kernel_hint_design.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>Problem &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"/> 
<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_cn.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>
<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/quickstart_cn.html">快速开始</a></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="../build_and_install/index_cn.html">安装与编译</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../build_and_install/pip_install_cn.html">使用pip安装</a></li>
<li class="toctree-l2"><a class="reference internal" href="../build_and_install/docker_install_cn.html">使用Docker安装运行</a></li>
<li class="toctree-l2"><a class="reference internal" href="../build_and_install/build_from_source_cn.html">从源码编译</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../howto/index_cn.html">进阶使用</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../howto/cmd_parameter/index_cn.html">命令行参数设置</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../howto/cmd_parameter/use_case_cn.html">使用案例</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/cmd_parameter/arguments_cn.html">参数概述</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/cmd_parameter/detail_introduction_cn.html">细节描述</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../howto/cluster/index_cn.html">分布式训练</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../howto/cluster/preparations_cn.html">环境准备</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/cluster/cmd_argument_cn.html">启动参数说明</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/cluster/multi_cluster/index_cn.html">在不同集群中运行</a><ul>
<li class="toctree-l4"><a class="reference internal" href="../howto/cluster/multi_cluster/k8s_cn.html">Kubernetes单机训练</a></li>
<li class="toctree-l4"><a class="reference internal" href="../howto/cluster/multi_cluster/k8s_distributed_cn.html">Kubernetes分布式训练</a></li>
<li class="toctree-l4"><a class="reference internal" href="../howto/cluster/multi_cluster/openmpi_cn.html">在OpenMPI集群中启动训练</a></li>
<li class="toctree-l4"><a class="reference internal" href="../howto/cluster/multi_cluster/fabric_cn.html">使用fabric启动集群训练</a></li>
<li class="toctree-l4"><a class="reference internal" href="../howto/cluster/multi_cluster/k8s_aws_cn.html">Kubernetes on AWS</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../howto/capi/index_cn.html">C-API预测库</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../howto/capi/compile_paddle_lib_cn.html">安装与编译C-API预测库</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/capi/organization_of_the_inputs_cn.html">输入/输出数据组织</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/capi/workflow_of_capi_cn.html">C-API使用流程</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../howto/rnn/index_cn.html">RNN模型</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../howto/rnn/rnn_config_cn.html">RNN配置</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/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/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性能调优</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../dev/index_cn.html">开发标准</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
<li class="toctree-l2"><a class="reference internal" href="../dev/write_docs_cn.html">如何贡献文档</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>
</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_cn.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_cn.html">Docs</a> &raquo;</li>
      
