Google Git
Sign in
apache / mxnet-site / b29f64d55499f1854ba5174ff443cf921bb86ea8 / . / versions / 0.11.0 / how_to / nnpack.html
blob: ba4810fbc162f60e5d66965564b07e1df72318d2 [file] [log] [blame]
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8"/>
<meta content="IE=edge" http-equiv="X-UA-Compatible"/>
<meta content="width=device-width, initial-scale=1" name="viewport"/>
<meta content="NNPACK for Multi-Core CPU Support in MXNet" property="og:title">
<meta content="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/og-logo.png" property="og:image">
<meta content="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/og-logo.png" property="og:image:secure_url">
<meta content="NNPACK for Multi-Core CPU Support in MXNet" property="og:description"/>
<title>NNPACK for Multi-Core CPU Support in MXNet — mxnet documentation</title>
<link crossorigin="anonymous" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/css/bootstrap.min.css" integrity="sha384-1q8mTJOASx8j1Au+a5WDVnPi2lkFfwwEAa8hDDdjZlpLegxhjVME1fgjWPGmkzs7" rel="stylesheet"/>
<link href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css" rel="stylesheet"/>
<link href="../_static/basic.css" rel="stylesheet" type="text/css">
<link href="../_static/pygments.css" rel="stylesheet" type="text/css">
<link href="../_static/mxnet.css" rel="stylesheet" type="text/css"/>
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT: '../',
VERSION: '',
COLLAPSE_INDEX: false,
FILE_SUFFIX: '.html',
HAS_SOURCE: true,
SOURCELINK_SUFFIX: '.txt'
};
</script>
<script src="https://code.jquery.com/jquery-1.11.1.min.js" type="text/javascript"></script>
<script src="../_static/underscore.js" type="text/javascript"></script>
<script src="../_static/searchtools_custom.js" type="text/javascript"></script>
<script src="../_static/doctools.js" type="text/javascript"></script>
<script src="../_static/selectlang.js" type="text/javascript"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML" type="text/javascript"></script>
<script type="text/javascript"> jQuery(function() { Search.loadIndex("/versions/0.11.0/searchindex.js"); Search.init();}); </script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new
Date();a=s.createElement(o),
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
})(window,document,'script','https://www.google-analytics.com/analytics.js','ga');
ga('create', 'UA-96378503-1', 'auto');
ga('send', 'pageview');
</script>
<!-- -->
<!-- <script type="text/javascript" src="../_static/jquery.js"></script> -->
<!-- -->
<!-- <script type="text/javascript" src="../_static/underscore.js"></script> -->
<!-- -->
<!-- <script type="text/javascript" src="../_static/doctools.js"></script> -->
<!-- -->
<!-- <script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script> -->
<!-- -->
<link href="../genindex.html" rel="index" title="Index">
<link href="../search.html" rel="search" title="Search"/>
<link href="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-icon.png" rel="icon" type="image/png"/>
</link></link></link></meta></meta></meta></head>
<body background="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-background-compressed.jpeg" role="document">
<div class="content-block"><div class="navbar navbar-fixed-top">
<div class="container" id="navContainer">
<div class="innder" id="header-inner">
<h1 id="logo-wrap">
<a href="../" id="logo"><img src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet_logo.png"/></a>
</h1>
<nav class="nav-bar" id="main-nav">
<a class="main-nav-link" href="/versions/0.11.0/get_started/install.html">Install</a>
<span id="dropdown-menu-position-anchor">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Gluon <span class="caret"></span></a>
<ul class="dropdown-menu navbar-menu" id="package-dropdown-menu">
<li><a class="main-nav-link" href="/versions/0.11.0/tutorials/gluon/gluon.html">About</a></li>
<li><a class="main-nav-link" href="https://www.d2l.ai/">Dive into Deep Learning</a></li>
<li><a class="main-nav-link" href="https://gluon-cv.mxnet.io">GluonCV Toolkit</a></li>
<li><a class="main-nav-link" href="https://gluon-nlp.mxnet.io/">GluonNLP Toolkit</a></li>
