Onnxruntime

Key Updates
Execution Providers
* **[Preview]** Availability of [Windows Machine Learning (WinML)](https://docs.microsoft.com/en-us/windows/ai/windows-ml/) APIs in Windows builds of ONNX Runtime, with [DirectML](https://github.com/microsoft/onnxruntime/blob/master/docs/execution_providers/DirectML-ExecutionProvider.md) for GPU acceleration
* Windows ML is a WinRT API designed specifically for Windows developers that already ships as an inbox component in newer Windows versions
* Compatible with Windows 8.1 for CPU and Windows 10 1709 for GPU
* Available as source code in the GitHub and pre-built Nuget packages (windows.ai.machinelearning.dll)
* For additional documentation and samples on getting started, visit the [Windows ML API Reference documentation](https://docs.microsoft.com/en-us/windows/ai/windows-ml/api-reference)
* TensorRT Execution Provider upgraded to TRT 7
* CUDA updated to 10.1
* Linux build requires CUDA Runtime 10.1.243, cublas10-10.2.1.243, and CUDNN 7.6.5.32. Note: cublas 10.1.x will not work
* Windows build requires CUDA Runtime 10.1.243, CUDNN 7.6.5.32
* onnxruntime now depends on curand lib, which is part of the CUDA SDK. If you already have the SDK fully installed, then it won't be an issue

Builds and Packages
* Nuget package structure updated. There is now a separate Managed Assembly (Microsoft.ML.OnnxRuntime.Managed) shared between the CPU and GPU Nuget packages. The "native" Nuget will depend on the "managed" Nuget to bring it into relevant projects automatically. [PR 3104](https://github.com/microsoft/onnxruntime/pull/3104) Note that this should transparent for customers installing the Nuget packages. ORT package details are [here](https://github.com/microsoft/onnxruntime#builds-and-packages).
* Build system: support getting dependencies from vcpkg (a C++ package manager for Windows, Linux, and MacOS)
* Capability to generate an onnxruntime Android Archive (AAR) file from source, which can be imported directly in Android Studio

API Updates
* SessionOptions:
* default value of max_num_graph_transformation_steps increased to 10
* default value of graph optimization level is changed to ORT_ENABLE_ALL(99)
* OrtEnv can be created/destroyed multiple times
* Java API
* Gradle now required to build onnxruntime
* Available on Android
* C API Additions:
* GetDenotationFromTypeInfo
* CastTypeInfoToMapTypeInfo
* CastTypeInfoToSequenceTypeInfo
* GetMapKeyType
* GetMapValueType
* GetSequenceElementType
* ReleaseMapTypeInfo
* ReleaseSequenceTypeInfo
* SessionEndProfiling
* SessionGetModelMetadata
* ModelMetadataGetProducerName
* ModelMetadataGetGraphName
* ModelMetadataGetDomain
* ModelMetadataGetDescription
* ModelMetadataLookupCustomMetadataMap
* ModelMetadataGetVersion
* ReleaseModelMetadata

Operators
* This release introduces a change to the forward-compatibility pattern ONNX Runtime previously followed. This change was added to guarantee correctness of model prediction and removes behavior ambiguity due to missing opset information. This release adds a model opset number and IR version check - ONNX Runtime will not support models with ONNX versions higher than the supported opset implemented for that version (see [version matrix](https://github.com/microsoft/onnxruntime/blob/master/docs/Versioning.md#version-matrix)). If higher opset versions are needed, consider using custom operators via ORT's custom schema/kernel registry mechanism.
* Int8 type support for Where Op
* Updates to Contrib ops:
* Changes: ReorderInput in kMSNchwcDomain, SkipLayerNormalization
* New: QLinearAdd, QLinearMul, QLinearReduceMean, MulInteger, QLinearAveragePool
* Added featurizer operators as an expansion of Contrib operators - these are not part of the official build and are experimental

Contributions
We'd like to recognize our community members across various teams at Microsoft and other companies for all their valuable contributions. Our community contributors in this release include: [Eric Cousineau](https://github.com/EricCousineau-TRI) (Toyota Research Institute), [Adam Pocock](https://github.com/Craigacp) (Oracle), [tinchi](https://github.com/tinchi), [Changyoung Koh](https://github.com/kcy1019), [Andrews548](https://github.com/Andrews548), [Jianhao Zhang](https://github.com/daquexian), [nicklas-mohr-jas](https://github.com/niklas-mohr-jdas), [James Yuzawa](https://github.com/yuzawa-san), [William Tambellini](https://github.com/WilliamTambellini), [Maher Jendoubi](https://github.com/MaherJendoubi), [Mina Asham](https://github.com/mina-asham), [Saquib Nadeem Hashmi](https://github.com/Saqhas), [Sanster](https://github.com/Sanster), and [Takeshi Watanabe](https://github.com/take-cheeze).