    <li>Problem</li>
      <li class="wy-breadcrumbs-aside">
        
          
            <a href="../_sources/design/kernel_hint_design.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="problem">
<span id="problem"></span><h1>Problem<a class="headerlink" href="#problem" title="永久链接至标题">¶</a></h1>
<p>In PaddlePaddle&#8217;s <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/doc/design/switch_kernel.md">Design</a>, one Operator may have multiple kernels. Users may have some personal preference to choose a certain type of kernel for an operator, such as <code class="docutils literal"><span class="pre">force_cpu</span></code> to choose a CPU kernel, <code class="docutils literal"><span class="pre">use_cudnn</span></code> to choose a CUDNN kernel, we need to provide a way for users to do this.</p>
<p>In the current design, we use KernelType to describe one kernel.</p>
<div class="highlight-cpp"><div class="highlight"><pre><span></span><span class="k">struct</span> <span class="n">KernelType</span> <span class="p">{</span>
  <span class="n">Place</span> <span class="n">place_</span><span class="p">;</span>
  <span class="n">DataType</span> <span class="n">data_type_</span><span class="p">;</span>
  <span class="n">LayoutType</span> <span class="n">layout_</span><span class="p">;</span>
<span class="p">};</span>
</pre></div>
</div>
<p><code class="docutils literal"><span class="pre">place_</span></code> <code class="docutils literal"><span class="pre">data_type_</span></code> and <code class="docutils literal"><span class="pre">layout_</span></code> can be got from the input tensors of the operator, <code class="docutils literal"><span class="pre">GetActualKernelType(inputs)</span></code> use inputs to infer the proper kernel key that fit the incoming data, but users can not directly configure it.</p>
<p>The <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/doc/design/switch_kernel.md">design</a> also provides a virtual method <code class="docutils literal"><span class="pre">GetExpectedKernelType</span></code> that user can overload and use to choose the KernelType they want to use.</p>
<p>So we should send the information user defined in proto to <code class="docutils literal"><span class="pre">GetExpectedKernelType</span></code> for choosing a kernel.</p>
<p>The problem is, how should we define and send the information for <code class="docutils literal"><span class="pre">GetExpectedKernelType</span></code> to use?</p>
</div>
<div class="section" id="solution">
<span id="solution"></span><h1>Solution<a class="headerlink" href="#solution" title="永久链接至标题">¶</a></h1>
<div class="section" id="potential-choice">
<span id="potential-choice"></span><h2>Potential choice<a class="headerlink" href="#potential-choice" title="永久链接至标题">¶</a></h2>
<ol class="simple">
<li>Do nothing, let the user add the information they want to operator‘s attribute and get them inside <code class="docutils literal"><span class="pre">GetExpectedKernelType</span></code>, this can work properly. But there is a little problem that users may define many kinds of hints for the same purpose, such as <code class="docutils literal"><span class="pre">force_cpu</span></code>, <code class="docutils literal"><span class="pre">use_cpu</span></code>, <code class="docutils literal"><span class="pre">cpu_kernel</span></code> to choose CPU kernel, and <code class="docutils literal"><span class="pre">use_cudnn</span></code>, <code class="docutils literal"><span class="pre">force_cudnn</span></code>, <code class="docutils literal"><span class="pre">cudnn_kernel</span></code> to choose CUDNN kernel.</li>
<li>Pre-define all the needed option and use a single attr key such as <code class="docutils literal"><span class="pre">kernel_hint</span></code> for the user, this is not so flexible if the user wants to define some more kind of hint.</li>
</ol>
</div>
<div class="section" id="final-choice">
<span id="final-choice"></span><h2>Final choice<a class="headerlink" href="#final-choice" title="永久链接至标题">¶</a></h2>
<p>To provide enough flexibility while avoiding confusion definition, we can define some global constants for these attribute names, such as <code class="docutils literal"><span class="pre">force_cpu</span></code>, <code class="docutils literal"><span class="pre">use_cudnn</span></code>, <code class="docutils literal"><span class="pre">use_mkldnn</span></code> for a user to choose.</p>
<p>In C++</p>
<div class="highlight-cpp"><div class="highlight"><pre><span></span><span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">kForceCPU</span> <span class="o">=</span> <span class="s">&quot;force_cpu&quot;</span><span class="p">;</span>
<span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">kUseCUDNN</span> <span class="o">=</span> <span class="s">&quot;use_cudnn&quot;</span><span class="p">;</span>
<span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">kUseMKLDNN</span> <span class="o">=</span> <span class="s">&quot;use_mkldnn&quot;</span><span class="p">;</span>

<span class="n">KernelType</span> <span class="nf">GetExpectedKernelType</span><span class="p">()</span> <span class="p">{</span>
  <span class="k">if</span> <span class="p">(</span><span class="n">Attr</span><span class="o">&lt;</span><span class="kt">bool</span><span class="o">&gt;</span><span class="p">(</span><span class="n">kForceCPU</span><span class="p">))</span> <span class="p">{</span>
    <span class="k">return</span> <span class="n">KernelType</span><span class="p">(</span><span class="n">CPUPlace</span><span class="p">,</span> <span class="p">...)</span>
  <span class="p">}</span> <span class="k">else</span> <span class="p">{</span>
    <span class="p">...</span>
  <span class="p">}</span>
<span class="p">}</span>
</pre></div>
</div>
<p>In Python code</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">FORCE_CPU</span> <span class="o">=</span> <span class="n">core</span><span class="o">.</span><span class="n">kForceCPU</span><span class="p">()</span>

<span class="k">def</span> <span class="nf">xx_layer</span><span class="p">(</span><span class="o">...</span><span class="p">,</span> <span class="n">force_cpu</span><span class="o">=</span><span class="n">false</span><span class="p">):</span>
  <span class="n">layer_helper</span> <span class="o">=</span> <span class="n">LayerHelper</span><span class="p">(</span><span class="o">...</span><span class="p">)</span>
  <span class="n">layer_helper</span><span class="o">.</span><span class="n">append_op</span><span class="p">(</span>
    <span class="nb">type</span><span class="o">=</span><span class="s2">&quot;xx&quot;</span><span class="p">,</span>
    <span class="n">attr</span><span class="o">=</span><span class="p">{</span><span class="n">FORCE_CPU</span><span class="p">:</span> <span class="n">force_cpu</span><span class="p">})</span>
</pre></div>
</div>
</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
        };
    </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 type="text/javascript">
      jQuery(function () {
          SphinxRtdTheme.StickyNav.enable();
      });
  </script>
   

</body>
</html>