===================
Anaconda Accelerate
===================

:emphasis:`High Performance Computing`

.. note::  This product is discontinued. This archived copy of the product documentation is provided for those customers who are still using it. SEE https://www.anaconda.com/blog/developer-blog/open-sourcing-anaconda-accelerate/

Anaconda Accelerate is a package that provides the Anaconda® platform access to several numerical libraries that are optimized for performance on Intel CPUs and NVidia GPUs.

The current version, 2.3.1, was released on January 30, 2017.

Anyone can now use the functionality from Accelerate without purchasing a license!

On July 27, 2017, Accelerate was split into the `Intel Distribution for Python <https://software.intel.com/en-us/articles/using-intel-distribution-for-python-with-anaconda>`_ and the open source `Numba <https://numba.pydata.org/>`_ project's sub-projects `pyculib <https://github.com/numba/pyculib>`_, `pyculib_sorting <https://github.com/numba/pyculib_sorting>`_ and `data_profiler <https://github.com/numba/data_profiler>`_. Numba and all its sub-projects are available under a BSD license.

More information is available in the post `Open Sourcing Anaconda Accelerate <https://www.anaconda.com/blog/developer-blog/open-sourcing-anaconda-accelerate>`_.

Features
========

* Bindings to the following :doc:`cuda-libs`: 
	* :doc:`cublas`
	* :doc:`cufft`
	* :doc:`cusparse`
	* :doc:`curand`
	* :doc:`sorting` algorithms from the CUB and Modern GPU libraries
* Speed-boosted linear algebra operations in NumPy, SciPy, scikit-learn and NumExpr libraries using Intel's Math Kernel Library (:doc:`MKL <mkl-overview>`).
* Accelerated variants of Numpy's built-in :doc:`UFuncs <mkl-ufuncs>`.
* Increased-speed Fast Fourier Transformations (:doc:`FFT <mkl-fft>`) in NumPy.

Installation
============

This section contains information related to:

.. toctree::
    :maxdepth: 1

    install
    

User guide
==========

This section contains information related to:

.. toctree::
    :maxdepth: 1

    cuda-libs
    mkl-overview
    profiling
    env-variables

License agreement
=================

.. toctree::
   :maxdepth: 1

   eula

Release notes
=============

.. toctree::
   :maxdepth: 1

   release-notes

Previous versions
=================

The following documentation is provided for users who have not yet upgraded to the current version:

.. toctree::
   :maxdepth: 1

   Accelerate 2.2 <2.2/index>
   Accelerate 2.1 <2.1/index>
   Accelerate 2.0 <2.0/index>
