Architecture and feature docs (#2092)

79878d71 · L.S. Cook · Michał Karzyński · 7b665771 · 79878d71 · 79878d71
Commit 79878d71 authored Nov 25, 2018 by L.S. Cook Committed by Michał Karzyński Nov 25, 2018
9 changed files
--- a/README.md
+++ b/README.md
-# nGraph Compiler Stack Beta
+# nGraph Compiler Stack
 [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/NervanaSystems/ngraph/blob/master/LICENSE) [![Build Status][build-status-badge]][build-status] 
 <div align="left">
-  <h3>
+  <h4>
-    <a href="https://ngraph.nervanasys.com/docs/latest/project/about.html">
+    <a href="./ABOUT.md">Architecture & features</a> | <a href="./ecosystem-overview.md" >Ecosystem</a> | <a href="https://ngraph.nervanasys.com/docs/latest/project/release-notes.html">Release notes</a><span> | </span> <a href="https://ngraph.nervanasys.com/docs/latest">Documentation</a><span> | </span> <a href="#How-to-contribute" >Contribution guide</a>
-      Architecture and features</a> | <a href="#Ecosystem" >nGraph ecosystem</a><span> </span> <span> | </span> 
+ </h4>
-    <a href="https://ngraph.nervanasys.com/docs/latest/project/release-notes.html">
-      Beta release notes</a><span> | </span> <br />
-    <a href="https://ngraph.nervanasys.com/docs/latest">Documentation</a><span> | </span>
-    <a href="#How-to-contribute" >How to contribute</a>
- </h3>
 </div>
 ## Quick start
@@ -19,14 +14,14 @@
 To begin using nGraph with popular frameworks to accelerate deep learning 
 workloads on CPU for inference, please refer to the links below. 
-|  Framework / Version       | Installation guide                     | Notes  
+|  Framework (Version)       | Installation guide                     | Notes  
 |----------------------------|----------------------------------------|-----------------------------------
 | TensorFlow* 1.12           | [Pip package] or [Build from source]   | 17 [Validated workloads]
 | MXNet* 1.4                 | [Enable the module] or [Source compile]| 17 [Validated workloads]   
-| ONNX 1.3                   | [Pip package]                          | 13 [Functional] workloads with DenseNet-121, Inception-v1, ResNet-50, Inception-v2, ShuffleNet, SqueezeNet, VGG-19, and 7 more   
+| ONNX 1.3                   | [Pip package]                          | 14 [Validated workloads] 
 Frameworks using nGraph Compiler stack to execute workloads have shown 
-**3X** to **45X** performance boost when compared to native framework 
+**up to 45X** performance boost when compared to native framework 
 implementations. We've also seen performance boosts running workloads that 
 are not included on the list of [Validated workloads], thanks to our 
 powerful subgraph pattern matching and thanks to the collaborative efforts 
@@ -47,23 +42,23 @@ We strongly believe in providing freedom, performance, and ease-of-use to AI
 developers. 
 The diagram below shows what deep learning frameworks and hardware targets
-we support. More details on these current and future plans are in the ecosystem
+we support. More details on these current and future plans are in the [ecosystem]
 section. 
-![nGraph ecosystem][ngraph-ecosystem]
+![nGraph wireframe][ngraph_wireframes_with_notice]
 While the ecosystem shown above is all functioning, we have validated 
-performance metrics for deep learning inference on CPU processors including 
+performance for deep learning inference on CPU processors such as Intel® Xeon®. 
-as Intel® Xeon®. Please refer to the [Beta release notes] to learn more. 
+Please refer to the [Release notes] to learn more. The Gold release 
-The Gold release is targeted for April 2019; it will feature broader workload 
+is targeted for April 2019; it will feature broader workload coverage, 
-coverage, including support for quantized graphs, and more detail on our 
+including quantized graphs, and more detail on our advanced support for 
-advanced support for ``int8``. 
+``int8``. 
 Our documentation has extensive information about how to use nGraph Compiler 
 stack to create an nGraph computational graph, integrate custom frameworks, 
-and interact with supported backends. If you wish to contribute to the 
+and to interact with supported backends. If you wish to contribute to the 
 project, please don't hesitate to ask questions in [GitHub issues] after 
 reviewing our contribution guide below. 
