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

.. raw:: html

    <p><cite>Accelerate</cite> provides access to numerical libraries optimized for performance on
    Intel CPUs and NVidia GPUs.</p>
    <div class="section" id="features">
    <h2>Features<a class="headerlink" href="#features" title="Permalink to this headline">¶</a></h2>
    <ul class="simple">
    <li>Bindings to CUDA libraries: cuBLAS, cuFFT, cuSPARSE, cuRAND, and sorting
    algorithms from the CUB and Modern GPU libraries</li>
    <li>Speed-boosted linear algebra operations in NumPy, SciPy, scikit-learn and
    NumExpr libraries using Intel&#8217;s Math Kernel Library (MKL).</li>
    <li>Accelerated variants of Numpy&#8217;s built-in UFuncs.</li>
    <li>Increased-speed Fast Fourier Transformations (FFT) in NumPy.</li>
    </ul>
    </div>
    <div class="section" id="requirements">
    <h2>Requirements<a class="headerlink" href="#requirements" title="Permalink to this headline">¶</a></h2>
    <ul>
    <li><p class="first">64-bit operating system: Linux, OS X or Windows</p>
    </li>
    <li><dl class="first docutils">
    <dt>Supported Python and Numpy combinations:</dt>
    <dd><ul class="first last simple">
    <li>Python 2.7 with Numpy 1.9 or 1.10</li>
    <li>Python 3.4 with Numpy 1.9 or 1.10</li>
    <li>Python 3.5 with Numpy 1.9 or 1.10</li>
    </ul>
    </dd>
    </dl>
    </li>
    <li><p class="first">Numba 0.25</p>
    </li>
    </ul>
    <p>For the CUDA features:</p>
    <ul class="simple">
    <li>NVidia driver version 349.00 or later</li>
    <li>CUDA toolkit 7.0</li>
    <li>At least one CUDA GPU with compute capability 2.0 or above</li>
    </ul>
    </div>
    <div class="section" id="installation">
    <h2>Installation<a class="headerlink" href="#installation" title="Permalink to this headline">¶</a></h2>
    <p>Accelerate is included with <a class="reference external" href="https://www.continuum.io/content/anaconda-subscriptions">Anaconda Workgroup and Anaconda Enterprise
    subscriptions</a>.</p>
    <p>To start a 30-day free trial just download and install the Anaconda Accelerate
    package.</p>
    <p>If you already have <a class="reference external" href="http://continuum.io/downloads.html">Anaconda</a> (free
    Python distribution) installed:</p>
    <div class="highlight-python"><div class="highlight"><pre><span></span>conda update conda
    conda install accelerate
    </pre></div>
    </div>
    <p>If you do not have Anaconda installed, you can download it <a class="reference external" href="http://continuum.io/downloads.html">here</a>.</p>
    <p>Anaconda Accelerate can also be installed into your own (non-Anaconda) Python
    environment. For more information about Accelerate please contact
    <a class="reference external" href="mailto:sales&#37;&#52;&#48;continuum&#46;io">sales<span>&#64;</span>continuum<span>&#46;</span>io</a>.</p>
    </div>
    <div class="section" id="update-instructions">
    <h2>Update Instructions<a class="headerlink" href="#update-instructions" title="Permalink to this headline">¶</a></h2>
    <p>If you have Anaconda (free Python distribution) installed:</p>
    <div class="highlight-python"><div class="highlight"><pre><span></span>conda update conda
    conda update accelerate
    </pre></div>
    </div>
    <p>If you already have NumbaPro installed, you must manually upgrade NumbaPro to
    install the NumbaPro compatibility layer:</p>
    <div class="highlight-python"><div class="highlight"><pre><span></span>conda update conda
    conda update numbapro
    </pre></div>
    </div>
    </div>
    <div class="section" id="contents">
    <h2>Contents<a class="headerlink" href="#contents" title="Permalink to this headline">¶</a></h2>
    <div class="toctree-wrapper compound">
    <ul>
    <li class="toctree-l1"><a class="reference internal" href="releasenotes.html">Release Notes</a><ul>
    <li class="toctree-l2"><a class="reference internal" href="releasenotes.html#version-2-2-0">Version 2.2.0</a></li>
    <li class="toctree-l2"><a class="reference internal" href="releasenotes.html#version-2-1-0">Version 2.1.0</a></li>
    <li class="toctree-l2"><a class="reference internal" href="releasenotes.html#version-2-0-2">Version 2.0.2</a></li>
    <li class="toctree-l2"><a class="reference internal" href="releasenotes.html#version-2-0-1">Version 2.0.1</a></li>
    <li class="toctree-l2"><a class="reference internal" href="releasenotes.html#version-2-0">Version 2.0</a><ul>
    <li class="toctree-l3"><a class="reference internal" href="releasenotes.html#cuda-libraries">CUDA Libraries</a></li>
    <li class="toctree-l3"><a class="reference internal" href="releasenotes.html#code-generation">Code Generation</a></li>
    <li class="toctree-l3"><a class="reference internal" href="releasenotes.html#intel-mkl">Intel MKL</a></li>
    </ul>
    </li>
    </ul>
    </li>