This is a minor patch release on 1.1.1.

This fixes the a minor issue that some logging in execution_frame.cc cannot be controlled by SessionLogVerbosityLevel in SessionOptions. PR 3043

This is a minor patch release on 1.1.0.

Summary
* Updated default optimization level to apply **all** by default to support best performance for popular models
* Operator updates and other bugs

All fixes
* update default optimization level + fix gemm_activation fusion 2791
* Fix C handling of unicode strings 2697
* Initialize max of softmax with lowest of float 2786
* Implement a more stable softmax 2715
* add uint8 support to where op 2792
* Fix memory leak in samples and test 2778
* Fix memory leak in TRT 2815
* Fix nightly build version number issue 2771

Key Updates
* Performance improvements to accelerate BERT model inference latency on both GPU and CPU. Updates include:
* Additional fused CPU kernels as well as related transformers for key operators such as Attention, EmbedLayerNormalization, SkipLayerNormalization, FastGelu
* Further optimization such as parallelizing Gelu and LayerNorm, enabling legacy stream mode, improving performance of elementwise operators, and fusing add bias into SkipLayerNormalization and FastGelu
* Extended CUDA support for opset 11
* Performance improvement for Faster R-CNN and Master R-CNN with new and updated implementation of opset 11 CUDA kernels, including Resize, Expand, Scatter, and Pad
* TensorRT Execution Provider updates, including support for inputs with dynamic shapes
* MKL-DNN (renamed DNNL) updated to v1.1
* **[Preview]** NN API Execution Provider for Android - [see more](https://github.com/microsoft/onnxruntime/blob/master/docs/execution_providers/NNAPI-ExecutionProvider.md)
* **[Preview]** Java API for ONNX Runtime - [see more](https://aka.ms/onnxruntime-java)
* [Tool for Python API](https://github.com/microsoft/onnxruntime/tree/master/onnxruntime/python/tools/featurizer_ops): Automatically maps a dataframe to the inputs of an ONNX graph based on schema information in the pandas frame
* Custom ops can be loaded from shared libraries: Custom ops can now be packaged in shared libraries and distributed for use in multiple applications without modification.

Contributions
We'd like to thank our community members across various teams at Microsoft and other companies for all the valuable contributions.

We'd like to extend special recognition to these individuals for their contributions in this release: [Jianhao Zhang](https://github.com/daquexian) (JD AI), [Adam Pocock](https://github.com/Craigacp) (Oracle), [nihui](https://github.com/nihui) (Tencent), and [Nick Groszewski](https://github.com/groszewn). From the Intel teams, we'd like to thank [Patrick Foley](https://github.com/psfoley), [Akhila Vidiyala](https://github.com/avidiyal), [Ilya Lavrenov](https://github.com/ilya-lavrenov), [Manohar Karlapalem](https://github.com/smkarlap), [Surya Siddharth Pemmaraju](https://github.com/suryasidd), [Sreekanth Yalachigere](https://github.com/sreekanth-yalachigere), [Michal Karzynski](https://github.com/postrational), [Thomas V Trimeloni](https://github.com/tvtrimel), [Tomasz Dolbniak](https://github.com/tomdol), [Amy Zhuang](https://github.com/ayzhuang), [Scott Cyphers](https://github.com/diyessi), [Alexander Slepko](https://github.com/aslepko) and other team members on their valuable work to support the Intel Execution Providers for ONNX Runtime.

Key Updates

General
- [ONNX 1.6](https://github.com/onnx/onnx/releases/tag/v1.6.0) compatibility - operator support for all opset11 ops on CPU, including Sequence ops.
- Free dimension override: Add ability to override free dimensions to the inputs of a model. Free dimensions are tensor shapes which aren't statically known at model author time, and must be provided at runtime. Free dimensions are most often used for the batch size of a model's inputs, allowing for customizable batch sizes at runtime. This feature enables certain optimizations since the shape can be known apriori.
- Performance improvements to further accelerate model inferencing latency on CPU and GPU. Notable updates include:
- Additional CUDA operators added to support Object Detection and BERT models. *Note: CUDA operator coverage is still limited and performance will vary significantly depending on the model and operator usage.*
- Improved parallelism for operators that use GEMM and MatMul
- New implementation for 64 bits MatMul on x86_64 CPU
- Added ability to set of threads used by intra and inter operator parallelism to allow optimal configuration for both sequential and concurrent inferencing scenarios
- Gelu fusion optimizer
- Threading updates:
- Eigen ThreadPool is now the default (previously there were two thread pool implementations, TaskThreadPool and Eigen ThreadPool)
- Ability to disable multiple threading by setting thread pool size to 1 and onnxruntime_USE_OPENMP to OFF.
- MLAS now uses the number of thread pool threads plus one as the parallelism level. (e.g. if you have 4 CPUs, you need to set the thread pool size to 3 so that you only have one thread per CPU)
- [CPU Python package](https://pypi.org/project/onnxruntime) is [manylinux1](https://www.python.org/dev/peps/pep-0513/) compliant. The [GPU Python package](https://pypi.org/project/onnxruntime-gpu/) is manylinux2010 and compatible with CUDA 10.0/cuDNN 7.6
- Support for [CentOS](https://www.centos.org/) 6 and 7 for Python, C, and C++. Most of the code is now C++11 compliant (previously required C++14). C# .NET Core compatibility coming soon.
- Package for [ArchLinux](https://aur.archlinux.org/packages/python-onnxruntime/)
- Telemetry - component level logging through [Trace Logging](https://docs.microsoft.com/en-us/windows/win32/tracelogging/trace-logging-portal) for Windows builds. Data collection is limited and used strictly to identify areas for improvement. You can read more about the data collected and how to manage these settings [here](https://aka.ms/ort-privacy).
- Bug fixes to address various issues filed on Github and other channels

