Add IntelGPU APIs

doc/sphinx/source/backends/backend-api/index.rst

@@ -4,68 +4,29 @@
 Backend
 =======
 
-:ref:`more_resources`
+* :ref:`generic_backend`
+* :ref:`intelgpu_backend`
 
-.. doxygenclass:: ngraph::runtime::Backend
-   :project: ngraph
-   :members:
-
-
-
-.. _more_resources: 
-
-Additional resources
-====================
-
-OpenCL
-------
-
-#. Install the latest Linux driver for your system from 
-   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>
+.. _generic_backend:
 
-   may, for example, be able to find details at the
-   ``/sys/module/[system]/parameters/`` location. 
+Generic backend
+---------------
 
+.. doxygenclass:: ngraph::runtime::Backend
+   :project: ngraph
+   :members:
 
 
-nGraph Bridge 
-~~~~~~~~~~~~~
-
-When specified as the generic backend -- either 
-manually or automatically from a framework --  
-``NGRAPH`` defaults to CPU, and it also allows 
-for additional device configuration or selection. 
-
-Because nGraph can select backends, you may try 
-specifying the ``INTELGPU`` backend as a runtime 
-environment variable: 
-
-:envvar:`NGRAPH_TF_BACKEND="INTELGPU"`
-
-An `axpy.py example`_ is optionally available to test;
-outputs will vary depending on the parameters
-specified. 
-
-.. code-block:: console
 
-   NGRAPH_TF_BACKEND="INTELGPU" python3 axpy.py
+.. _intelgpu_backend:
 
-* ``NGRAPH_INTELGPU_DUMP_FUNCTION`` -- dumps 
-  nGraph’s functions in dot format.
+IntelGPU
+--------
 
-* `` `` --.
+.. doxygenclass:: ngraph::runtime::intelgpu::IntelGPUBackend
+   :project: ngraph
+   :members:
 
-* `` `` --.
 
-* `` `` --.
 
-.. _axpy.py example: https://github.com/tensorflow/ngraph-bridge/blob/master/examples/axpy.py
-.. _OpenCL SDK: https://software.intel.com/en-us/opencl-sdk
\ No newline at end of file

doc/sphinx/source/backends/cpp-api.rst

@@ -7,9 +7,10 @@ Backend APIs
    :maxdepth: 1
    
    backend-api/index
-   executable-api/index
    dynamicbackend-api/index
    plaidml-ng-api/index
+   executable-api/index
+   
 
 As of version ``0.15``, there is a new backend API to work with functions that 
 can be compiled as a runtime ``Executable``. Where previously ``Backend`` used a 

doc/sphinx/source/backends/executable-api/index.rst

@@ -4,11 +4,29 @@
 Executable
 ==========
 
+* :ref:`generic_executable`
+* :ref:`intelgpu_executable`
+
+
 The ``compile`` function on an ``Executable`` has more direct methods to 
 actions such as ``validate``, ``call``, ``get_performance_data``, and so on. 
 
 
+.. _generic_executable:
+
+Generic executable
+------------------
+
 .. doxygenclass:: ngraph::runtime::Executable
    :project: ngraph
    :members: 
 
+
+.. _intelgpu_executable:
+
+IntelGPU executable
+-------------------
+
+.. doxygenclass:: ngraph::runtime::intelgpu::IntelGPUExecutable
+   :project: ngraph
+   :members: 

doc/sphinx/source/backends/index.rst

@@ -6,6 +6,7 @@ Developer Resources for Backends
 
 * :ref:`what_is_backend`
 * :ref:`how_to_use`
+* :ref:`miscellaneous_resources`
 
 
 .. _what_is_backend:
@@ -60,3 +61,58 @@ interface; each backend implements the following five functions:
   for later execution.
 * And, finally, the ``call()`` method is used to invoke an nGraph function 
   against a particular set of tensors.
+
+
+.. _miscellaneous_resources: 
+
+Miscellaneous resources
+=======================
+
+Additional resources for device or framework-specific configurations:
+
+OpenCL
+------
+
+#. 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. 
+
+
+nGraph Bridge from TensorFlow*\ 
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+When specified as the generic backend -- either manually or automatically 
+from a framework --  ``NGRAPH`` defaults to CPU, and it also allows for 
+additional device configuration or selection. 
+
+Because nGraph can select backends, you may try specifying the ``INTELGPU`` 
+backend as a runtime environment variable: 
+
+:envvar:`NGRAPH_TF_BACKEND="INTELGPU"`
+
+An `axpy.py example`_ is optionally available to test; outputs will vary 
+depending on the parameters specified. 
+
+.. code-block:: console
+
+   NGRAPH_TF_BACKEND="INTELGPU" python3 axpy.py
+
+* ``NGRAPH_INTELGPU_DUMP_FUNCTION`` -- dumps 
+  nGraph’s functions in dot format.
+
+* `` `` --.
+
+* `` `` --.
+
+* `` `` --.
+
+.. _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/frameworks/mxnet_integ.rst

 .. frameworks/mxnet_integ.rst:
 
 MXNet\* bridge
-===============
+==============
+
+.. deprecated:: 0.21.0
+
 
 * See the nGraph-MXNet `Integration Guide`_ on the nGraph-MXNet repo.
 

doc/sphinx/source/project/release-notes.rst

@@ -23,8 +23,8 @@ Core updates for |version|
 0.22-doc
 --------
 
-+ Initial doc on iGPU. 
-+ Improve Backend APIs with new DynamicBackend API.
++ Initial doc and API for IntelGPU backend. 
++ DynamicBackend API.
 + Note deprecation of support of MXNet's ``ngraph-mxnet`` PyPI.
 + Noted changes on graph inspection options resultant from PR 3016.
 + Added better tips and details to doc-contributor-README.