support_new_device.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>Design Doc: Supporting new Device/Library &mdash; PaddlePaddle  文档</title>
  

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

        <link rel="index" title="索引"
              href="../genindex.html"/>
        <link rel="search" title="搜索" href="../search.html"/>
    <link rel="top" title="PaddlePaddle  文档" href="../index.html"/> 

  <link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
  <link rel="stylesheet" href="../_static/css/override.css" type="text/css" />
  <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">

  
  <header class="site-header">
    <div class="site-logo">
      <a href="/"><img src="../_static/images/PP_w.png"></a>
    </div>
    <div class="site-nav-links">
      <div class="site-menu">
        <a class="fork-on-github" href="https://github.com/PaddlePaddle/Paddle" target="_blank"><i class="fa fa-github"></i>Fork me on Github</a>
        <div class="language-switcher dropdown">
          <a type="button" data-toggle="dropdown">
            <span>English</span>
            <i class="fa fa-angle-up"></i>
            <i class="fa fa-angle-down"></i>
          </a>
          <ul class="dropdown-menu">
            <li><a href="/doc_cn">中文</a></li>
            <li><a href="/doc">English</a></li>
          </ul>
        </div>
        <ul class="site-page-links">
          <li><a href="/">Home</a></li>
        </ul>
      </div>
      <div class="doc-module">
        
        <ul>
<li class="toctree-l1"><a class="reference internal" href="../getstarted/index_cn.html">新手入门</a></li>
<li class="toctree-l1"><a class="reference internal" href="../howto/index_cn.html">进阶指南</a></li>
<li class="toctree-l1"><a class="reference internal" href="../api/index_cn.html">API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../faq/index_cn.html">FAQ</a></li>
<li class="toctree-l1"><a class="reference internal" href="../mobile/index_cn.html">MOBILE</a></li>
</ul>

        
<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>
  </header>
  
  <div class="main-content-wrap">

    
    <nav class="doc-menu-vertical" role="navigation">
        
          
          <ul>
<li class="toctree-l1"><a class="reference internal" href="../getstarted/index_cn.html">新手入门</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../getstarted/build_and_install/index_cn.html">安装与编译</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../getstarted/build_and_install/pip_install_cn.html">使用pip安装</a></li>
<li class="toctree-l3"><a class="reference internal" href="../getstarted/build_and_install/docker_install_cn.html">使用Docker安装运行</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/dev/build_cn.html">用Docker编译和测试PaddlePaddle</a></li>
<li class="toctree-l3"><a class="reference internal" href="../getstarted/build_and_install/build_from_source_cn.html">从源码编译</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../getstarted/concepts/use_concepts_cn.html">基本使用概念</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../howto/index_cn.html">进阶指南</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/cmd_parameter/index_cn.html">设置命令行参数</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../howto/usage/cmd_parameter/use_case_cn.html">使用案例</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/usage/cmd_parameter/arguments_cn.html">参数概述</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/usage/cmd_parameter/detail_introduction_cn.html">细节描述</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/cluster/cluster_train_cn.html">PaddlePaddle分布式训练</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/k8s/k8s_basis_cn.html">Kubernetes 简介</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/k8s/k8s_cn.html">Kubernetes单机训练</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/k8s/k8s_distributed_cn.html">Kubernetes分布式训练</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../howto/optimization/gpu_profiling_cn.html">GPU性能分析与调优</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../api/index_cn.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/model_configs.html">模型配置</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/evaluators.html">Evaluators</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/data.html">数据访问</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/data/data_reader.html">Data Reader Interface</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/data/image.html">Image Interface</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/data/dataset.html">Dataset</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/run_logic.html">训练与应用</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../faq/index_cn.html">FAQ</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../faq/build_and_install/index_cn.html">编译安装与单元测试</a></li>
<li class="toctree-l2"><a class="reference internal" href="../faq/model/index_cn.html">模型配置</a></li>
<li class="toctree-l2"><a class="reference internal" href="../faq/parameter/index_cn.html">参数设置</a></li>
<li class="toctree-l2"><a class="reference internal" href="../faq/local/index_cn.html">本地训练与预测</a></li>
<li class="toctree-l2"><a class="reference internal" href="../faq/cluster/index_cn.html">集群训练与预测</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../mobile/index_cn.html">MOBILE</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../mobile/cross_compiling_for_android_cn.html">Android平台编译指南</a></li>
<li class="toctree-l2"><a class="reference internal" href="../mobile/cross_compiling_for_ios_cn.html">iOS平台编译指南</a></li>
<li class="toctree-l2"><a class="reference internal" href="../mobile/cross_compiling_for_raspberry_cn.html">Raspberry Pi平台编译指南</a></li>
</ul>
</li>
</ul>