</ul>
</span>
<span id="dropdown-menu-position-anchor">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">API <span class="caret"></span></a>
<ul class="dropdown-menu navbar-menu" id="package-dropdown-menu">
<li><a class="main-nav-link" href="/versions/0.11.0/api/python/index.html">Python</a></li>
<li><a class="main-nav-link" href="/versions/0.11.0/api/c++/index.html">C++</a></li>
<li><a class="main-nav-link" href="/versions/0.11.0/api/julia/index.html">Julia</a></li>
<li><a class="main-nav-link" href="/versions/0.11.0/api/perl/index.html">Perl</a></li>
<li><a class="main-nav-link" href="/versions/0.11.0/api/r/index.html">R</a></li>
<li><a class="main-nav-link" href="/versions/0.11.0/api/scala/index.html">Scala</a></li>
</ul>
</span>
<span id="dropdown-menu-position-anchor-docs">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Docs <span class="caret"></span></a>
<ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-docs">
<li><a class="main-nav-link" href="/versions/0.11.0/how_to/faq.html">FAQ</a></li>
<li><a class="main-nav-link" href="/versions/0.11.0/tutorials/index.html">Tutorials</a>
<li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/v0.11.0/example">Examples</a></li>
<li><a class="main-nav-link" href="/versions/0.11.0/architecture/index.html">Architecture</a></li>
<li><a class="main-nav-link" href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home">Developer Wiki</a></li>
<li><a class="main-nav-link" href="/versions/0.11.0/model_zoo/index.html">Model Zoo</a></li>
<li><a class="main-nav-link" href="https://github.com/onnx/onnx-mxnet">ONNX</a></li>
</li></ul>
</span>
<span id="dropdown-menu-position-anchor-community">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Community <span class="caret"></span></a>
<ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-community">
<li><a class="main-nav-link" href="http://discuss.mxnet.io">Forum</a></li>
<li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/v0.11.0">Github</a></li>
<li><a class="main-nav-link" href="/versions/0.11.0/community/contribute.html">Contribute</a></li>
</ul>
</span>
<span id="dropdown-menu-position-anchor-version" style="position: relative"><a href="#" class="main-nav-link dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="true">0.11.0<span class="caret"></span></a><ul id="package-dropdown-menu" class="dropdown-menu"><li><a href="/">master</a></li><li><a href="/versions/1.7.0/">1.7.0</a></li><li><a href=/versions/1.6.0/>1.6.0</a></li><li><a href=/versions/1.5.0/>1.5.0</a></li><li><a href=/versions/1.4.1/>1.4.1</a></li><li><a href=/versions/1.3.1/>1.3.1</a></li><li><a href=/versions/1.2.1/>1.2.1</a></li><li><a href=/versions/1.1.0/>1.1.0</a></li><li><a href=/versions/1.0.0/>1.0.0</a></li><li><a href=/versions/0.12.1/>0.12.1</a></li><li><a href=/versions/0.11.0/>0.11.0</a></li></ul></span></nav>
<script> function getRootPath(){ return "../" } </script>
<div class="burgerIcon dropdown">
<a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button">☰</a>
<ul class="dropdown-menu" id="burgerMenu">
<li><a href="/versions/0.11.0/get_started/install.html">Install</a></li>
<li><a class="main-nav-link" href="/versions/0.11.0/tutorials/index.html">Tutorials</a></li>
<li class="dropdown-submenu dropdown">
<a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">Gluon</a>
<ul class="dropdown-menu navbar-menu" id="package-dropdown-menu">
<li><a class="main-nav-link" href="/versions/0.11.0/tutorials/gluon/gluon.html">About</a></li>
<li><a class="main-nav-link" href="http://gluon.mxnet.io">The Straight Dope (Tutorials)</a></li>
<li><a class="main-nav-link" href="https://gluon-cv.mxnet.io">GluonCV Toolkit</a></li>
<li><a class="main-nav-link" href="https://gluon-nlp.mxnet.io/">GluonNLP Toolkit</a></li>
</ul>
</li>
<li class="dropdown-submenu">
<a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">API</a>
<ul class="dropdown-menu">
<li><a class="main-nav-link" href="/versions/0.11.0/api/python/index.html">Python</a></li>
<li><a class="main-nav-link" href="/versions/0.11.0/api/c++/index.html">C++</a></li>
