optimize quantize

.gitmodules

@@ -25,10 +25,6 @@
 [submodule "cmake/external/re2"]
 	path = cmake/external/re2
 	url = https://github.com/google/re2.git
-[submodule "cmake/external/onnx-tensorrt"]
-	path = cmake/external/onnx-tensorrt
-	url = https://github.com/onnx/onnx-tensorrt.git
-        branch = v5.0
 [submodule "cmake/external/eigen"]
 	path = cmake/external/eigen
 	url = https://github.com/eigenteam/eigen-git-mirror.git
@@ -41,3 +37,7 @@
 [submodule "cmake/external/spdlog"]
 	path = cmake/external/spdlog
 	url = https://github.com/gabime/spdlog.git
+[submodule "cmake/external/onnx-tensorrt"]
+	path = cmake/external/onnx-tensorrt
+	url = https://github.com/onnx/onnx-tensorrt.git
+	branch = 5.1

README.md

@@ -11,15 +11,19 @@
 [ONNX](https://onnx.ai) is an interoperable format for machine learning models supported by various ML and DNN frameworks and tools. The universal format makes it easier to interoperate between frameworks and maximize the reach of hardware optimization investments.
 
 ***
+**[Key Features](#key-features)**
+
 **Setup**
 * [Installation](#installation)
 * [APIs and Official Binaries](#apis-and-official-builds)
 * [Building from Source](#building-from-source)
 
-**Getting Started**
+**Usage**
 * [Getting ONNX Models](#getting-onnx-models)
 * [Deploying ONNX Runtime](#deploying-onnx-runtime)
-* [Examples and Tutorials](#examples-and-tutorials)
+* [Performance Tuning](#performance-tuning)
+
+**[Examples and Tutorials](#examples-and-tutorials)**
 
 **More Info**
 * [Technical Design Details](#technical-design-details)
@@ -29,39 +33,43 @@
 
 **[License](#license)**
 ***
-## Key Features
-### Run any ONNX model
+# Key Features
+## Run any ONNX model
 ONNX Runtime provides comprehensive support of the ONNX spec and can be used to run all models based on ONNX v1.2.1 and higher. See version compatibility details [here](https://github.com/microsoft/onnxruntime/blob/master/docs/Versioning.md).
 
-*Note: Some operators not supported in the current ONNX version may be available as a [Contrib Operator](https://github.com/microsoft/onnxruntime/blob/master/docs/ContribOperators.md)*
-
 **Traditional ML support**
 
 In addition to DNN models, ONNX Runtime fully supports the [ONNX-ML profile](https://github.com/onnx/onnx/blob/master/docs/Operators-ml.md) of the ONNX spec for traditional ML scenarios.
 
-### High Performance
+For the full set of operators and types supported, please see [operator documentation](https://github.com/microsoft/onnxruntime/blob/master/docs/OperatorKernels.md)
+
+*Note: Some operators not supported in the current ONNX version may be available as a [Contrib Operator](https://github.com/microsoft/onnxruntime/blob/master/docs/ContribOperators.md)*
+
+
+## High Performance
 ONNX Runtime supports both CPU and GPU. Using various graph optimizations and accelerators, ONNX Runtime can provide lower latency compared to other runtimes for faster end-to-end customer experiences and minimized machine utilization costs.
 
 Currently ONNX Runtime supports the following accelerators:
-* CPU
-  * MLAS (Microsoft Linear Algebra Subprograms)
-  * MKL-DNN
-  * MKL-ML
-  * [Intel nGraph](https://github.com/microsoft/onnxruntime/blob/master/docs/execution_providers/nGraph-ExecutionProvider.md)
-* GPU
-  * CUDA
-  * [TensorRT](https://github.com/microsoft/onnxruntime/blob/master/docs/execution_providers/TensorRT-ExecutionProvider.md)
+* MLAS (Microsoft Linear Algebra Subprograms)
+* [MKL-DNN](https://github.com/microsoft/onnxruntime/blob/master/docs/execution_providers/MKL-DNN-ExecutionProvider.md) - [subgraph optimization](https://github.com/microsoft/onnxruntime/blob/master/docs/execution_providers/MKL-DNN-Subgraphs.md)
+* MKL-ML
+* [Intel nGraph](https://github.com/microsoft/onnxruntime/blob/master/docs/execution_providers/nGraph-ExecutionProvider.md)
+* CUDA
+* [TensorRT](https://github.com/microsoft/onnxruntime/blob/master/docs/execution_providers/TensorRT-ExecutionProvider.md)
+* [OpenVINO](https://github.com/microsoft/onnxruntime/blob/master/docs/execution_providers/OpenVINO-ExecutionProvider.md)
+* [Nuphar](docs/execution_providers/Nuphar-ExecutionProvider.md)
 
-Not all variations are supported in the [official release builds](#apis-and-official-builds), but can be built from source following [these instructions](https://github.com/Microsoft/onnxruntime/blob/master/BUILD.md).
+Not all variations are supported in the [official release builds](#apis-and-official-builds), but can be built from source following [these instructions](https://github.com/Microsoft/onnxruntime/blob/master/BUILD.md). Find Dockerfiles [here](https://github.com/microsoft/onnxruntime/tree/master/dockerfiles).
 