        
    </nav>
    
    <section class="doc-content-wrap">

      
<div role="navigation" aria-label="breadcrumbs navigation">
  <ul class="wy-breadcrumbs">
      
    <li>Design Doc: Supporting new Device/Library</li>
  </ul>
</div>
      
      <div class="wy-nav-content" id="doc-content">
        <div class="rst-content">
          <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
           <div itemprop="articleBody">
            
  <div class="section" id="design-doc-supporting-new-device-library">
<span id="design-doc-supporting-new-device-library"></span><h1>Design Doc: Supporting new Device/Library<a class="headerlink" href="#design-doc-supporting-new-device-library" title="永久链接至标题">¶</a></h1>
<div class="section" id="background">
<span id="background"></span><h2>Background<a class="headerlink" href="#background" title="永久链接至标题">¶</a></h2>
<p>Deep learning has a high demand for computing resources. New high-performance devices and computing libraries are appearing very frequently. Deep learning frameworks have to integrate these high-performance devices and computing libraries flexibly and efficiently.</p>
<p>On one hand, hardware and computing libraries usually do not have a one-to-one correspondence. For example,Intel CPUs support Eigen and MKL computing libraries while Nvidia GPUs support Eigen and cuDNN computing libraries. We have to implement operator specific kernels for each computing library.</p>
<p>On the other hand, users usually do not want to care about the low-level hardware and computing libraries when writing a neural network configuration. In Fluid, <code class="docutils literal"><span class="pre">Layer</span></code> is exposed in <code class="docutils literal"><span class="pre">Python</span></code>, and <code class="docutils literal"><span class="pre">Operator</span></code> is exposed in <code class="docutils literal"><span class="pre">C++</span></code>. Both <code class="docutils literal"><span class="pre">Layer</span></code> and <code class="docutils literal"><span class="pre">Operator</span></code> are hardware independent.</p>
<p>So, how to support a new Device/Library in Fluid becomes a challenge.</p>
</div>
<div class="section" id="basic-integrate-a-new-device-library">
<span id="basic-integrate-a-new-device-library"></span><h2>Basic: Integrate A New Device/Library<a class="headerlink" href="#basic-integrate-a-new-device-library" title="永久链接至标题">¶</a></h2>
<p>For a general overview of fluid, please refer to the <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/doc/howto/read_source.md">overview doc</a>.</p>
<p>There are mainly three parts that we have to consider while integrating a new device/library:</p>
<ul class="simple">
<li>Place and DeviceContext: indicates the device id and manages hardware resources</li>
<li>Memory and Tensor: malloc/free data on certain device</li>
<li>Math Functor and OpKernel: implement computing unit on certain devices/libraries</li>
</ul>
<div class="section" id="place-and-devicecontext">
<span id="place-and-devicecontext"></span><h3>Place and DeviceContext<a class="headerlink" href="#place-and-devicecontext" title="永久链接至标题">¶</a></h3>
<div class="section" id="place">
<span id="place"></span><h4>Place<a class="headerlink" href="#place" title="永久链接至标题">¶</a></h4>
<p>Fluid uses class <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/platform/place.h#L55">Place</a> to represent different devices and computing libraries. There are inheritance relationships between different kinds of <code class="docutils literal"><span class="pre">Place</span></code>.</p>
<div class="highlight-default"><div class="highlight"><pre><span></span>        <span class="o">|</span>   <span class="n">CPUPlace</span>   <span class="o">--&gt;</span> <span class="n">MKLDNNPlace</span>
<span class="n">Place</span> <span class="o">--|</span>   <span class="n">CUDAPlace</span>  <span class="o">--&gt;</span> <span class="n">CUDNNPlace</span>
        <span class="o">|</span>   <span class="n">FPGAPlace</span>
</pre></div>
</div>
<p>And <code class="docutils literal"><span class="pre">Place</span></code> is defined as follows:</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">typedef</span> <span class="n">boost</span><span class="p">::</span><span class="n">variant</span><span class="o">&lt;</span><span class="n">CUDAPlace</span><span class="p">,</span> <span class="n">CPUPlace</span><span class="p">,</span> <span class="n">FPGAPlace</span><span class="o">&gt;</span> <span class="n">Place</span><span class="p">;</span>