@@ -85,20 +80,8 @@ to improve it:
  modifications are necessary, may provide feedback to guide you. When
  accepted, your pull request will be merged to the repository.
-![nGraph Compiler Stack][ngraph-compiler-stack-readme]
-| Backend                                       | current support   | future support |
-|-----------------------------------------------|-------------------|----------------|
-| Intel® Architecture CPU                       | yes               | yes            |
-| Intel® Nervana™ Neural Network Processor (NNP)| yes               | yes            |
-| Intel [Movidius™ Myriad™ 2] VPUs              | coming soon       | yes            |
-| Intel® Architecture GPUs                      | via PlaidML       | yes            |
-| AMD* GPUs                                     | via PlaidML       | yes            |
-| NVIDIA* GPUs                                  | via PlaidML       | some           | 
-| Field Programmable Gate Arrays (FPGA)         | no                | yes            |
+[Ecosystem]: ecosystem-overview
 [Architecture and features]:https://ngraph.nervanasys.com/docs/latest/project/about.html
 [Documentation]: https://ngraph.nervanasys.com/docs/latest
 [build the Library]: https://ngraph.nervanasys.com/docs/latest/buildlb.html
@@ -112,7 +95,7 @@ to improve it:
 [contrib guide]: https://ngraph.nervanasys.com/docs/latest/project/code-contributor-README.html
 [pull request]: https://github.com/NervanaSystems/ngraph/pulls
 [how to import]: https://ngraph.nervanasys.com/docs/latest/howto/import.html
-[ngraph-ecosystem]: doc/sphinx/source/graphics/599px-Intel-ngraph-ecosystem.png "nGraph Ecosystem"
+[ngraph_wireframes_with_notice]: doc/sphinx/source/graphics/ngraph_wireframes_with_notice.png "nGraph wireframe"
 [ngraph-compiler-stack-readme]: doc/sphinx/source/graphics/ngraph-compiler-stack-readme.png "nGraph Compiler Stack"
 [build-status]: https://travis-ci.org/NervanaSystems/ngraph/branches
 [build-status-badge]: https://travis-ci.org/NervanaSystems/ngraph.svg?branch=master
@@ -121,6 +104,7 @@ to improve it:
 [PlaidML]: https://github.com/plaidml/plaidml
 [Pip package]: https://github.com/NervanaSystems/ngraph-onnx#installing-ngraph-onnx
 [Build from source]: https://github.com/NervanaSystems/ngraph-tf
+[Enable the module]: https://github.com/NervanaSystems/ngraph/blob/mbrookhart/mxnet_tutorial/doc/sphinx/source/shared/mxnet_tutorial.rst
 [Source compile]: https://github.com/NervanaSystems/ngraph-mxnet/blob/master/NGRAPH_README.md
 [nGraph-ONNX]: https://github.com/NervanaSystems/ngraph-onnx/blob/master/README.md
 [nGraph-ONNX adaptable]: https://ai.intel.com/adaptable-deep-learning-solutions-with-ngraph-compiler-and-onnx/

--- a/doc/sphinx/cmake_install.cmake
+++ b/doc/sphinx/cmake_install.cmake
+# Install script for directory: /opt/libraries/ngraph/doc/sphinx
+# Set the install prefix
+if(NOT DEFINED CMAKE_INSTALL_PREFIX)
+  set(CMAKE_INSTALL_PREFIX "/usr/local")
+endif()
+string(REGEX REPLACE "/$" "" CMAKE_INSTALL_PREFIX "${CMAKE_INSTALL_PREFIX}")
+# Set the install configuration name.
+if(NOT DEFINED CMAKE_INSTALL_CONFIG_NAME)
+  if(BUILD_TYPE)
+    string(REGEX REPLACE "^[^A-Za-z0-9_]+" ""
+           CMAKE_INSTALL_CONFIG_NAME "${BUILD_TYPE}")
+  else()
+    set(CMAKE_INSTALL_CONFIG_NAME "")
+  endif()
+  message(STATUS "Install configuration: \"${CMAKE_INSTALL_CONFIG_NAME}\"")
+endif()
+# Set the component getting installed.
