openmpi_en.html



<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
  <meta charset="utf-8">
  
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  
  <title>OpenMPI &mdash; PaddlePaddle  documentation</title>
  

    <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
  

        <link rel="index" title="Index"
              href="../../../genindex.html"/>
        <link rel="search" title="Search" href="../../../search.html"/>
    <link rel="top" title="PaddlePaddle  documentation" href="../../../index.html"/>
        <link rel="up" title="Use different clusters" href="index_en.html"/>
        <link rel="next" title="Kubernetes" href="k8s_en.html"/>
        <link rel="prev" title="Fabric" href="fabric_en.html"/> 
<script>
var _hmt = _hmt || [];
(function() {
  var hm = document.createElement("script");
  hm.src = "//hm.baidu.com/hm.js?b9a314ab40d04d805655aab1deee08ba";
  var s = document.getElementsByTagName("script")[0]; 
  s.parentNode.insertBefore(hm, s);
})();
</script>


  <script src="../../../_static/js/modernizr.min.js"></script>

</head>

<body class="wy-body-for-nav" role="document">

  <div class="wy-grid-for-nav">

    
    <nav data-toggle="wy-nav-shift" class="wy-nav-side">
      <div class="wy-side-scroll">
        <div class="wy-side-nav-search">
          

            <a href="../../../index_en.html" class="icon icon-home"> PaddlePaddle
          

          </a>

          
<div role="search">
  <form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
    <input type="text" name="q" placeholder="Search docs" />
    <input type="hidden" name="check_keywords" value="yes" />
    <input type="hidden" name="area" value="default" />
  </form>
</div>

          
        </div>

        <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
          
<nav class="doc-menu-vertical" role="navigation">

<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_en.html">GET STARTED</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../getstarted/quickstart_en.html">Quick Start</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../getstarted/concepts/use_concepts_en.html">Basic Concept</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../build_and_install/index_en.html">Install and Build</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../build_and_install/pip_install_en.html">Install using pip</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../build_and_install/docker_install_en.html">Run in Docker Containers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../build_and_install/build_from_source_en.html">Build from Sources</a></li>
</ul>
</li>
<li class="toctree-l1 current"><a class="reference internal" href="../../index_en.html">HOW TO</a><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../../cmd_parameter/index_en.html">Set Command-line Parameters</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../cmd_parameter/use_case_en.html">Use Case</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../cmd_parameter/arguments_en.html">Argument Outline</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../cmd_parameter/detail_introduction_en.html">Detail Description</a></li>
</ul>
</li>
<li class="toctree-l2 current"><a class="reference internal" href="../index_en.html">Distributed Training</a><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="../preparations_en.html">Preparations</a></li>
<li class="toctree-l3"><a class="reference internal" href="../cmd_argument_en.html">Command-line arguments</a></li>
<li class="toctree-l3 current"><a class="reference internal" href="index_en.html">Use different clusters</a><ul class="current">
<li class="toctree-l4"><a class="reference internal" href="fabric_en.html">Fabric</a></li>
<li class="toctree-l4 current"><a class="current reference internal" href="#">OpenMPI</a></li>
<li class="toctree-l4"><a class="reference internal" href="k8s_en.html">Kubernetes</a></li>
<li class="toctree-l4"><a class="reference internal" href="k8s_aws_en.html">Kubernetes on AWS</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../rnn/index_en.html">RNN Models</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../rnn/rnn_config_en.html">RNN Configuration</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../rnn/recurrent_group_en.html">Recurrent Group Tutorial</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../rnn/hierarchical_layer_en.html">Layers supporting hierarchical sequence as input</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../rnn/hrnn_rnn_api_compare_en.html">API comparision between RNN and hierarchical RNN</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../dev/index_en.html">Development</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../dev/contribute_to_paddle_en.html">Contribute Code</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../dev/write_docs_en.html">Contribute Documentation</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../faq/index_en.html">FAQ</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../faq/build_and_install/index_en.html">Install, Build and Unit test</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../faq/model/index_en.html">Model Configuration</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../faq/parameter/index_en.html">Parameter Setting</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../faq/local/index_en.html">Local Training and Prediction</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../faq/cluster/index_en.html">Cluster Training and Prediction</a></li>
</ul>
</li>
</ul>

</nav>

        </div>
      </div>
    </nav>

    <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">

      
      <nav class="wy-nav-top" role="navigation" aria-label="top navigation">
        <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
        <a href="../../../index_en.html">PaddlePaddle</a>
      </nav>


      <div class="wy-nav-content">
        <div class="rst-content">
          

<div role="navigation" aria-label="breadcrumbs navigation">
  <ul class="wy-breadcrumbs">
    <li><a href="../../../index_en.html">Docs</a> &raquo;</li>
      