</pre></div>
</div>
</div>
<div class="section" id="devicecontext">
<span id="devicecontext"></span><h4>DeviceContext<a class="headerlink" href="#devicecontext" title="永久链接至标题">¶</a></h4>
<p>Fluid uses class <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/platform/device_context.h#L30">DeviceContext</a> to manage the resources in different hardwares, such as CUDA stream in <code class="docutils literal"><span class="pre">CDUADeviceContext</span></code>. There are also inheritance relationships between different kinds of <code class="docutils literal"><span class="pre">DeviceContext</span></code>.</p>
<div class="highlight-default"><div class="highlight"><pre><span></span>                <span class="o">/-&gt;</span>  <span class="n">CPUDeviceContext</span>   <span class="o">--&gt;</span> <span class="n">MKLDeviceContext</span>
<span class="n">DeviceContext</span> <span class="o">----&gt;</span>  <span class="n">CUDADeviceContext</span>  <span class="o">--&gt;</span> <span class="n">CUDNNDeviceContext</span>
                \<span class="o">-&gt;</span>  <span class="n">FPGADeviceContext</span>
</pre></div>
</div>
<p>An example of Nvidia GPU is as follows:</p>
<ul class="simple">
<li>DeviceContext</li>
</ul>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="k">class</span> <span class="nc">DeviceContext</span> <span class="p">{</span>
  <span class="n">virtual</span> <span class="n">Place</span> <span class="n">GetPlace</span><span class="p">()</span> <span class="n">const</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
<span class="p">};</span>  
</pre></div>
</div>
<ul class="simple">
<li>CUDADeviceContext</li>
</ul>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="k">class</span> <span class="nc">CUDADeviceContext</span> <span class="p">:</span> <span class="n">public</span> <span class="n">DeviceContext</span> <span class="p">{</span>
  <span class="n">Place</span> <span class="n">GetPlace</span><span class="p">()</span> <span class="n">const</span> <span class="n">override</span> <span class="p">{</span> <span class="k">return</span> <span class="n">place_</span><span class="p">;</span> <span class="p">}</span>
<span class="n">private</span><span class="p">:</span>
  <span class="n">CUDAPlace</span> <span class="n">place_</span><span class="p">;</span>
  <span class="n">cudaStream_t</span> <span class="n">stream_</span><span class="p">;</span> 
  <span class="n">cublasHandle_t</span> <span class="n">cublas_handle_</span><span class="p">;</span>
  <span class="n">std</span><span class="p">::</span><span class="n">unique_ptr</span><span class="o">&lt;</span><span class="n">Eigen</span><span class="p">::</span><span class="n">GpuDevice</span><span class="o">&gt;</span> <span class="n">eigen_device_</span><span class="p">;</span>  <span class="o">//</span> <span class="n">binds</span> <span class="k">with</span> <span class="n">stream_</span>
<span class="p">};</span>
</pre></div>
</div>
<ul class="simple">
<li>CUDNNDeviceContext</li>
</ul>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="k">class</span> <span class="nc">CUDNNDeviceContext</span> <span class="p">:</span> <span class="n">public</span> <span class="n">CUDADeviceContext</span> <span class="p">{</span>
  <span class="n">private</span><span class="p">:</span>
    <span class="n">cudnnHandle_t</span> <span class="n">cudnn_handle_</span><span class="p">;</span>
<span class="p">};</span>
</pre></div>
</div>
</div>
</div>
<div class="section" id="memory-and-tensor">
<span id="memory-and-tensor"></span><h3>Memory and Tensor<a class="headerlink" href="#memory-and-tensor" title="永久链接至标题">¶</a></h3>
<div class="section" id="memory-module">
<span id="memory-module"></span><h4>memory module<a class="headerlink" href="#memory-module" title="永久链接至标题">¶</a></h4>
<p>Fluid provides the following <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/memory/memory.h#L36">memory interfaces</a>:</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">template</span> <span class="o">&lt;</span><span class="n">typename</span> <span class="n">Place</span><span class="o">&gt;</span>
<span class="n">void</span><span class="o">*</span> <span class="n">Alloc</span><span class="p">(</span><span class="n">Place</span> <span class="n">place</span><span class="p">,</span> <span class="n">size_t</span> <span class="n">size</span><span class="p">);</span>