+if(NOT CMAKE_INSTALL_COMPONENT)
+  if(COMPONENT)
+    message(STATUS "Install component: \"${COMPONENT}\"")
+    set(CMAKE_INSTALL_COMPONENT "${COMPONENT}")
+  else()
+    set(CMAKE_INSTALL_COMPONENT)
+  endif()
+endif()
+# Install shared libraries without execute permission?
+if(NOT DEFINED CMAKE_INSTALL_SO_NO_EXE)
+  set(CMAKE_INSTALL_SO_NO_EXE "1")
+endif()
+# Is this installation the result of a crosscompile?
+if(NOT DEFINED CMAKE_CROSSCOMPILING)
+  set(CMAKE_CROSSCOMPILING "FALSE")
+endif()
+if(CMAKE_INSTALL_COMPONENT)
+  set(CMAKE_INSTALL_MANIFEST "install_manifest_${CMAKE_INSTALL_COMPONENT}.txt")
+else()
+  set(CMAKE_INSTALL_MANIFEST "install_manifest.txt")
+endif()
+string(REPLACE ";" "\n" CMAKE_INSTALL_MANIFEST_CONTENT
+       "${CMAKE_INSTALL_MANIFEST_FILES}")
+file(WRITE "/opt/libraries/ngraph/doc/sphinx/${CMAKE_INSTALL_MANIFEST}"
+     "${CMAKE_INSTALL_MANIFEST_CONTENT}")
--- a/doc/sphinx/source/distr/index.rst
+++ b/doc/sphinx/source/distr/index.rst
@@ -49,9 +49,9 @@ across all workers with an op that performs "allreduce", and applied to update
 the weights.
 Using multiple machines helps to scale and speed up deep learning. With large 
-mini-batch training, `one could train ResNet-50 with Imagenet-1k data`_ to the 
+mini-batch training, one could train ResNet-50 with Imagenet-1k data to the 
-*Top 5* classifier in minutes using thousands of CPU nodes. See also: 
+*Top 5* classifier in minutes using thousands of CPU nodes. See 
-`arxiv.org/pdf/1709.05011.pdf`_. 
+`arxiv.org/abs/1709.05011`_. 
@@ -96,7 +96,6 @@ communication collective ops such as allgather, scatter, gather, etc. in
 the future. 
-.. _based on the synchronous: https://arxiv.org/pdf/1602.06709.pdf 
+.. _arxiv.org/abs/1709.05011: https://arxiv.org/format/1709.05011
-.. _one could train ResNet-50 with Imagenet-1k data: https://blog.surf.nl/en/imagenet-1k-training-on-intel-xeon-phi-in-less-than-40-minutes/
+.. _based on the synchronous: https://arxiv.org/format/1602.06709 
-.. _arxiv.org/pdf/1709.05011.pdf: https://arxiv.org/pdf/1709.05011.pdf
 .. _Intel MLSL: https://github.com/intel/MLSL/releases
\ No newline at end of file
--- a/doc/sphinx/source/frameworks/validation-testing.rst
+++ b/doc/sphinx/source/frameworks/validation-testing.rst
@@ -4,96 +4,99 @@
 Validation and testing
 ######################
-* **Validating** -- To provide optimizations with nGraph, we first 
+We validated performance for the following TensorFlow* and MXNet* workloads:
-  confirm that a given workload is "validated" as being functional; 
-  that is, we can successfully load its serialized graph as an nGraph 
-  :term:`function graph`. Following here is a list of 14 workloads 
-  we've tested with success.