<li><a class="main-nav-link" href="/versions/0.11.0/api/julia/index.html">Julia</a></li>
<li><a class="main-nav-link" href="/versions/0.11.0/api/perl/index.html">Perl</a></li>
<li><a class="main-nav-link" href="/versions/0.11.0/api/r/index.html">R</a></li>
<li><a class="main-nav-link" href="/versions/0.11.0/api/scala/index.html">Scala</a></li>
</ul>
</li>
<li class="dropdown-submenu">
<a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">Docs</a>
<ul class="dropdown-menu">
<li><a href="/versions/0.11.0/how_to/faq.html" tabindex="-1">FAQ</a></li>
<li><a href="/versions/0.11.0/tutorials/index.html" tabindex="-1">Tutorials</a></li>
<li><a href="https://github.com/apache/incubator-mxnet/tree/v0.11.0/example" tabindex="-1">Examples</a></li>
<li><a href="/versions/0.11.0/architecture/index.html" tabindex="-1">Architecture</a></li>
<li><a href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home" tabindex="-1">Developer Wiki</a></li>
<li><a href="/versions/0.11.0/model_zoo/index.html" tabindex="-1">Gluon Model Zoo</a></li>
<li><a href="https://github.com/onnx/onnx-mxnet" tabindex="-1">ONNX</a></li>
</ul>
</li>
<li class="dropdown-submenu dropdown">
<a aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" role="button" tabindex="-1">Community</a>
<ul class="dropdown-menu">
<li><a href="http://discuss.mxnet.io" tabindex="-1">Forum</a></li>
<li><a href="https://github.com/apache/incubator-mxnet/tree/v0.11.0" tabindex="-1">Github</a></li>
<li><a href="/versions/0.11.0/community/contribute.html" tabindex="-1">Contribute</a></li>
</ul>
</li>
<li id="dropdown-menu-position-anchor-version-mobile" class="dropdown-submenu" style="position: relative"><a href="#" tabindex="-1">0.11.0</a><ul class="dropdown-menu"><li><a tabindex="-1" href=/>master</a></li><li><a tabindex="-1" href=/versions/1.6.0/>1.6.0</a></li><li><a tabindex="-1" href=/versions/1.5.0/>1.5.0</a></li><li><a tabindex="-1" href=/versions/1.4.1/>1.4.1</a></li><li><a tabindex="-1" href=/versions/1.3.1/>1.3.1</a></li><li><a tabindex="-1" href=/versions/1.2.1/>1.2.1</a></li><li><a tabindex="-1" href=/versions/1.1.0/>1.1.0</a></li><li><a tabindex="-1" href=/versions/1.0.0/>1.0.0</a></li><li><a tabindex="-1" href=/versions/0.12.1/>0.12.1</a></li><li><a tabindex="-1" href=/versions/0.11.0/>0.11.0</a></li></ul></li></ul>
</div>
<div class="plusIcon dropdown">
<a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button"><span aria-hidden="true" class="glyphicon glyphicon-plus"></span></a>
<ul class="dropdown-menu dropdown-menu-right" id="plusMenu"></ul>
</div>
<div id="search-input-wrap">
<form action="../search.html" autocomplete="off" class="" method="get" role="search">
<div class="form-group inner-addon left-addon">
<i class="glyphicon glyphicon-search"></i>
<input class="form-control" name="q" placeholder="Search" type="text"/>
</div>
<input name="check_keywords" type="hidden" value="yes">
<input name="area" type="hidden" value="default"/>
</input></form>
<div id="search-preview"></div>
</div>
<div id="searchIcon">
<span aria-hidden="true" class="glyphicon glyphicon-search"></span>
</div>
<!-- <div id="lang-select-wrap"> -->
<!-- <label id="lang-select-label"> -->
<!-- <\!-- <i class="fa fa-globe"></i> -\-> -->
<!-- <span></span> -->
<!-- </label> -->
<!-- <select id="lang-select"> -->
<!-- <option value="en">Eng</option> -->
<!-- <option value="zh">中文</option> -->
<!-- </select> -->
<!-- </div> -->
<!-- <a id="mobile-nav-toggle">
<span class="mobile-nav-toggle-bar"></span>
<span class="mobile-nav-toggle-bar"></span>
<span class="mobile-nav-toggle-bar"></span>
</a> -->
</div>
</div>
</div>
<script type="text/javascript">
$('body').css('background', 'white');
</script>
<div class="container">
<div class="row">
<div aria-label="main navigation" class="sphinxsidebar leftsidebar" role="navigation">
