* Move some ops into v0

* namespace

* Make comments pretty

* Make comments pretty

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

* Checking if provenance_tags key exists

* Add provenance tag prototype

* Format provenance tag

* Display provenance tag

* Clean debug printing

* Add const to variables

* Separate method for add provenance tags

* Return NodeVector reference

* Return const NodeVector

* Moved add_provenance_tags function to commons

* Style apply

* Simple model for tests

* Provenance tag test

* Expect substring instead of  equal

* Add provenance tags to intermediate nodes recursively

* One tag per node

* Add traverse node args instead of recursion

* Return NodeVector instead of set of pointers

* Use treverse_nodes and lambda function

* Remove unused helper functions

* Remove is_constant() condition

* Update test model prototxt

* Update test substring

* Make code slightly more readable
Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
Co-authored-by: Michał Karzyński <postrational@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: Michał Karzyński <postrational@users.noreply.github.com>
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>

* Use normalize in onnx importer

* Introduced changes after code review
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.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: Robert Kimball <robert.kimball@intel.com>

* Call generic CPU kernels for Broadcast and Reshape

* Move generic kernels to opt_kernel

* Use strides in broadcast
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* separate mlir core to a lib

* rename in one more file

* change core lib linking to PUBLIC

* New GCPU layout

* Passing tests

* Test passing

* Move GCPU to the gcpu directory since names must match

* Revert "Move GCPU to the gcpu directory since names must match"

This reverts commit a51f50699d0d1ab602a71226687cf053a9ade27d.

* Cleanup

* Disable some onnx tests

* Fix manifest

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

* Add option NGRAPH_EXPORT_TARGETS_ENABLE
Default value is TRUE
This option controls exporting and installing ngraph cmake config files.
Static library build only works with NGRAPH_EXPORT_TARGETS_ENABLE=OFF
for now.

* Turn off option for static nGraph lib.

* Register backends

* Add missing header files.
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Remove ScalarConstantLikeBase

* Remove code no longer needed
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* wip

* Add unit test to check that every v0 op properly implements the is_* methods in Node
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* CSE optimizations

* Get TI working with clang 6
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Fix spelling, and comment formatting.

* Update Reduction operation to use v1 operators.

* Upgrade/downgrade passess for ReduceMin/Max ops.

* Address review comments:

- Remove unnecessary AutoBroadcast arg.
- Use default_opset namespace.
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

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

* Use v1 ops in ONNX Softplus

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

* Use v1::Broadcast in ONNX LpNorm

* Missing include

* Missing include

* Include the default opset in lp_norm.cpp

* Reference Constant from default_opset

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

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

* Update MKLDNN to v1.1.1.

* Modify mkldnn_v1 patch.

* Modify bf16 check for mkldnn-v1.
Co-authored-by: baojun <32073718+baojun-nervana@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>

* Fix maxpoolbprop layout pass

* Use default format for max pooling bprop.

* Fix MaxPoolWithIndicesBackprop unit test.

* Fix CODEGEN.

* Modify MaxPoolWithIndicesBackprop unit test.
Co-authored-by: Amy Zhuang <amyzhuang97@gmail.com>
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Fix using statements

* Add missing line ending

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

* Remove conditional compile

* style
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>

* Use v1::Minimum and v1::Maximum in ONNX Clip implementation

* Use v1::Maximum in ONNX LeakyRelu
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>

* Enable self-concat to broadcast replacement for a single concat.

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

* Affine lowering support for
    1) GreaterEq
    2) LessEq
    3) Equal
    4) NotEqual

* - cast result op from i1 to i8 for comparision operators

* Addressed PR comments

* Style fix

* - style check
- use select instead of zero_extendi durinng CompOp lowering

* - fix style
- use createOneConstant and createZeroConstant helpers in select intrinsic

* Use NG_U8_TYPE_ID for BooleanType in ngraph dialect

* Diable CE and Softmax unit test in MLIR

* - LIT parser test for comparision ops

* - Affine dailect LIT tests for Comparision Ops

* Address PR feedback

* fix typo

* - use `cast` to deduce element Type
- add more strict type checking to LIT Test

* fix CHECK label's for comparision ops

* Use UInt8 in verification logic for CMP op's

* - use UInt8 for the resultOp verification Logic in CMP op
- fix unit test failures

* Update license to new year

* Pick up some strays

* [MLIR] Update MLIR/LLVM repo

I need it to get MemRef lowering override mechanism (291a309d).

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

* wip

* Use AlignedBuffer instead of vector for performance

* cleanup

* More cleanup

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

* update matmul fprop

* clean up

*  - emit mlkddn for LRN only for normalizing acorss/within channel

* - remove explicit checking of axes in lrn builder
Co-authored-by: Jayaram Bobba <jayaram.bobba@intel.com>

* Backprop matmul maybe works - due to internal error with /usr/bin/ar issue file truncated, I could`t check it

* fix error

* clean up

* update

* fix style
Co-authored-by: baojun <32073718+baojun-nervana@users.noreply.github.com>

* Pass _GLIBCXX_USE_CXX11_ABI to protobuf

- this change allows building nGraph with newer GLIBC: v5.1+

* Specify _GLIBCXX_USE_CXX11_ABI only when NGRAPH_USE_CXX_ABI is defined

* first version

* Added constant cast

* Updated ref implementation

* Fixed out element type

* Added UT

* Code refactor

* - update external_mlir_prebuilt.cmake to support pre built MLIR

* fix typo

* - unify prebuilt and external pull, build "mlir" cmake logic
- throw cmake error if MLIR_LLVM_PREBUILT_PATH is not specified when -DNGRAPH_USE_PREBUILT_MLIR=True