+TensorFlow 
+==========
 .. csv-table::
-   :header: "Workload", "Validated"
+   :header: "TensorFlow Workloads", "Type"
   :widths: 27, 53
   :escape: ~
-   DenseNet-121, Functional
+   Resnet50 v1 and v2, Image recognition
-   Inception-v1, Functional
+   Inception V3 and V4, Image recognition
-   Inception-v2, Functional
+   Inception-ResNetv2, Image recognition
-   ResNet-50, Functional
+   MobileNet v1, Image recognition
-   Shufflenet, Functional
+   SqueezeNet v1.1, Image recognition
-   SqueezeNet, Functional
+   DenseNet-121, Image recognition
-   VGG-19, Functional
+   SSD-VGG16, Object detection
-   ZFNet-512, Functional
+   SSD-MobileNetv1, Object detection
-   MNIST, Functional
+   Faster RCNN, Object detection
-   Emotion-FERPlus, Functional
+   Yolo v2, Object detection
-   BVLC AlexNet, Functional
+   Wide & Deep, Recommender system
-   BVLC GoogleNet, Functional
+   NCF, Recommender system
-   BVLC CaffeNet, Functional
+   WaveNet, Speech generation
-   BVLC R-CNN ILSVRC13, Functional 
+   U-Net, Image segmentation
+   DCGAN, Generative adversarial network
+   DRAW, Image generation
+   A3C, Reinforcement learning
+MXNet
+=====
+.. csv-table::
+   :header: "MXNet Workloads", "Type"
+   :widths: 27, 53
+   :escape: ~
-* **Testing & Performance Optimizations** for workloads that have been 
+   Resnet50 v1 and v2, Image recognition
-  "validated" with nGraph are also available via the nGraph 
+   DenseNet (121, 161, 169, 201), Image recognition
-  :abbr:`Intermediate Representation (IR)`). For example, a common use 
+   InceptionV3, Image recognition
-  case for data scientists is to train a new model with a large dataset, 
+   InceptionV4, Image recognition
-  and so nGraph already has several accelerations available "out of the 
+   Inception-ResNetv2, Image recognition
-  box" for the workloads noted below.
+   MobileNet v1, Image recognition
+   SqueezeNet v1 and v1.1, Image recognition
+   VGG16, Image recognition
+   Faster RCNN, Object detection
+   SSD-VGG16, Object detection
+   GNMT, Language translation
+   Transformer-LT, Language translation
+   Wide & Deep, Recommender system
+   WaveNet, Speech generation
+   DeepSpeech2, Speech recognition
+   DCGAN, Generative adversarial network
+   A3C, Reinforcement learning
+ONNX
+=====
+Additionally, we validated the following workloads are functional through nGraph ONNX importer: 
-TensorFlow 
-==========
 .. csv-table::
-   :header: "TensorFlow Workloads", "Performance"
+   :header: "Workload", "Type"
   :widths: 27, 53
   :escape: ~
-   Resnet50 v1 and v2, 50% of P40
+   DenseNet-121, Image recognition
-   Inception V3 and V4, 50% of P40
+   Inception-v1, Image recognition
-   Inception-ResNetv2, 50% of P40
+   Inception-v2, Image recognition
-   MobileNet v1, 50% of P40
+   ResNet-50, Image recognition
-   SqueezeNet v1.1, 50% of P40
+   Shufflenet, Image recognition
-   SSD-VGG16, 50% of P40
+   SqueezeNet, Image recognition
-   R-FCN, 50% of P40
+   VGG-19, Image recognition
-   Faster RCNN, 50% of P40
+   ZFNet-512, Image recognition
-   Yolo v2, 50% of P40
+   MNIST, Image recognition
-   GNMT, Greater than or equal to :abbr:`Direct Optimization (DO)`
+   Emotion-FERPlus, Image recognition
-   Transformer-LT, 50% of P40
+   BVLC AlexNet, Image recognition
-   Wide & Deep, 50% of P40
+   BVLC GoogleNet, Image recognition
-   WaveNet, Functional
+   BVLC CaffeNet, Image recognition
-   U-Net, Greater than DO
+   BVLC R-CNN ILSVRC13, Object detection 
-   DRAW, 50% of P40
-   A3C, 50% of P40
-MXNet
-=====
-.. csv-table::
-   :header: "MXNet Workloads", "Performance"
-   :widths: 27, 53
-   :escape: ~
-   Resnet50 v1 and v2, 50% of P40
+.. important:: Please see Intel's `Optimization Notice`_ for details on disclaimers. 