<span class="n">template</span> <span class="o">&lt;</span><span class="n">typename</span> <span class="n">Place</span><span class="o">&gt;</span>
<span class="n">void</span> <span class="n">Free</span><span class="p">(</span><span class="n">Place</span> <span class="n">place</span><span class="p">,</span> <span class="n">void</span><span class="o">*</span> <span class="n">ptr</span><span class="p">);</span>

<span class="n">template</span> <span class="o">&lt;</span><span class="n">typename</span> <span class="n">Place</span><span class="o">&gt;</span>
<span class="n">size_t</span> <span class="n">Used</span><span class="p">(</span><span class="n">Place</span> <span class="n">place</span><span class="p">);</span>
</pre></div>
</div>
<p>To implementing these interfaces, we have to implement MemoryAllocator for different Devices</p>
</div>
<div class="section" id="tensor">
<span id="tensor"></span><h4>Tensor<a class="headerlink" href="#tensor" title="永久链接至标题">¶</a></h4>
<p><a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/tensor.h#L36">Tensor</a> holds data with some shape in a specific Place.</p>
<div class="highlight-cpp"><div class="highlight"><pre><span></span><span class="k">class</span> <span class="nc">Tensor</span> <span class="p">{</span>
 <span class="k">public</span><span class="o">:</span>
  <span class="cm">/*! Return a pointer to mutable memory block. */</span>
  <span class="k">template</span> <span class="o">&lt;</span><span class="k">typename</span> <span class="n">T</span><span class="o">&gt;</span>
  <span class="kr">inline</span> <span class="n">T</span><span class="o">*</span> <span class="n">data</span><span class="p">();</span>

  <span class="cm">/**</span>
<span class="cm">   * @brief   Return a pointer to mutable memory block.</span>
<span class="cm">   * @note    If not exist, then allocation.</span>
<span class="cm">   */</span>
  <span class="k">template</span> <span class="o">&lt;</span><span class="k">typename</span> <span class="n">T</span><span class="o">&gt;</span>
  <span class="kr">inline</span> <span class="n">T</span><span class="o">*</span> <span class="n">mutable_data</span><span class="p">(</span><span class="n">platform</span><span class="o">::</span><span class="n">Place</span> <span class="n">place</span><span class="p">);</span>