 We are continuously working to integrate new execution providers for further improvements in latency and efficiency. If you are interested in contributing a new execution provider, please see [this page](docs/AddingExecutionProvider.md).
 
-### Cross Platform
+
+## Cross Platform
 [API documentation and package installation](https://github.com/microsoft/onnxruntime#installation)
 
 ONNX Runtime is available for Linux, Windows, Mac with Python, C#, and C APIs, with more to come!
 If you have specific scenarios that are not currently supported, please share your suggestions and scenario details via [Github Issues](https://github.com/microsoft/onnxruntime/issues).
-
+***
 # Installation
 **Quick Start:** The [ONNX-Ecosystem Docker container image](https://github.com/onnx/onnx-docker/tree/master/onnx-ecosystem) is available on Dockerhub and includes ONNX Runtime (CPU, Python), dependencies, tools to convert from various frameworks, and Jupyter notebooks to help get started.
 
@@ -80,28 +88,34 @@ Additional dockerfiles for some features can be found [here](https://github.com/
 |---|:---|:---|:---|
 | **Python** | **[pypi: onnxruntime](https://pypi.org/project/onnxruntime)**<br><br>Windows (x64)<br>Linux (x64)<br>Mac OS X (x64) | -- | **[pypi: onnxruntime-gpu](https://pypi.org/project/onnxruntime-gpu)**<br><br>Windows (x64)<br>Linux (x64) |
 | **C#** | **[Nuget: Microsoft.ML.OnnxRuntime](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime/)**<br><br>Windows (x64, x86)<br>Linux (x64, x86)<br>Mac OS X (x64) | **[Nuget: Microsoft.ML.OnnxRuntime.MKLML](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.MKLML/)**<br><br>Windows (x64)<br>Linux (x64)<br>Mac OS X (x64) | **[Nuget: Microsoft.ML.OnnxRuntime.Gpu](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.Gpu/)**<br><br>Windows (x64)<br>Linux (x64) |
-| **C** | **[Nuget: Microsoft.ML.OnnxRuntime](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime)**<br><br>**[.zip, .tgz](https://aka.ms/onnxruntime-release)**<br><br>Windows (x64, x86)<br>Linux (x64, x86)<br>Mac OS X (x64 | **[Nuget: Microsoft.ML.OnnxRuntime.MKLML](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.MKLML/)**<br><br>Windows (x64)<br>Linux (x64)<br>Mac OS X (x64) | **[Nuget: Microsoft.ML.OnnxRuntime.Gpu](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.Gpu/)**<br><br>**[.zip, .tgz](https://aka.ms/onnxruntime-release)**<br><br>Windows (x64)<br>Linux (x64) |
+| **C/C++ wrapper** | **[Nuget: Microsoft.ML.OnnxRuntime](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime)**<br><br>**[.zip, .tgz](https://aka.ms/onnxruntime-release)**<br><br>Windows (x64, x86)<br>Linux (x64, x86)<br>Mac OS X (x64) | **[Nuget: Microsoft.ML.OnnxRuntime.MKLML](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.MKLML/)**<br><br>Windows (x64)<br>Linux (x64)<br>Mac OS X (x64) | **[Nuget: Microsoft.ML.OnnxRuntime.Gpu](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.Gpu/)**<br><br>**[.zip, .tgz](https://aka.ms/onnxruntime-release)**<br><br>Windows (x64)<br>Linux (x64) |
 