<div class="sphinxsidebarwrapper">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../api/python/index.html">Python Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../api/r/index.html">R Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../api/julia/index.html">Julia Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../api/c++/index.html">C++ Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../api/scala/index.html">Scala Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../api/perl/index.html">Perl Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="index.html">HowTo Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../architecture/index.html">System Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../tutorials/index.html">Tutorials</a></li>
</ul>
</div>
</div>
<div class="content">
<div class="page-tracker"></div>
<div class="section" id="nnpack-for-multi-core-cpu-support-in-mxnet">
<span id="nnpack-for-multi-core-cpu-support-in-mxnet"></span><h1>NNPACK for Multi-Core CPU Support in MXNet<a class="headerlink" href="#nnpack-for-multi-core-cpu-support-in-mxnet" title="Permalink to this headline"></a></h1>
<p><a class="reference external" href="https://github.com/Maratyszcza/NNPACK">NNPACK</a> is an acceleration package
for neural network computations, which can run on x86-64, ARMv7, or ARM64 architecture CPUs.
Using NNPACK, higher-level libraries like <em>MXNet</em> can speed up
the execution on multi-core CPU computers, including laptops and mobile devices.</p>
<p><em>MXNet</em> supports NNPACK for forward propagation (inference only) in convolution, max-pooling, and fully-connected layers.
In this document, we give a high level overview of how to use NNPACK with <em>MXNet</em>.</p>
</div>
<div class="section" id="conditions">
<span id="conditions"></span><h1>Conditions<a class="headerlink" href="#conditions" title="Permalink to this headline"></a></h1>
<p>The underlying implementation of NNPACK utilizes several acceleration methods,
including <a class="reference external" href="https://arxiv.org/abs/1312.5851">fft</a> and <a class="reference external" href="https://arxiv.org/abs/1509.09308">winograd</a>.
These algorithms work better on some special <code class="docutils literal"><span class="pre">batch</span> <span class="pre">size</span></code>, <code class="docutils literal"><span class="pre">kernel</span> <span class="pre">size</span></code>, and <code class="docutils literal"><span class="pre">stride</span></code> settings than on other,
so depending on the context, not all convolution, max-pooling, or fully-connected layers can be powered by NNPACK.
When favorable conditions for running NNPACKS are not met,
<em>MXNet</em> will fall back to the default implementation automatically.</p>
<p>NNPACK only supports Linux and OS X systems. Windows is not supported at present.
The following table explains under which conditions NNPACK will work.</p>
<table border="1" class="docutils">
<colgroup>
<col width="50%"/>
<col width="50%"/>
</colgroup>
<thead valign="bottom">
<tr class="row-odd"><th class="head">operation</th>
<th class="head">conditions</th>
</tr>
</thead>
<tbody valign="top">
<tr class="row-even"><td>convolution</td>
<td>2d convolution <code class="docutils literal"><span class="pre">and</span></code> no-bias=False <code class="docutils literal"><span class="pre">and</span></code> dilate=(1,1) <code class="docutils literal"><span class="pre">and</span></code> num_group=1 <code class="docutils literal"><span class="pre">and</span></code> batch-size = 1 or batch-size > 1 &amp;&amp; stride = (1,1);</td>
</tr>
<tr class="row-odd"><td>pooling</td>
<td>max-pooling <code class="docutils literal"><span class="pre">and</span></code> kernel=(2,2) <code class="docutils literal"><span class="pre">and</span></code> stride=(2,2) <code class="docutils literal"><span class="pre">and</span></code> pooling_convention=full</td>
</tr>
<tr class="row-even"><td>fully-connected</td>
<td>without any restrictions</td>
</tr>
</tbody>
</table>
</div>
<div class="section" id="build-install-nnpack-with-mxnet">
<span id="build-install-nnpack-with-mxnet"></span><h1>Build/Install NNPACK with MXNet<a class="headerlink" href="#build-install-nnpack-with-mxnet" title="Permalink to this headline"></a></h1>
<p>If the trained model meets some conditions of using NNPACK,
you can build MXNet with NNPACK support.
