Add refs to DLDT doc and remove PlaidML-related docs (#4334)

* Update sitemap to not use a page title

* Update doc for DLDT layers and remove references to PlaidML

doc/sphinx/source/backends/index.rst

@@ -23,10 +23,6 @@ from a framework on a CPU, GPU, or ASIC; it can also be used with an
 *Interpreter* mode, which is primarily intended for testing, to analyze a 
 program, or to help a framework developer customize targeted solutions. 
 
-nGraph also provides a way to use the advanced tensor compiler PlaidML 
-as a backend; you can learn more about this backend and how to build it 
-from source in our documentation: :ref:`ngraph_plaidml_backend`.
-
 .. csv-table::
    :header: "Backend", "Current nGraph support", "Future nGraph support"
    :widths: 35, 10, 10
@@ -104,26 +100,4 @@ depending on the parameters specified.
 * ``NGRAPH_INTELGPU_DUMP_FUNCTION`` -- dumps nGraph’s functions 
   in dot format.
 
-.. _opencl: 
-
-OpenCL
-------
-
-OpenCL is only needed for the :doc:`plaidml-ng-api/index`; if you have only 
-a CPU backend, it is not needed.
-
-#. Install the latest Linux driver for your system. You can find a list 
-   of drivers at https://software.intel.com/en-us/articles/opencl-drivers;
-   You may need to install `OpenCL SDK`_ in case of an ``libOpenCL.so`` absence.
-
-#. Any user added to "video" group:
-
-   .. code-block:: console
-
-      sudo usermod –a –G video <user_id>
-
-   may, for example, be able to find details at the ``/sys/module/[system]/parameters/`` 
-   location.
-
 .. _axpy.py example: https://github.com/tensorflow/ngraph-bridge/blob/master/examples/axpy.py
-.. _OpenCL SDK: https://software.intel.com/en-us/opencl-sdk

doc/sphinx/source/backends/plaidml-ng-api/index.rst

-.. backends/plaidml-ng-api/index.rst:
-
-
-PlaidML from nGraph
-===================
-
-.. doxygenclass:: ngraph::runtime::plaidml::PlaidML_Backend
-   :project: ngraph
-   :members:
-   
\ No newline at end of file

doc/sphinx/source/buildlb.rst

@@ -5,7 +5,6 @@ Build and Test
 ###############
 
 * :ref:`default_ngflags`
-* :ref:`ngraph_plaidml_backend`
 
 There are a few common paths to take when manually building the |project| 
 from source code. Today nGraph supports various developers working on all 
@@ -17,18 +16,6 @@ A "from scratch" source-code build of the nGraph Library enables the CPU,
 ``Interpreter``, and unit tests by default. See :ref:`default_ngflags` 
 for more detail.
 
-A "from scratch" source-code build that defaults to the PlaidML backend 
-contains rich algorithm libraries akin to those that were previously available 
-only to developers willing to spend extensive time writing, testing, and 
-customizing kernels. An ``NGRAPH_PLAIDML`` dist can function like a framework 
-that lets developers compose, train, and even deploy :abbr:`DL (Deep Learning)` 
-models in their preferred language on neural networks of any size. This is 
-a good option if, for example, you are working on a laptop with a high-end 
-GPU that you want to use for compute. See :ref:`ngraph_plaidml_backend` 
-for instructions on how to build.
-
-In either case, there are some prerequisites that your system will need 
-to build from sources.
 
 .. _prerequisites:
 
@@ -63,6 +50,11 @@ file to change or customize the default CMake procedure.
 * :ref:`ubuntu`
 * :ref:`centos`
 
+Other Compilation Flags
+-----------------------
+
+See :doc:`inspection/index`. 
+
 
 .. _ubuntu:
 
@@ -161,59 +153,6 @@ The process documented here will work on CentOS 7.4.
       $ make && sudo make install 
 
 
-.. _ngraph_plaidml_backend:
-
-Building nGraph-PlaidML from source
-===================================
-
-The following instructions will create the ``~/ngraph_plaidml_dist`` 
-locally:
-
-#. Ensure you have installed the :ref:`prerequisites` for your OS.
-
-#. Install the prerequisites for the backend. Our hybrid ``NGRAPH_PLAIDML``
-   backend works best with Python3 versions. We recommend that you use a 
-   virtual environment, due to some of the difficulties that users have 
-   seen when trying to install outside of a venv.
-
-   .. code-block:: console
-
-      $ sudo apt install python3-pip
-      $ pip install plaidml 
-      $ plaidml-setup
-
-#. Clone the source code, create and enter your build directory:
-
-   .. code-block:: console
-
-      $ git clone https://github.com/NervanaSystems/ngraph.git
-      $ cd ngraph && mkdir build && cd build
-
-#. Prepare the CMake files as follows: 
-
-   .. code-block:: console
-
-      $ cmake .. -DCMAKE_INSTALL_PREFIX=~/ngraph_plaidml_dist -DNGRAPH_CPU_ENABLE=OFF -DNGRAPH_PLAIDML_ENABLE=ON 
-
-#. Run :command:`make` and ``make install``. Note that if you are building 
-   outside a local or user path, you may need to run ``make install`` as the 
-   root user.
-
-   .. code-block:: console
-
-      $ make
-      $ make install
-
-   This should create the shared library ``libplaidml_backend.so`` and 
-   nbench. Note that if you built in a virtual environment and run 
-   ``make check`` from it, the Google Test may report failures. Full 
-   tests can be run when PlaidML devices are available at the machine 
-   level.
-
-For more about working with the PlaidML backend from nGraph, see our 
-API documentation :doc:`backends/plaidml-ng-api/index`. 
-
-
 macOS\* development
 --------------------
 

doc/sphinx/source/frameworks/quickstart.rst

@@ -68,22 +68,6 @@ Now you can start exploring some of the :doc:`onnx_integ` examples.
 