 #### System Requirements (pre-requisite dependencies)
 * ONNX Runtime binaries in the CPU packages use OpenMP and depend on the library being available at runtime in the
 system.
   * For Windows, **OpenMP** support comes as part of VC runtime. It is also available as redist packages:
     [vc_redist.x64.exe](https://aka.ms/vs/15/release/vc_redist.x64.exe) and [vc_redist.x86.exe](https://aka.ms/vs/15/release/vc_redist.x86.exe)
   * For Linux, the system must have **libgomp.so.1** which can be installed using `apt-get install libgomp1`.
-* GPU builds require the **CUDA 10.0 and cuDNN 7.3** runtime libraries being installed on the system. Older releases used 9.1/7.1 - please refer to [release notes](https://github.com/microsoft/onnxruntime/releases) for more details.
-* Python binaries are compatible with **Python 3.5-3.7**. See [Python Dev Notes](https://github.com/microsoft/onnxruntime/blob/master/docs/Python_Dev_Notes.md)
+* GPU builds require CUDA runtime libraries being installed on the system:
+	 * Version: **CUDA 10.0** and **cuDNN 7.3**
+	 * Linux Python packages require **CUDA 10.1** and **cuDNN 7.6** 
+  * Older ONNX Runtime releases: used **CUDA 9.1** and **cuDNN 7.1** - please refer to [prior release notes](https://github.com/microsoft/onnxruntime/releases) for more details.
+* Python binaries are compatible with **Python 3.5-3.7**. See [Python Dev Notes](https://github.com/microsoft/onnxruntime/blob/master/docs/Python_Dev_Notes.md). If using `pip` to be download the Python binaries, run `pip install --upgrade pip` prior to downloading. 
 * Certain operators makes use of system locales. Installation of the **English language package** and configuring `en_US.UTF-8 locale` is required.
   * For Ubuntu install [language-pack-en package](https://packages.ubuntu.com/search?keywords=language-pack-en)
   * Run the following commands:
     `locale-gen en_US.UTF-8`
     `update-locale LANG=en_US.UTF-8`
   * Follow similar procedure to configure other locales on other platforms.
-  
+
 ## Building from Source
 If additional build flavors are needed, please find instructions on building from source at [Build ONNX Runtime](BUILD.md). For production scenarios, it's strongly recommended to build from an [official release branch](https://github.com/microsoft/onnxruntime/releases).
 
 Dockerfiles are available [here](https://github.com/microsoft/onnxruntime/tree/faxu-doc-updates/tools/ci_build/github/linux/docker) to help you get started.
 
+***
+# Usage
+
 ## Getting ONNX Models
 * The [ONNX Model Zoo](https://github.com/onnx/models) has popular ready-to-use pre-trained models.
 * To export or convert a trained ONNX model trained from various frameworks, see [ONNX Tutorials](https://github.com/onnx/tutorials). Versioning comptability information can be found under [Versioning](docs/Versioning.md#tool-compatibility)
@@ -115,8 +129,12 @@ ONNX Runtime can be deployed to the cloud for model inferencing using [Azure Mac
 
 **ONNX Runtime Server (beta)** is a hosted application for serving ONNX models using ONNX Runtime, providing a REST API for prediction. Usage details can be found [here](https://github.com/microsoft/onnxruntime/blob/master/docs/ONNX_Runtime_Server_Usage.md), and image installation instructions are [here](https://github.com/microsoft/onnxruntime/tree/master/dockerfiles#onnx-runtime-server-preview).
 
-## Examples and Tutorials
-### Python
+## Performance Tuning
+ONNX Runtime is open and extensible, supporting a broad set of configurations and execution providers for model acceleration. For performance tuning guidance, please see [this page](https://github.com/microsoft/onnxruntime/blob/master/docs/ONNX_Runtime_Perf_Tuning.md).
+
+***
+# Examples and Tutorials
+## Python
 * [Basic Inferencing Sample](https://github.com/onnx/onnx-docker/blob/master/onnx-ecosystem/inference_demos/simple_onnxruntime_inference.ipynb)
 * [Inferencing (Resnet50)](https://github.com/onnx/onnx-docker/blob/master/onnx-ecosystem/inference_demos/resnet50_modelzoo_onnxruntime_inference.ipynb)
 * [Inferencing samples](https://github.com/onnx/onnx-docker/tree/master/onnx-ecosystem/inference_demos) using [ONNX-Ecosystem Docker image](https://github.com/onnx/onnx-docker/tree/master/onnx-ecosystem)
@@ -127,21 +145,29 @@ ONNX Runtime can be deployed to the cloud for model inferencing using [Azure Mac
 