-   DenseNet (121 161 169 201), 50% of P40
-   InceptionV3, 50% of P40
-   InceptionV4, 50% of P40
-   Inception-ResNetv2, 50% of P40
+.. _Optimization Notice: https://software.intel.com/en-us/articles/optimization-notice
-   MobileNet v1, 50% of P40
-   SqueezeNet v1 and v1.1, 50% of P40
-   VGG16, Functional (No DO available)
-   Faster RCNN, 50% of P40
-   SSD-VGG16, 50% of P40
-   GNMT, Greater than or equal to :abbr:`Direct Optimization (DO)`
-   Transformer-LT, 50% of P40
-   Wide & Deep, 50% of P40
-   WaveNet, Functional
-   DeepSpeech2, 50% of P40
-   DCGAN, 50% of P40
-   A3C, Greater than or equal to DO
+.. Notice revision #20110804: Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

--- a/doc/sphinx/source/glossary.rst
+++ b/doc/sphinx/source/glossary.rst
@@ -175,5 +175,15 @@ Glossary
   SGD
      :abbr:`Stochastic Gradient Descent (SGD)`, also known as incremental 
-      gradient descent, is an iterative method for optimizing a differentiable 
+      gradient descent, is an iterative method for optimizing a 
-      objective function.
+      differentiable objective function.
\ No newline at end of file
+   validated
+      To provide optimizations with nGraph, we first confirm that a given 
+      workload is "validated" as being functional; that is, we can
+      successfully load its serialized graph as an nGraph :term:`function 
+      graph`
--- a/doc/sphinx/source/graphics/ngraph_wireframes_with_notice.png
+++ b/doc/sphinx/source/graphics/ngraph_wireframes_with_notice.png
--- a/doc/sphinx/source/graphics/ngraph_wireframes_with_notice.xcf
+++ b/doc/sphinx/source/graphics/ngraph_wireframes_with_notice.xcf
--- a/doc/sphinx/source/project/about.rst
+++ b/doc/sphinx/source/project/about.rst
@@ -16,27 +16,27 @@ nGraph Compiler stack architecture
 ==================================
-The diagram below represents our current Beta release stack. Please note that
+The diagram below represents our current |release| release stack. Please 
-the stack diagram is simplified to show how nGraph executes deep learning 
+note that the stack diagram is simplified to show how nGraph executes deep 
-workloads with two hardware backends; however, many other deep learning 
+learning workloads with two hardware backends; however, many other deep 
-frameworks and backends currently are functioning. 
+learning frameworks and backends currently are functioning. 
 .. figure:: ../graphics/stackngrknl.png
-    :width: 771px
+    :width: 455px
    :alt: Current Beta release stack
    Simplified stack diagram for nGraph Compiler and components Beta 
-Starting from the top of the diagram, we present a simplified view of how 
+Starting from the top of the diagram, we present a simplified view of the nGraph 
-the nGraph :abbr:`Intermediate Representation (IR)` can receive a graph from a
+Intermediate Representation (IR). The nGraph IR is a format which works with a 
-framework such as TensorFlow\* or MXNet\* when there is a corresponding 
+framework such as TensorFlow* or MXNet* when there is a corresponding "Bridge"
-"Bridge" or import method, such as from NNVM or via `ONNX`_. Once the nGraph 
+or import method, such as from NNVM or via `ONNX`_. Once the nGraph IR can begin 
-:doc:`../ops/index` can begin parsing the graph as a computation graph, they
+using nGraph's Core ops, components lower in the stack can begin parsing and 
-can pattern-match subgraphs for device-specific optimizations; these are then 
+pattern-matching subgraphs for device-specific optimizations; these are then 
 encapsulated. This encapsulation is represented on the diagram as the colored 
 background between the ``ngraph`` kernel(s) and the the stack above.
-Note that everything at or below the "Kernel APIs" and "Subgraph APIs" gets 
+Note that everything at or below the **Kernel APIs** and **Subgraph APIs** gets 
 executed "automatically" during training runs. In other words, the accelerations 
 are automatic: parts of the graph that are not encapsulated default to framework 
 implementation when executed. For example, if nGraph optimizes ResNet50 for 
@@ -89,7 +89,7 @@ Features
 The nGraph :abbr:`(IR) Intermediate Representation` contains a combination of 
 device-specific and non-device-specific optimization :
-* **Fusion** -- Fuse multiple ops to to decrease memory usage "localities".
+* **Fusion** -- Fuse multiple ops to to decrease memory usage.
 * **Data layout abstraction** -- Make abstraction easier and faster with nGraph 
  translating element order to work best for a given or available device.
 * **Data reuse** -- Save results and reuse for subgraphs with the same input.