  <span class="cm">/**</span>
<span class="cm">   * @brief     Return a pointer to mutable memory block.</span>
<span class="cm">   *</span>
<span class="cm">   * @param[in] dims    The dimensions of the memory block.</span>
<span class="cm">   * @param[in] place   The place of the memory block.</span>
<span class="cm">   *</span>
<span class="cm">   * @note      If not exist, then allocation.</span>
<span class="cm">   */</span>
  <span class="k">template</span> <span class="o">&lt;</span><span class="k">typename</span> <span class="n">T</span><span class="o">&gt;</span>
  <span class="kr">inline</span> <span class="n">T</span><span class="o">*</span> <span class="n">mutable_data</span><span class="p">(</span><span class="n">DDim</span> <span class="n">dims</span><span class="p">,</span> <span class="n">platform</span><span class="o">::</span><span class="n">Place</span> <span class="n">place</span><span class="p">);</span>

  <span class="cm">/*! Resize the dimensions of the memory block. */</span>
  <span class="kr">inline</span> <span class="n">Tensor</span><span class="o">&amp;</span> <span class="n">Resize</span><span class="p">(</span><span class="k">const</span> <span class="n">DDim</span><span class="o">&amp;</span> <span class="n">dims</span><span class="p">);</span>

  <span class="cm">/*! Return the dimensions of the memory block. */</span>
  <span class="kr">inline</span> <span class="k">const</span> <span class="n">DDim</span><span class="o">&amp;</span> <span class="n">dims</span><span class="p">()</span> <span class="k">const</span><span class="p">;</span>

 <span class="k">private</span><span class="o">:</span>
  <span class="cm">/*! holds the memory block if allocated. */</span>
  <span class="n">std</span><span class="o">::</span><span class="n">shared_ptr</span><span class="o">&lt;</span><span class="n">Placeholder</span><span class="o">&gt;</span> <span class="n">holder_</span><span class="p">;</span>