 
 **Deployment with AzureML**
-* Inferencing: [Inferencing Facial Expression Recognition](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-inference-facial-expression-recognition-deploy.ipynb), [Inferencing MNIST Handwritten Digits](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-inference-mnist-deploy.ipynb), [ Resnet50 Image Classification](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-modelzoo-aml-deploy-resnet50.ipynb), [TinyYolo](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-convert-aml-deploy-tinyyolo.ipynb)
-* [Train and Inference MNIST from Pytorch](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-train-pytorch-aml-deploy-mnist.ipynb)
-* [FER+ on Azure Kubernetes Service with TensorRT](https://github.com/microsoft/onnxruntime/blob/master/docs/python/notebooks/onnx-inference-byoc-gpu-cpu-aks.ipynb)
-
-
-### C#
+* Inferencing using [ONNX Model Zoo](https://github.com/onnx/models) models: 
+  * [Facial Expression Recognition](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-inference-facial-expression-recognition-deploy.ipynb) 
+  * [MNIST Handwritten Digits](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-inference-mnist-deploy.ipynb)
+  * [Resnet50 Image Classification](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-modelzoo-aml-deploy-resnet50.ipynb)
+* Convert existing model for Inferencing:
+  * [TinyYolo](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-convert-aml-deploy-tinyyolo.ipynb)
+* Train a model with PyTorch and Inferencing:
+  * [MNIST](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-train-pytorch-aml-deploy-mnist.ipynb)
+
+* Inferencing with TensorRT Execution Provider on GPU (AKS)
+  * [FER+](https://github.com/microsoft/onnxruntime/blob/master/docs/python/notebooks/onnx-inference-byoc-gpu-cpu-aks.ipynb)
+
+
+## C#
 * [Inferencing Tutorial](https://github.com/microsoft/onnxruntime/blob/master/docs/CSharp_API.md#getting-started)
 
 
-### C/C++
+## C/C++
 * [Basic Inferencing (SqueezeNet) - C](https://github.com/microsoft/onnxruntime/blob/master/csharp/test/Microsoft.ML.OnnxRuntime.EndToEndTests.Capi/C_Api_Sample.cpp)
 * [Basic Inferencing (SqueezeNet) - C++](https://github.com/microsoft/onnxruntime/blob/master/csharp/test/Microsoft.ML.OnnxRuntime.EndToEndTests.Capi/CXX_Api_Sample.cpp)
 * [Inferencing (MNIST) - C++](https://github.com/microsoft/onnxruntime/tree/master/samples/c_cxx/MNIST)
 
-
+***
 # Technical Design Details
 * [High level architectural design](docs/HighLevelDesign.md)
 * [Versioning](docs/Versioning.md)
@@ -153,6 +179,7 @@ ONNX Runtime can be deployed to the cloud for model inferencing using [Azure Mac
 transform](include/onnxruntime/core/optimizer/graph_transformer.h)
 * [Add a new rewrite rule](include/onnxruntime/core/optimizer/rewrite_rule.h)
 
+***
 # Contribute
 We welcome contributions! Please see the [contribution guidelines](CONTRIBUTING.md).
 
@@ -163,6 +190,6 @@ For any feedback or to report a bug, please file a [GitHub Issue](https://github
 This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
 For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)
 or contact [[email protected]](mailto:[email protected]) with any additional questions or comments.
-
+***
 # License
 [MIT License](LICENSE)

cgmanifest.json

@@ -49,7 +49,7 @@
          "component":{
             "type":"git",
             "git": {
-              "commitHash": "65b8e0f9979fbade16e3becbdfa69c0764946f72",
+              "commitHash": "7d90796473295ca3cdf976ed772215c5980ad3e0",
               "repositoryUrl": "https://github.com/onnx/onnx.git"
             }
          }

cmake/CMakeLists.txt

@@ -50,9 +50,10 @@ option(onnxruntime_USE_OPENVINO "Build with OpenVINO support" OFF)
 option(onnxruntime_USE_NSYNC "Build with NSYNC support. This option only takes effect on Linux" OFF)
 option(onnxruntime_USE_EIGEN_FOR_BLAS "Use eign for blas" ON)
 option(onnxruntime_USE_NNAPI "Build with DNNLibrary for Android NNAPI support" OFF)
-option(onnxruntime_USE_MLAS "Use optimized blas library for GEMM and 2D Convolution" ON)
 option(onnxruntime_USE_MKLDNN "Build with MKL-DNN support" OFF)
 option(onnxruntime_USE_MKLML "Build MKL-DNN with MKL-ML binary dependency" OFF)
+option(onnxruntime_USE_GEMMLOWP "Build with gemmlowp for quantized gemm" OFF)
+option(onnxruntime_USE_AUTOML "Build AutoML support" ON)
 option(onnxruntime_USE_NGRAPH "Build with nGraph support" OFF)
 option(onnxruntime_USE_OPENBLAS "Use openblas" OFF)
 option(onnxruntime_DEV_MODE "Enable developer warnings and treat most of them as error." OFF)
@@ -349,8 +350,13 @@ if (onnxruntime_USE_TVM)
   add_definitions(-DUSE_TVM)
 
   set(onnxruntime_tvm_libs onnxruntime_codegen_tvm)
-  list(APPEND onnxruntime_EXTERNAL_LIBRARIES tvm nnvm_compiler)
-
+  # needs to link with stdc++fs in Linux
+  if(UNIX)
+    if (NOT APPLE)
+      set(FS_STDLIB stdc++fs)
+    endif()
+  endif()
+  list(APPEND onnxruntime_EXTERNAL_LIBRARIES tvm nnvm_compiler ${FS_STDLIB})
   list(APPEND onnxruntime_EXTERNAL_DEPENDENCIES tvm nnvm_compiler)
 endif()
 
