* CPUQuantFusion pass and some usions for converting mixed precision sub-graphs to int8 fused ops

* - Added unit tests and misc bug fixes for mixed-precision fusions
- Adjust fused sum_scale in quantization builders instead of mkldnn
  primitive creation

* IntelGPU backend: Slice operation datatypes fix

* e correct type for int64_t

* [ONNX] Move make_ng_constant to Tensor class

* [ONNX] Add workaround for initializers without corresponding inputs

* Fix malformed test models

* clang-format

* Avoid creating multiple constants

* Code review comments

Fix cmake TBB lib path on Windows.

* Fix memory leak

* Add comments

* Update CODEOWNERS

* Fix hybrid

* Fix in place

* Style

* Adding non in-place support for all fused convadds

* fixed quantized test case on GPU build

* Add new Introduction section based on IEEE presentation and illustrations

* WIP changes to doc navigation

* Update illustrations

* Cleaner ToC

* Minor fixes to the theme and removing useless bower files

* Better captions

* Revise intro

* Latest

* Make framework support section be its own section

* More updates to backend support section and add a new cpp api

* add changes to section

* Update intro with better detail

* Rework intro with better detail on motivation

* Editing

* Update README with new contrib guide filename

* Add the illustration referred to RE MobileNet group convolution fusion

* Fix off-by-a-line emph on code description

* Fix off-by-a-line emph on code description

* prep work

* wip

* remove debug

* style

* update unit test

* [ONNX] Add support for ONNX sinh op

* [ONNX] Test the sinh op and improve an error msg about not supported op version

* [ONNX] Fix the failing tests by moving sinh to opset 1

* [ONNX] Apply clang-format to fix failing CI builds

* [ONNX] Add and test ONNX cosh op

* [ONNX] Add and test ONNX cosh op

* IntelGPU backend: Min and Max operations fix

* IntelGPU backend: PR2357 style changed if/else to switch/case

* IntelGPU backend: PR2357 passed tests adjusted

* IntelGPU backend: PR2357 failed test removed

* Fix Klocwork issues

* style

* fix windows build

* wip

* mkldnn seems to build

* address various errors building cpu backend with MSVC

* wip

* wip

* Windows support.

    * Delete dependency of LLVM when building with MSVC.

* Define EIGEN_HAS_CONSTEXPR when using MSVS.

* Fix MSVC build errors.

    * Incorrect argument to 'decltype'. It is VC bug. Work around the
    error with rename the function into different name.

    * MINMAX issue in matmul_bias.cpp.

    * Correct TBB_LINK_LIBS on Windows.

* Fix MSVC link errors.

    1. redefine problems in cpu_builder.obj and convert_layout.obj. It
    is because cpu_builder.hpp contains an implicit implement of
    function runtime::cpu::Builder::build for cpu::op::ConvertLayout.
    The fix is deleting the registration item in cpu_builder.cpp and
    using REGISTER_CPU_OP_BUILDER in convert_layout.cpp.

    2. Fix the dependent libraries path on Windows. It should be *.lib
    not *.dll when linking these libraries.

* Set visibility for CPU backend to fix the MSVC linker error.

    MSVC complain that the .def file exceed the size limitatoin
    when using CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS. All the functions
    with CPU_BACKEND_API are used by unit test or nbench.

* Fix unit test build errors on Windows.

    * backend_unary_elementwise.in.cpp: Use all_close_f to test case
    BACKEDND sqrt

    * cpu_fustion.cpp: Fix 'NUM_STEPS' cannot be implicitly
    captured because no default capture mode has been specified

    * cpu_test.cpp: Use portable setenv and unsetenv from misc.hpp.

    * tools.cpp: Use portable fpopen from misc.hpp.

    * misc.hpp/misc.cpp: Add new files to host misc functions that Linux and
    Windows using different implementation.

* Make Debug mode work with MSVC.

* style

* fix line ending

* remove general splitting code. New code in hybrid transformer.

* more cleanup

* builds

* pass unit test

* cleanup

* -   check to verify if the data_slices shares the same weights

* add the serialized graph

* - explicitly fuse the data slices, so all the parameter partitioned by slices are in contigous memory location
- fixes all the failing test cases

* Fix inconsistent ifdefs that broke macos build
Add quant ops to op table
Define serialize/deserialize for Quant con, avg pool, max pool
Add empty cases to interpreter

* iGPU cases.

* Include quant ops

* Define ngpu emitters

* Use pre-built tbb on macos

* Review comments

* Only copy lib when changed