Follow these simple steps:</p>
<ul class="simple">
<li>Build NNPACK shared library with the following commands. <em>MXNet</em> will link NNPACK dynamically.</li>
</ul>
<p>Note: The following NNPACK installation instructions have been tested on Ubuntu 14.04 and 16.04.</p>
<div class="highlight-bash"><div class="highlight"><pre><span></span><span class="c1"># Install Pip</span>
$ sudo apt-get update
$ sudo apt-get install -y python-pip
$ sudo pip install --upgrade pip
<span class="c1"># Install Peach</span>
$ git clone https://github.com/Maratyszcza/PeachPy.git
$ <span class="nb">cd</span> PeachPy
$ sudo pip install --upgrade -r requirements.txt
$ python setup.py generate
$ sudo pip install --upgrade .
<span class="c1"># Install Ninja Build System</span>
$ sudo apt-get install ninja-build
$ pip install ninja-syntax
<span class="c1"># Build NNPack shared library</span>
$ <span class="nb">cd</span> ~
$ git clone --recursive https://github.com/Maratyszcza/NNPACK.git
$ <span class="nb">cd</span> NNPACK
<span class="c1"># Latest NNPACK do not support building NNPACK as shared library using --enable-shared flag</span>
<span class="c1"># Reset to commit that supports it.</span>
$ git reset --hard 9c6747d7b80051b40e6f92d6828e2ed997529cd2
$ git submodule init <span class="o">&amp;&amp;</span> git submodule update --recursive
$ python ./configure.py --enable-shared
$ ninja
$ <span class="nb">cd</span> ~
</pre></div>
</div>
<ul class="simple">
<li>Set lib path of NNPACK as the environment variable, e.g. <code class="docutils literal"><span class="pre">export</span> <span class="pre">LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$YOUR_NNPACK_INSTALL_PATH/lib</span></code></li>
<li>Add the include file of NNPACK and its third-party to <code class="docutils literal"><span class="pre">ADD_CFLAGS</span></code> in config.mk, e.g. <code class="docutils literal"><span class="pre">ADD_CFLAGS</span> <span class="pre">=</span> <span class="pre">-I$(YOUR_NNPACK_INSTALL_PATH)/include/</span> <span class="pre">-I$(YOUR_NNPACK_INSTALL_PATH)/third-party/pthreadpool/include/</span></code></li>
<li>Set <code class="docutils literal"><span class="pre">USE_NNPACK</span> <span class="pre">=</span> <span class="pre">1</span></code> in config.mk.</li>
<li>Build MXNet from source following the <a class="reference external" href="/versions/0.11.0/get_started/install.html">install guide</a>.</li>
</ul>
</div>
<div class="section" id="nnpack-performance">
<span id="nnpack-performance"></span><h1>NNPACK Performance<a class="headerlink" href="#nnpack-performance" title="Permalink to this headline"></a></h1>
<p>Though not all convolutional, pooling, and fully-connected layers can make full use of NNPACK,
for some popular models it provides significant speedups. These include the most popular image recognition networks: Alexnet, VGG, and Inception-bn.</p>
<p>To benchmark NNPACK, we use <code class="docutils literal"><span class="pre">example/image-classification/benchmark_score.py</span></code>(changed with more range of batch-size). We use CPU e5-2670, MXNET_CPU_NNPACK_NTHREADS=4.</p>
<p>build MXNet without NNPACK, the log is:</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">network</span><span class="p">:</span> <span class="n">alexnet</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">device</span><span class="p">:</span> <span class="n">cpu</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">1</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">6.389429</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">2</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">7.961457</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">4</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">8.950112</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">8</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">9.578176</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">16</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">9.701248</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">32</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">9.839940</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">64</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">10.075369</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">128</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">10.053556</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">256</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">9.972228</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">network</span><span class="p">:</span> <span class="n">vgg</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">device</span><span class="p">:</span> <span class="n">cpu</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">1</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">1.223822</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">2</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">1.322814</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">4</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">1.383586</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">8</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">1.402376</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">16</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">1.415972</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">32</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">1.428377</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">64</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">1.443987</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">128</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">1.427531</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">256</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">1.435279</span>
</pre></div>
</div>