@@ -367,10 +373,6 @@ if (onnxruntime_RUN_ONNX_TESTS)
   add_definitions(-DORT_RUN_EXTERNAL_ONNX_TESTS)
 endif()
 
-if (onnxruntime_USE_MLAS)
-  add_definitions(-DUSE_MLAS)
-endif()
-
 #Adjust warning flags
 if (WIN32)
     add_definitions(-DPLATFORM_WINDOWS -DNOGDI -DNOMINMAX -D_USE_MATH_DEFINES)
@@ -476,6 +478,10 @@ if (onnxruntime_USE_MKLDNN OR onnxruntime_USE_MKLML)
   include(mkldnn)
 endif()
 
+if(onnxruntime_USE_GEMMLOWP)
+  add_definitions(-DUSE_GEMMLOWP=1)
+endif()
+
 if (onnxruntime_USE_MKLML)
   add_definitions(-DUSE_MKLML=1 -DUSE_MKLML_FOR_BLAS=1)
   if (WIN32 OR APPLE)
@@ -646,6 +652,12 @@ include(onnxruntime_optimizer.cmake)
 include(onnxruntime_session.cmake)
 include(onnxruntime_mlas.cmake)
 
+if(onnxruntime_USE_AUTOML)
+  add_definitions(-DMICROSOFT_AUTOML)
+  # Build shared featurizer library
+  include(onnxruntime_automl_featurizers.cmake)
+endif()
+
 if(WIN32)
   list(APPEND onnxruntime_EXTERNAL_LIBRARIES Shlwapi)
   list(APPEND onnxruntime_EXTERNAL_LIBRARIES debug Dbghelp)

cmake/external/mkldnn.cmake

@@ -11,6 +11,8 @@ if(WIN32)
   set(MKLDNN_SHARED_LIB mkldnn.dll)
   set(MKLDNN_IMPORT_LIB mkldnn.lib)
   if(onnxruntime_USE_MKLML)
+    # Windows-only updated MKLML binary which contains fix for thread cleanup hang.
+    set(MKLML_VERSION 2020.0.20190813)
     set(MKLML_SHARED_LIB mklml.dll)
     set(MKLML_IMPORT_LIB mklml.lib)
     set(IOMP5MD_SHARED_LIB libiomp5md.dll)
@@ -59,15 +61,15 @@ if (onnxruntime_USE_MKLDNN)
     set(MKLDNN_DLL_PATH ${MKLDNN_LIB_DIR}/${MKLDNN_SHARED_LIB})
   endif()
   set(MKLDNN_INCLUDE_DIR ${MKLDNN_INSTALL}/include)
-  set (MKLDNN_CMAKE_EXTRA_ARGS)
+  set(MKLDNN_CMAKE_EXTRA_ARGS)
+  set(MKLDNN_PATCH_COMMAND1 git apply ${CMAKE_SOURCE_DIR}/patches/mkldnn/mem-patch.cmake.patch)
+  # discard prior changes due to patching in mkldnn source to unblock incremental builds.
+  set(MKLDNN_PATCH_DISCARD_COMMAND cd ${MKLDNN_SOURCE} && git checkout -- .)
   if(NOT onnxruntime_BUILD_FOR_NATIVE_MACHINE)
     # pre-v1.0
     list(APPEND MKLDNN_CMAKE_EXTRA_ARGS "-DARCH_OPT_FLAGS=")
     # v1.0
     list(APPEND MKLDNN_CMAKE_EXTRA_ARGS "-DMKLDNN_ARCH_OPT_FLAGS=")
-    set(MKLDNN_PATCH_COMMAND1 git apply ${CMAKE_SOURCE_DIR}/patches/mkldnn/mem-patch.cmake.patch)
-    # discard prior changes due to patching in mkldnn source to unblock incremental builds.
-    set(MKLDNN_PATCH_DISCARD_COMMAND cd ${MKLDNN_SOURCE} && git checkout -- .)
   endif()
   ExternalProject_Add(project_mkldnn
     PREFIX mkl-dnn