

* Added opset2
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* FQ output data type copied from 3,4 input data type

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

* Add friendly names to nGraph ONNX nodes generated

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

* [ONNX] Add new ConstatntOfShape operator

* Fix a bug in op implementation

* Modify downgrade pass to support broadcast scalars

* Style-fix

* Use at instead of []

* Use onnx helper instead of ngraph builder

* Add some UT

* Style fix

* Limit range of DynBroadcast in downgrade pass

* Move tests to better location

* Rewrite tests to test_case

* Add check if arg_pshape is static

* Style

* Trigger CI
Co-authored-by: Michał Karzyński <postrational@users.noreply.github.com>
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Changed constant to scalar.

* Used v1 div.

* Code refactoring.

* Bugfix.

* Bugfix

* Bugfix

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

* Move Executable to its own files

* Normalize class names

* More cleanup
Co-authored-by: Chris Sullivan <chris.sullivan@intel.com>

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

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

* [MLIR] Update MLIR repo

* Nagy's fix

* Changes related to mlir-opt

* Update MLIR commit

* [MLIR] Enable bare ptr calling convention

This PR adds a flag to enable the bare pointer calling convention
in LLVM lowering pass.

* Update MLIR commit and callbacks.

* Disable 'noalias' attribute.

It will be re-introduced in a follow-up commit.

* Remove '__mlir' prefix in callback test

* Address feedback

* Fix EDSC includes

* Move MLIR repo forward

* Update type converter code

* Address feedback

* Enable 'noalias' code

* Address feedback
Co-authored-by: Amy Zhuang <amyzhuang97@gmail.com>
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>

[ONNX] builder::split used by onnx importer should produce v1 ops

avoid error tautological-constant-out-of-range-compare

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

* [MLIR] Update MLIR repo

* Nagy's fix

* Changes related to mlir-opt

* Update MLIR commit

* Update MLIR commit and callbacks.

* Disable 'noalias' attribute.

It will be re-introduced in a follow-up commit.

* Remove '__mlir' prefix in callback test

* Address feedback

* Fix EDSC includes

* Move MLIR repo forward

* Update type converter code

* Address feedback
Co-authored-by: Amy Zhuang <amyzhuang97@gmail.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

* first verion of AvgPool

code review remarks introduced

Changed tests to use default BackendMode value

* first version of maxpool

* Changed PoolingFactory to support dynamic shapes

* fixed Pad op

* Added Uts to global ops

* Code review remarks introduced

* code review remarks introduced

* Code refactor

* Code review remarks introduced
Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>

* Added Round op to onnx importer.

* Added a new line.

* Excluded test from plaidml.

* Code formatting.

* Added header.

* Unabled test on gpu.
Co-authored-by: Chris Sullivan <chris.sullivan@intel.com>
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>

* Update MKLDNN to v1.2.

* Change class to struct.

* Change to struct.
Co-authored-by: Robert Kimball <robert.kimball@intel.com>
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>