 See also nGraph's :doc:`../python_api/index`.
 
-PlaidML
--------
-
-See the :ref:`ngraph_plaidml_backend` section on how to build the 
-nGraph-PlaidML.
-
-
-Other integration paths
------------------------
-
-If you are considering incorporating components from the nGraph Compiler stack 
-in your framework or neural network design, another useful doc is the section 
-on :doc:`other/index` . Contents here are also useful if you are working on 
-something built-from-scratch, or on an existing framework that is less 
-widely-supported than the popular frameworks like TensorFlow and PyTorch.
-
 
 .. _ngraph-tensorflow-bridge: https://pypi.org/project/ngraph-tensorflow-bridge
 .. _ngraph ONNX: https://github.com/NervanaSystems/ngraph-onnx

doc/sphinx/source/introduction.rst

@@ -142,50 +142,19 @@ work for what will ultimately be a fragile setup that is costly to maintain.
    **Figure C**:  Inevitable scaling problem
 
 
-Integrating PlaidML with nGraph provides flexbility to support the latest deep
-learning models in the absence of hand-optimized kernels for new operations.
-PlaidML works together with nGraph to address the exponential growth of
-kernels.
-
-PlaidML takes two inputs: the operation defined by the user and the machine
-description of the hardware target. It then automatically generates kernels
-that are iteratively optimized through an IR known as `Stripe`_. Integration of
-PlaidML with nGraph allows users to choose the hardware and framework that
-suits their needs, resulting in freedom from kernel libraries. 
-
-
-Solution: nGraph and PlaidML
-============================
-
-We developed nGraph and integrated it with PlaidML to allow developers to
-accelerate deep learning performance and address the problem of scalable
-kernel libraries. To address the problem of scaling backends, nGraph applies 
-graph-level optimizations to deep learning computations and unifies 
-computational graphsfrom deep learning frameworks with nGraph IR.
-
-In conjunction with nGraph's graph-level optimizations, PlaidML automatically
-applies low-level optimizations to improve deep learning performance.
-Additionally, PlaidML offers extensive support for various hardware targets
-due to its ability to generate code in LLVM, OpenCL, OpenGL, and Metal.
-
-Given a backend with existing kernel libraries, nGraph can readily support the
-target hardware because the backend only needs to support a few primitive
-operations. If the hardware supports one of the coding languages supported by
-PlaidML, developers must specify the machine description to support the
-hardware. Together, nGraph and PlaidML provide the best of both worlds.
-
-This documentation provides technical details of nGraph's core functionality
-as well as framework and backend integrations. Creating a compiler stack like
-nGraph and PlaidML requires expert knowledge, and we're confident that nGraph
-and PlaidML will make life easier for many kinds of developers:
-
-#. Framework owners looking to support new hardware and custom chips.
-#. Data scientists and ML developers wishing to accelerate deep learning
-   performance.
-#. New DL accelerator developers creating an end-to-end software stack from a
-   deep learning framework to their silicon.
-
-.. _Stripe: https://arxiv.org/abs/1903.06498
-.. _publication: https://arxiv.org/abs/1801.08058
-.. _up to 45X: https://ai.intel.com/ngraph-compiler-stack-beta-release/
-.. _more transistors on denser and denser circuits: https://www.intel.com/content/www/us/en/silicon-innovations/moores-law-technology.html
+
+Solution: A customizable graph compiler for complex operations
+==============================================================
+
+`OpenVINO toolkit`_ is powered by nGraph capabilities for Graph compilation. 
+To represent a :abbr:`DL (Deep Learning)` model in real-time and perform 
+complex operations on that model, users can `build an nGraph function`_.
+
+Once created, it can wrap into a ``CNNNetwork``, creating utility for data 
+scientists or application developers to use operations that do not depend 
+on existing Deep Learning (DL) frameworks. 
+ 
+
+.. _OpenVINO toolkit: http://docs.openvinotoolkit.org/latest/_docs_IE_DG_Deep_Learning_Inference_Engine_DevGuide.html
+.. _build an nGraph function: http://docs.openvinotoolkit.org/latest/_docs_IE_DG_nGraphTutorial.html
+.. _add custom operations: http://docs.openvinotoolkit.org/latest/_docs_IE_DG_AddingNGraphOps.html
\ No newline at end of file

doc/sphinx/source/sitemap.rst

@@ -42,7 +42,6 @@
      :maxdepth: 1
 
      Basic Concepts <backends/index.rst>
-     backends/plaidml-ng-api/index.rst
      Integrating Other Backends <backends/cpp-api.rst>