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: 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: Scott Cyphers <diyessi@users.noreply.github.com>

* remove code

* Cleanup

* cleanup

* cleanup

* Fix build error

* Move executable to separate file

* style
Co-authored-by: raramer01 <rebecca.a.ramer@gmail.com>

* Rename tensor_view to tensor

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

* Cleanup null distributed device

* Fix build error

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

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

* stringstream version

* string concat for faster performance

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

* Fixed GEMM conversion

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

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>

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

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

* Move op to v0 namespace

* BatchMatMul

* BatchNorm*

* CompiledKernel

* Constant

* Fix more

* More

* Fix Quantaized*

* fix last v0 ops

* fix compile error

* fix build error

* Fix GPU build

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

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

* Add attribute visitor to xor op

* Add attribute visitor to VariadicSplit op

* Add attribute visitor to Unsqueeze op

* Add attribute visitor to Transpose op

* Add attribute visitor to TopK op

* Add attribute visitor to Tile op

* Add attribute visitor to Tanh op

* Add attribute visitor to Tan op

* Add attribute visitor to StridedSlice op

* Add attribute visitor to Squeeze op

* Add attribute visitor to SquaredDifference op

* Add attribute visitor to Split op

* Add attribute visitor to SpaceToDepth op

* Add attribute visitor to Sqrt op

* Add attribute visitor to Softmax op

* Add attribute visitor to Sinh op

* Add attribute visitor to Sin op

* Add attribute visitor to Sign op

* Add attribute visitor to ShuffleChannels op

* Add attribute visitor to ShapeOf op

* Add attribute visitor to Selu op

* style

* Review Fix I

* Add attribute visitor to TensorIterator op

* Revert "Add attribute visitor to TensorIterator op"

This reverts commit 04850068f3a3e3b6ddcea58023327c76df574fa1.

* Add support for AutoBroadcast in attribute_visitor

* Add tests for operators with attributes
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
Co-authored-by: Robert Kimball <robert.kimball@intel.com>

Co-authored-by: raramer01 <rebecca.a.ramer@gmail.com>

- unit test for split with specialized function
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Allow for opset extensions

* Remove raw pointer from OpSet (#4395)

* style
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>

add missing space, otherwise "error: corrupt patch at line 12"

* Add new attribute adapters for vector<float> and vector<string> types

* Add attribute visitor to LSTMSequence op

* Add attribute visitor to LSTMCell op

* Add attribute visitor to LRN op

* Add attribute visitor to LogicalNot op

* Add attribute visitor to Log op

* Add attribute visitor to HardSigmoid op

* Add attribute visitor to GRN op

* Add attribute visitor to GroupConvolutionBackpropData op

* Add attribute visitor to GroupConvolution op

* Add attribute visitor to GatherTree op

* Add attribute visitor to Gather op

* Add attribute visitor to Floor op

* Add attribute visitor to FakeQuantize op

* Add attribute visitor to Exp op

* Add attribute visitor to Erf op

* Add attribute visitor to Elu op

* Add test for LRN, LSTMSewuence and LSTMCell

* Add test for Elu

* Add test for FakeQuantize

* Revert user_op test missed

* Add test for GRN

* Fix for CoordinateDiff

* Add tests for GroupConvolution and GroupCinvolutionBackpropData

* Tests alphabetical reorder
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>

Co-authored-by: Ashok Emani <ashok.emani@intel.com>

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>