          <li><a href="../../index_en.html">HOW TO</a> &raquo;</li>
      
          <li><a href="../index_en.html">Distributed Training</a> &raquo;</li>
      
          <li><a href="index_en.html">Use different clusters</a> &raquo;</li>
      
    <li>OpenMPI</li>
      <li class="wy-breadcrumbs-aside">
        
          
            <a href="../../../_sources/howto/cluster/multi_cluster/openmpi_en.md.txt" rel="nofollow"> View page source</a>
          
        
      </li>
  </ul>
  <hr/>
</div>
          <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
           <div itemprop="articleBody">
            
  <div class="section" id="openmpi">
<span id="openmpi"></span><h1>OpenMPI<a class="headerlink" href="#openmpi" title="Permalink to this headline">¶</a></h1>
<div class="section" id="prepare-an-openmpi-cluster">
<span id="prepare-an-openmpi-cluster"></span><h2>Prepare an OpenMPI cluster<a class="headerlink" href="#prepare-an-openmpi-cluster" title="Permalink to this headline">¶</a></h2>
<p>Run the following command to start a 3-node MPI cluster and one &#8220;head&#8221; node.</p>
<div class="highlight-bash"><div class="highlight"><pre><span></span><span class="nb">cd</span> paddle/scripts/cluster_train_v2/openmpi/docker_cluster
kubectl create -f head.yaml
kubectl create -f mpi-nodes.yaml
</pre></div>
</div>
<p>Then you can log in to every OpenMPI node using ssh without input any passwords.</p>
</div>
<div class="section" id="launching-cluster-job">
<span id="launching-cluster-job"></span><h2>Launching Cluster Job<a class="headerlink" href="#launching-cluster-job" title="Permalink to this headline">¶</a></h2>
<p>Follow the steps to launch a PaddlePaddle training job in OpenMPI cluster:\</p>
<div class="highlight-bash"><div class="highlight"><pre><span></span><span class="c1"># find out node IP addresses</span>
kubectl get po -o wide
<span class="c1"># generate a &quot;machines&quot; file containing node IP addresses</span>
kubectl get po -o wide <span class="p">|</span> grep nodes <span class="p">|</span> awk <span class="s1">&#39;{print $6}&#39;</span> &gt; machines
<span class="c1"># copy necessary files onto &quot;head&quot; node</span>
scp -i ssh/id_rsa.mpi.pub machines prepare.py train.py start_mpi_train.sh tutorial@<span class="o">[</span>headIP<span class="o">]</span>:~
<span class="c1"># login to head node using ssh</span>
ssh -i ssh/id_rsa.mpi.pub tutorial@<span class="o">[</span>headIP<span class="o">]</span>
<span class="c1"># --------------- in head node ---------------</span>
<span class="c1"># prepare training data</span>
python prepare.py
<span class="c1"># copy training data and dict file to MPI nodes</span>
cat machines <span class="p">|</span> xargs -i scp word_dict.pickle train.py start_mpi_train.sh machines <span class="o">{}</span>:/home/tutorial
<span class="c1"># creat a directory for storing log files</span>
mpirun -hostfile machines -n <span class="m">3</span> mkdir /home/tutorial/logs
<span class="c1"># copy training data to every node</span>
scp train.txt-00000 test.txt-00000 <span class="o">[</span>node1IP<span class="o">]</span>:/home/tutorial
scp train.txt-00001 test.txt-00001 <span class="o">[</span>node2IP<span class="o">]</span>:/home/tutorial
scp train.txt-00002 test.txt-00002 <span class="o">[</span>node3IP<span class="o">]</span>:/home/tutorial
<span class="c1"># start the job</span>
mpirun -hostfile machines -n <span class="m">3</span>  /home/tutorial/start_mpi_train.sh
</pre></div>
</div>
</div>
</div>


           </div>
          </div>
          <footer>
  
    <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
      
        <a href="k8s_en.html" class="btn btn-neutral float-right" title="Kubernetes" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
      
      
        <a href="fabric_en.html" class="btn btn-neutral" title="Fabric" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
      
    </div>
  

  <hr/>

  <div role="contentinfo">
    <p>
        &copy; Copyright 2016, PaddlePaddle developers.

    </p>
  </div>
  Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. 

</footer>

        </div>
      </div>

    </section>

  </div>
  

    <script type="text/javascript">
        var DOCUMENTATION_OPTIONS = {
            URL_ROOT:'../../../',
            VERSION:'',
            COLLAPSE_INDEX:false,
            FILE_SUFFIX:'.html',
            HAS_SOURCE:  true
        };
    </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>

  
    <script type="text/javascript" src="../../../_static/js/theme.js"></script>
  

  <script type="text/javascript">
      jQuery(function () {
          SphinxRtdTheme.StickyNav.enable();
      });
  </script>
   

</body>
</html>