API updates
- Updates to the C API for clarity of usage. The 1.0 version of the API is now stable and will maintain backwards compatibility. Versioning is in supported to accommodate future updates.
- C APIs are ABI compatible and follows Semantic Versioning. Programs linked with the current version of the ONNX Runtime library will continue to work with subsequent releases without updating any client code or re-linking.
- New session option available for serializing optimized ONNX models
- Enabled some new capabilities through the Python and C APIs for feature parity, including registration of execution providers in Python and setting additional run options in C.

Execution Providers (EP)
Updates
- General Availability of the OpenVINO™ EP for Intel® CPU, Intel® Integrated Graphics, [Intel® Neural Compute Stick 2](https://software.intel.com/en-us/neural-compute-stick), and the [Intel® Vision Accelerator Design with Intel® Movidius™ Myriad™ VPU](https://software.intel.com/en-us/iot/hardware/vision-accelerator-movidius-vpu) powered by OpenVINO™nGraph EP support of new operators.
- MKL-DNN EP updated from 0.18.1 to 1.0.2 for an average of 5-10% (up to 50%) performance improvement on ONNX Model Zoo model latency
- nGraph EP updated from 0.18 to 0.26, with support of new operators for quantization and performance improvements on LSTM ops (without peephole) and Pad op
- TensorRT EP updated to the latest TensorRT 6.0 libraries
- Android DNNLibrary version update
New EP support
- *[Preview]* [NUPHAR](https://aka.ms/build-ort-nuphar) (Neural-network Unified Preprocessing Heterogeneous ARchitecture) is a TVM and LLVM based EP offering model acceleration by compiling nodes in subgraphs into optimized functions via JIT
- *[Preview]* [DirectML](https://aka.ms/build-ort-directml) is a high-performance, hardware-accelerated DirectX 12 library for machine learning on Windows, providing GPU acceleration for common machine learning tasks across a broad range of supported hardware and drivers
- *[Preview]* Support for [Intel® Vision Accelerator Design with Intel® Arria™ 10 FPGA powered by OpenVINO™](https://software.intel.com/en-us/iot/hardware/vision-accelerator-arria-10).
- *[Preview]* [ARM Compute Library (ACL)](https://aka.ms/build-ort-acl) Execution Provider targets ARM CPUs and GPUs for optimized execution of ONNX operators using the low-level libraries.

Build updates
- Two new cmake options: onnxruntime_USE_GEMMLOWP, onnxruntime_USE_AUTOML, onnxruntime_USE_DML
- Removed two cmake options: onnxruntime_USE_MLAS/onnxruntime_USE_EIGEN_THREADPOOL. These are always ON now.
- The minimal supported gcc version is 4.8.2

Tooling
- Availability of [ONNX Go Live tool](https://github.com/microsoft/OLive), which automates the process of shipping ONNX models by combining model conversion, correctness tests, and performance tuning into a single pipeline as a series of Docker images.
- Updates to the [quantization tool](./onnxruntime/python/tools/quantization)
- Supports selective quantization for some nodes instead of all possible nodes
- Bias quantization for Conv nodes
- Node fusion for dynamic quantization
- onnxruntime_perf_tool usage updates:
- new option "-y" for controlling inter_op_num_threads
- max optimization level is now 99, and 3 is now an invalid value. In most cases, this tool should be run with "-o 99"

Other Dependency Updates
- Replaced gsl with gsl-lite to be compatible with C++11
- Added NVIDIA cub
- Added Wil for DML execution provider
- Pybind11 updated from 2.2.4 to 2.4.0 to fix a compatibility issue with Baidu PaddlePaddle and some other python modules that are also depend on Pybind11
- TVM updated to a newer version

Bug Fixes
- Fix in C API marshalling for InferenceSession.Run()
- Some fixes in OnnxRuntime server

Only NuGet packages are released for this patch release, because only the C API users are impacted