  <span class="cm">/*! points to dimensions of memory block. */</span>
  <span class="n">DDim</span> <span class="n">dim_</span><span class="p">;</span>
<span class="p">};</span>
</pre></div>
</div>
<p><code class="docutils literal"><span class="pre">Placeholder</span></code> is used to delay memory allocation; that is, we can first define a tensor, using <code class="docutils literal"><span class="pre">Resize</span></code> to configure its shape, and then call <code class="docutils literal"><span class="pre">mutuable_data</span></code> to allocate the actual memory.</p>
<div class="highlight-cpp"><div class="highlight"><pre><span></span><span class="n">paddle</span><span class="o">::</span><span class="n">framework</span><span class="o">::</span><span class="n">Tensor</span> <span class="n">t</span><span class="p">;</span>
<span class="n">paddle</span><span class="o">::</span><span class="n">platform</span><span class="o">::</span><span class="n">CPUPlace</span> <span class="n">place</span><span class="p">;</span>
<span class="c1">// set size first</span>
<span class="n">t</span><span class="p">.</span><span class="n">Resize</span><span class="p">({</span><span class="mi">2</span><span class="p">,</span> <span class="mi">3</span><span class="p">});</span>
<span class="c1">// allocate memory on CPU later</span>
<span class="n">t</span><span class="p">.</span><span class="n">mutable_data</span><span class="p">(</span><span class="n">place</span><span class="p">);</span>
</pre></div>
</div>
</div>
</div>
<div class="section" id="math-functor-and-opkernel">
<span id="math-functor-and-opkernel"></span><h3>Math Functor and OpKernel<a class="headerlink" href="#math-functor-and-opkernel" title="永久链接至标题">¶</a></h3>
<p>Fluid implements computing units based on different DeviceContexts. Some computing units are shared between operators. This common part will be put in operators/math directory as basic Functors.</p>
<p>Let&#8217;s take <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/operators/math/maxouting.h#L27">MaxOutFunctor</a> as an example:</p>
<p>The interface is defined in header file.</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">template</span> <span class="o">&lt;</span><span class="n">typename</span> <span class="n">DeviceContext</span><span class="p">,</span> <span class="n">typename</span> <span class="n">T</span><span class="o">&gt;</span>
<span class="k">class</span> <span class="nc">MaxOutFunctor</span> <span class="p">{</span>
 <span class="n">public</span><span class="p">:</span>
  <span class="n">void</span> <span class="n">operator</span><span class="p">()(</span><span class="n">const</span> <span class="n">DeviceContext</span><span class="o">&amp;</span> <span class="n">context</span><span class="p">,</span> <span class="n">const</span> <span class="n">framework</span><span class="p">::</span><span class="n">Tensor</span><span class="o">&amp;</span> <span class="nb">input</span><span class="p">,</span>
                  <span class="n">framework</span><span class="p">::</span><span class="n">Tensor</span><span class="o">*</span> <span class="n">output</span><span class="p">,</span> <span class="nb">int</span> <span class="n">groups</span><span class="p">);</span>
<span class="p">};</span>
</pre></div>
</div>
<p>CPU implemention is in .cc file</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">template</span> <span class="o">&lt;</span><span class="n">typename</span> <span class="n">T</span><span class="o">&gt;</span>
<span class="k">class</span> <span class="nc">MaxOutFunctor</span><span class="o">&lt;</span><span class="n">platform</span><span class="p">::</span><span class="n">CPUDeviceContext</span><span class="p">,</span> <span class="n">T</span><span class="o">&gt;</span> <span class="p">{</span>
  <span class="n">public</span><span class="p">:</span>
  <span class="n">void</span> <span class="n">operator</span><span class="p">()(</span><span class="n">const</span> <span class="n">platform</span><span class="p">::</span><span class="n">CPUDeviceContext</span><span class="o">&amp;</span> <span class="n">context</span><span class="p">,</span>
                  <span class="n">const</span> <span class="n">framework</span><span class="p">::</span><span class="n">Tensor</span><span class="o">&amp;</span> <span class="nb">input</span><span class="p">,</span> <span class="n">framework</span><span class="p">::</span><span class="n">Tensor</span><span class="o">*</span> <span class="n">output</span><span class="p">,</span>
                  <span class="nb">int</span> <span class="n">groups</span><span class="p">)</span> <span class="p">{</span>
                  <span class="o">...</span>
                  <span class="p">}</span>
<span class="p">};</span>
</pre></div>
</div>
<p>CUDA implemention is in .cu file</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">template</span> <span class="o">&lt;</span><span class="n">typename</span> <span class="n">T</span><span class="o">&gt;</span>
<span class="k">class</span> <span class="nc">MaxOutFunctor</span><span class="o">&lt;</span><span class="n">platform</span><span class="p">::</span><span class="n">CUDADeviceContext</span><span class="p">,</span> <span class="n">T</span><span class="o">&gt;</span> <span class="p">{</span>