<p>build MXNet with NNPACK, log is:</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">network</span><span class="p">:</span> <span class="n">alexnet</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">device</span><span class="p">:</span> <span class="n">cpu</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">1</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">19.027215</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">2</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">12.879975</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">4</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">17.424076</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">8</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">21.283966</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">16</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">24.469325</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">32</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">25.910348</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">64</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">27.441672</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">128</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">28.009156</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">256</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">28.918950</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">network</span><span class="p">:</span> <span class="n">vgg</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">device</span><span class="p">:</span> <span class="n">cpu</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">1</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">3.980907</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">2</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">2.392069</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">4</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">3.610553</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">8</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">4.994450</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">16</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">6.396612</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">32</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">7.614288</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">64</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">8.826084</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">128</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">9.193653</span>
<span class="n">INFO</span><span class="p">:</span><span class="n">root</span><span class="p">:</span><span class="n">batch</span> <span class="n">size</span> <span class="mi">256</span><span class="p">,</span> <span class="n">image</span><span class="o">/</span><span class="n">sec</span><span class="p">:</span> <span class="mf">9.991472</span>
</pre></div>
</div>
<p>The results show that NNPACK can confer a speedup of about 2X~7X as compared to the original <em>MXNet</em> CPU implementation.</p>
</div>
<div class="section" id="tips">
<span id="tips"></span><h1>Tips<a class="headerlink" href="#tips" title="Permalink to this headline"></a></h1>
<p>NNPACK aims to provide high-performance implementations of some layers for multi-core CPUs, so you can easily set the thread number by changing the environmental variable <code class="docutils literal"><span class="pre">MXNET_CPU_NNPACK_NTHREADS</span></code>. However, we found that the performance is not proportional to the number of threads, and suggest using 4~8 threads when using NNPACK.</p>
</div>
</div>
</div>
<div aria-label="main navigation" class="sphinxsidebar rightsidebar" role="navigation">
<div class="sphinxsidebarwrapper">
<h3><a href="../index.html">Table Of Contents</a></h3>
<ul>
<li><a class="reference internal" href="#">NNPACK for Multi-Core CPU Support in MXNet</a></li>
<li><a class="reference internal" href="#conditions">Conditions</a></li>
<li><a class="reference internal" href="#build-install-nnpack-with-mxnet">Build/Install NNPACK with MXNet</a></li>
<li><a class="reference internal" href="#nnpack-performance">NNPACK Performance</a></li>
<li><a class="reference internal" href="#tips">Tips</a></li>
</ul>
</div>
</div>
</div><div class="footer">
<div class="section-disclaimer">
<div class="container">
<div>
<img height="60" src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/apache_incubator_logo.png"/>
<p>
Apache MXNet is an effort undergoing incubation at The Apache Software Foundation (ASF), <strong>sponsored by the <i>Apache Incubator</i></strong>. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
</p>
<p>
"Copyright © 2017-2018, The Apache Software Foundation
Apache MXNet, MXNet, Apache, the Apache feather, and the Apache MXNet project logo are either registered trademarks or trademarks of the Apache Software Foundation."
</p>
</div>
</div>
</div>
</div> <!-- pagename != index -->
</div>
<script crossorigin="anonymous" integrity="sha384-0mSbJDEHialfmuBBQP6A4Qrprq5OVfW37PRR3j5ELqxss1yVqOtnepnHVP9aJ7xS" src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/js/bootstrap.min.js"></script>
<script src="../_static/js/sidebar.js" type="text/javascript"></script>
<script src="../_static/js/search.js" type="text/javascript"></script>
<script src="../_static/js/navbar.js" type="text/javascript"></script>
<script src="../_static/js/clipboard.min.js" type="text/javascript"></script>
<script src="../_static/js/copycode.js" type="text/javascript"></script>
<script src="../_static/js/page.js" type="text/javascript"></script>
<script src="../_static/js/docversion.js" type="text/javascript"></script>
<script type="text/javascript">
$('body').ready(function () {
$('body').css('visibility', 'visible');
});
</script>
</body>
</html>