@@ -110,7 +110,6 @@ device-specific and non-device-specific optimization :
   added with new functions that build sub-graphs from existing core ops.   
 .. _portable:
 Portable

--- a/ecosystem-overview.md
+++ b/ecosystem-overview.md
+# Framework & runtime support
+One of nGraph’s key features is framework neutrality. We currently support 
+popular deep learning frameworks such as TensorFlow and MXNet with stable 
+bridges to pass computational graphs to nGraph. Additionally nGraph 
+Compiler has functional bridges to PaddlePaddle and PyTorch (via [ONNXIFI]). 
+For these frameworks, we have successfully tested functionality with a few 
+deep learning workloads, and we plan to bring stable support for them in the 
+upcoming releases. 
+To further promote framework neutrality, the nGraph team has been actively 
+contributing to the ONNX project. Developers who already have a "trained" 
+DNN (Deep Neural Network) model can use nGraph to bypass significant 
+framework-based complexity and [import it] to test or run on targeted and 
+efficient backends with our user-friendly Python-based API.
+nGraph is also integrated as an computation provider for [ONNX Runtime], 
+which is a runtime for [WinML] on Windows OS and Azure to accelerate DL 
+workloads. 
+The table below summarizes our current progress on supported frameworks. 
+If you are an architect of a framework wishing to take advantage of speed 
+and multi-device support of nGraph Compiler, please refer to [Framework integration guide] section.  
+|  Framework & Runtime       | Supported          |  Validated 
+|----------------------------|--------------------|-------------
+| TensorFlow* 1.12           | :heavy_check_mark: |  :heavy_check_mark:
+| MXNet* 1.4                 | :heavy_check_mark: |  :heavy_check_mark:
+| ONNX 1.3                   | :heavy_check_mark: |  :heavy_check_mark:
+| ONNX Runtime  Functional   | Functional         |  No
+| PyTorch (via ONNXIFI)      | Functional         |  No
+| PaddlePaddle               | Functional         |  No
+## Hardware & backend support
+The current release of nGraph primarily focuses on accelerating inference 
+performance on CPU. However we are also working on adding support for more 
+hardware and backends. As with the frameworks, we believe in providing 
+freedom to AI developers to deploy their deep learning workloads to the 
+desired hardware without a lock in. We currently have functioning backends 
+for Intel, Nvidia*, and AMD* GPU either leveraging kernel libraries 
+such as clDNN and cuDNN directly or utilizing PlaidML to compile for codegen 
+and emit OpenCL, OpenGL, LLVM, Cuda, and Metal. Please refer to [Architecture 
+and features] section to learn more about how we plan to take advantage of 
+both solutions using hybrid transformer. We expect to have stable support for aformentioned GPUs
+in the early second half of 2019. In the similar time frame, we plan 
+to release multinode support. 
+Additionally, we are excited about providing support for our upcoming deep learning 
+accelerators such as NNP (Neural Network Processor) via nGraph compiler 
+stack, and early adopters will be able test them in 2019.
+| Backend                                       | supported         
+|-----------------------------------------------|-------------------
+| Intel® Architecture CPU                       | :heavy_check_mark:               
+| Intel® Architecture GPUs                      | Functional via clDNN and PlaidML      
+| AMD* GPUs                                     | Functional via PlaidML                 
+| Nvidia* GPUs                                  | Functional via cuDNN and PlaidML        
+| Intel® Nervana™ Neural Network Processor (NNP)| Functional               
+| Upcoming DL accelerators                      | Functional and will be announced in the near future       
+[Architecture and features]: ./ABOUT.md
+[Upcoming DL accelerators]: https://www.intel.com/content/dam/www/public/us/en/documents/product-briefs/vision-accelerator-design-product-brief.pdf
+[import it]: http://ngraph.nervanasys.com/docs/latest/howto/import.html
+[ONNXIFI]: https://github.com/onnx/onnx/blob/master/docs/ONNXIFI.md
+[ONNX Runtime]:https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-build-deploy-onnx
+[WinML]: http://docs.microsoft.com/en-us/windows/ai
+[How to]: https://ngraph.nervanasys.com/docs/latest/howto/index.html
+[Framework integration guide]: https://ngraph.nervanasys.com/docs/latest/frameworks/index.html