    <li class="toctree-l1"><a class="reference internal" href="cudalibs.html">CUDA Libraries</a><ul>
    <li class="toctree-l2"><a class="reference internal" href="cublas.html">cuBLAS</a><ul>
    <li class="toctree-l3"><a class="reference internal" href="cublas.html#blas-level-1">BLAS Level 1</a></li>
    <li class="toctree-l3"><a class="reference internal" href="cublas.html#blas-level-2">BLAS Level 2</a></li>
    <li class="toctree-l3"><a class="reference internal" href="cublas.html#blas-level-3">BLAS Level 3</a></li>
    </ul>
    </li>
    <li class="toctree-l2"><a class="reference internal" href="cusparse.html">cuSPARSE</a><ul>
    <li class="toctree-l3"><a class="reference internal" href="cusparse.html#blas-level-1">BLAS Level 1</a></li>
    <li class="toctree-l3"><a class="reference internal" href="cusparse.html#blas-level-2">BLAS Level 2</a></li>
    <li class="toctree-l3"><a class="reference internal" href="cusparse.html#blas-level-3">BLAS Level 3</a></li>
    <li class="toctree-l3"><a class="reference internal" href="cusparse.html#extra-functions">Extra Functions</a></li>
    <li class="toctree-l3"><a class="reference internal" href="cusparse.html#preconditioners">Preconditioners</a></li>
    <li class="toctree-l3"><a class="reference internal" href="cusparse.html#format-conversion">Format Conversion</a></li>
    </ul>
    </li>
    <li class="toctree-l2"><a class="reference internal" href="cufft.html">cuFFT</a><ul>
    <li class="toctree-l3"><a class="reference internal" href="cufft.html#forward-fft">Forward FFT</a></li>
    <li class="toctree-l3"><a class="reference internal" href="cufft.html#inverse-fft">Inverse FFT</a></li>
    <li class="toctree-l3"><a class="reference internal" href="cufft.html#fftplan">FFTPlan</a></li>
    </ul>
    </li>
    <li class="toctree-l2"><a class="reference internal" href="curand.html">cuRAND</a><ul>
    <li class="toctree-l3"><a class="reference internal" href="curand.html#class-prng">class PRNG</a></li>
    <li class="toctree-l3"><a class="reference internal" href="curand.html#class-qrng">class QRNG</a></li>
    <li class="toctree-l3"><a class="reference internal" href="curand.html#top-level-prng-functions">Top Level PRNG Functions</a></li>
    <li class="toctree-l3"><a class="reference internal" href="curand.html#top-level-qrng-functions">Top Level QRNG Functions</a></li>
    </ul>
    </li>
    <li class="toctree-l2"><a class="reference internal" href="sorting.html">CUDA Sorting</a><ul>
    <li class="toctree-l3"><a class="reference internal" href="sorting.html#sorting-large-arrays">Sorting Large Arrays</a></li>
    <li class="toctree-l3"><a class="reference internal" href="sorting.html#sorting-many-small-arrays">Sorting Many Small Arrays</a></li>
    </ul>
    </li>
    </ul>
    </li>
    <li class="toctree-l1"><a class="reference internal" href="mkl.html">MKL</a><ul>
    <li class="toctree-l2"><a class="reference internal" href="mkl_control.html">MKL utility functions</a><ul>
    <li class="toctree-l3"><a class="reference internal" href="mkl_control.html#reference">Reference</a></li>
    </ul>
    </li>
    <li class="toctree-l2"><a class="reference internal" href="mkl_fft.html">MKL FFT</a></li>
    <li class="toctree-l2"><a class="reference internal" href="mkl_ufuncs.html">Accelerated UFuncs</a><ul>
    <li class="toctree-l3"><a class="reference internal" href="mkl_ufuncs.html#arithmetic-functions">Arithmetic Functions</a></li>
    <li class="toctree-l3"><a class="reference internal" href="mkl_ufuncs.html#power-and-root-functions">Power and Root Functions</a></li>
    <li class="toctree-l3"><a class="reference internal" href="mkl_ufuncs.html#exponential-and-logarithmic-functions">Exponential and Logarithmic Functions</a></li>
    <li class="toctree-l3"><a class="reference internal" href="mkl_ufuncs.html#trigonometric-functions">Trigonometric Functions</a></li>
    <li class="toctree-l3"><a class="reference internal" href="mkl_ufuncs.html#hyperbolic-functions">Hyperbolic Functions</a></li>
    </ul>
    </li>
    </ul>
    </li>
    <li class="toctree-l1"><a class="reference internal" href="profiling.html">Profiling</a><ul>
    <li class="toctree-l2"><a class="reference internal" href="profiling.html#the-accelerate-profiler-api">The accelerate.profiler API</a></li>
    </ul>
    </li>
    </ul>
    </div>
    </div>
    <div class="section" id="license-agreement">
    <h2>License Agreement<a class="headerlink" href="#license-agreement" title="Permalink to this headline">¶</a></h2>
    <div class="toctree-wrapper compound">
    <ul>
    <li class="toctree-l1"><a class="reference internal" href="eula.html">Anaconda Accelerate END USER LICENSE AGREEMENT</a></li>
    </ul>
    </div>
    </div>

.. toctree::
   :maxdepth: 1
   :hidden:

   cublas
   cudalibs
   cufft
   curand
   cusparse
   eula
   mkl
   mkl_control
   mkl_fft
   mkl_ufuncs
   profiling
   releasenotes
   sorting