 <span class="n">public</span><span class="p">:</span>
  <span class="n">void</span> <span class="n">operator</span><span class="p">()(</span><span class="n">const</span> <span class="n">platform</span><span class="p">::</span><span class="n">CUDADeviceContext</span><span class="o">&amp;</span> <span class="n">context</span><span class="p">,</span>
                  <span class="n">const</span> <span class="n">framework</span><span class="p">::</span><span class="n">Tensor</span><span class="o">&amp;</span> <span class="nb">input</span><span class="p">,</span> <span class="n">framework</span><span class="p">::</span><span class="n">Tensor</span><span class="o">*</span> <span class="n">output</span><span class="p">,</span>
                  <span class="nb">int</span> <span class="n">groups</span><span class="p">)</span> <span class="p">{</span>
                  <span class="o">...</span>
                  <span class="p">}</span>
<span class="p">};</span>                  
</pre></div>
</div>
<p>We get computing handle from a concrete DeviceContext, and make compution on tensors.</p>
<p>The implemention of <code class="docutils literal"><span class="pre">OpKernel</span></code> is similar to math functors, the extra thing we need to do is to register the OpKernel in a global map.</p>
<p>Fluid provides different register interfaces in op_registry.h</p>
<p>Let&#8217;s take <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/operators/crop_op.cc#L134">Crop</a> operator as an example:</p>
<p>In .cc file:</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">REGISTER_OP_CPU_KERNEL</span><span class="p">(</span><span class="n">crop</span><span class="p">,</span> <span class="n">ops</span><span class="p">::</span><span class="n">CropKernel</span><span class="o">&lt;</span><span class="nb">float</span><span class="o">&gt;</span><span class="p">);</span>
<span class="n">REGISTER_OP_CPU_KERNEL</span><span class="p">(</span>
    <span class="n">crop_grad</span><span class="p">,</span> <span class="n">ops</span><span class="p">::</span><span class="n">CropGradKernel</span><span class="o">&lt;</span><span class="n">paddle</span><span class="p">::</span><span class="n">platform</span><span class="p">::</span><span class="n">CPUDeviceContext</span><span class="p">,</span> <span class="nb">float</span><span class="o">&gt;</span><span class="p">);</span>
</pre></div>
</div>
<p>In .cu file:</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">REGISTER_OP_CUDA_KERNEL</span><span class="p">(</span><span class="n">crop</span><span class="p">,</span> <span class="n">ops</span><span class="p">::</span><span class="n">CropKernel</span><span class="o">&lt;</span><span class="nb">float</span><span class="o">&gt;</span><span class="p">);</span>
<span class="n">REGISTER_OP_CUDA_KERNEL</span><span class="p">(</span>
    <span class="n">crop_grad</span><span class="p">,</span> <span class="n">ops</span><span class="p">::</span><span class="n">CropGradKernel</span><span class="o">&lt;</span><span class="n">paddle</span><span class="p">::</span><span class="n">platform</span><span class="p">::</span><span class="n">CUDADeviceContext</span><span class="p">,</span> <span class="nb">float</span><span class="o">&gt;</span><span class="p">);</span>
</pre></div>
</div>
</div>
</div>
<div class="section" id="advanced-topics-how-to-switch-between-different-device-library">
<span id="advanced-topics-how-to-switch-between-different-device-library"></span><h2>Advanced topics: How to switch between different Device/Library<a class="headerlink" href="#advanced-topics-how-to-switch-between-different-device-library" title="永久链接至标题">¶</a></h2>
<p>Generally, we will impelement OpKernel for all Device/Library of an Operator. We can easily train a Convolutional Neural Network in GPU. However, some OpKernel is not sutibale on a specific Device. For example, crf operator can only run on CPU, whereas most other operators can run at GPU. To achieve high performance in such circumstance, we have to switch between different Device/Library.</p>
<p>We will discuss how to implement an efficient OpKernel switch policy.</p>
<ul class="simple">
<li>TBD</li>
</ul>
</div>
</div>


           </div>
          </div>
          <footer>
  

  <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,
            SOURCELINK_SUFFIX: ".txt",
        };
    </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="../_static/translations.js"></script>
      <script type="text/javascript" src="https://cdn.bootcss.com/mathjax/2.7.0/MathJax.js"></script>
       
  
    <script type="text/javascript" src="../_static/js/theme.js"></script>
  
  
  <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/js/bootstrap.min.js" integrity="sha384-Tc5IQib027qvyjSMfHjOMaLkfuWVxZxUPnCJA7l2mCWNIpG9mGCD8wGNIcPD7Txa" crossorigin="anonymous"></script>
  <script src="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/js/perfect-scrollbar.jquery.min.js"></script>
  <script src="../_static/js/paddle_doc_init.js"></script> 

</body>
</html>