float16.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: float16 &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/docker_install_cn.html">PaddlePaddle的Docker容器使用方式</a></li>
<li class="toctree-l3"><a class="reference internal" href="../getstarted/build_and_install/cmake/build_from_source_cn.html">PaddlePaddle的编译选项</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/build_cn.html">编译PaddlePaddle和运行单元测试</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></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">构建Android平台上的PaddlePaddle库</a></li>
<li class="toctree-l2"><a class="reference internal" href="../mobile/cross_compiling_for_ios_cn.html">构建iOS平台上的PaddlePaddle库</a></li>
<li class="toctree-l2"><a class="reference internal" href="../mobile/cross_compiling_for_raspberry_cn.html">构建Raspberry Pi平台上的PaddlePaddle库</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: float16</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-float16">
<span id="design-doc-float16"></span><h1>Design Doc: float16<a class="headerlink" href="#design-doc-float16" title="永久链接至标题">¶</a></h1>
<div class="section" id="why-float16">
<span id="why-float16"></span><h2>Why float16<a class="headerlink" href="#why-float16" title="永久链接至标题">¶</a></h2>
<p>Half precision (float16) is a binary floating-point format that occupies 16 bits in memory. float16 is half the size of traditional 32-bit single precision format (float) and has lower precision and smaller range.</p>
<p>When high precision computation is not required, using float16 data type could potentially</p>
<ul class="simple">
<li>reduce storage space, memory bandwidth, and power usages;</li>
<li>increase the chance of data fitting into a smaller cache of lower latency;</li>
<li>provide arithmetic speed up if supported by hardware.</li>
</ul>
</div>
<div class="section" id="survey-of-current-float16-support">
<span id="survey-of-current-float16-support"></span><h2>Survey of current float16 support<a class="headerlink" href="#survey-of-current-float16-support" title="永久链接至标题">¶</a></h2>
<p>A brief survey of float16 support on different compilers, hardwares, and libraries can be found below. Interested readers can refer to <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/issues/4853">link1</a> and <a class="reference external" href="https://github.com/Xreki/Xreki.github.io/blob/master/multi_data_types_in_dl_framework/ppt/float16_and_quantized_type.md">link2</a> for more info.</p>
<p>The goal of float16 is to serve as a key for the executor to find and run the correct version of compute method specialized for float16 in operator kernel. It should be compatible with various natively supported float16 implementations including <code class="docutils literal"><span class="pre">__half</span></code> for cuda, <code class="docutils literal"><span class="pre">float16_t</span></code> for ARM, and <code class="docutils literal"><span class="pre">Eigen::half</span></code> for Eigen to make writing customized float16 kernels easier.</p>
<div class="section" id="compiler">
<span id="compiler"></span><h3>Compiler<a class="headerlink" href="#compiler" title="永久链接至标题">¶</a></h3>
<ul class="simple">
<li>nvcc supports <code class="docutils literal"><span class="pre">__half</span></code> data type after CUDA 7.5.</li>
<li><code class="docutils literal"><span class="pre">__fp16</span></code> or <code class="docutils literal"><span class="pre">float16_t</span></code> is supported as storage type for gcc &gt;= 6.1 and clang &gt;= 3.4.</li>
<li><code class="docutils literal"><span class="pre">__fp16</span></code> or <code class="docutils literal"><span class="pre">float16_t</span></code> is supported as arithmetic type for gcc &gt;= 7.1 and clang &gt;= 3.9.</li>
</ul>
</div>
<div class="section" id="hardware">
<span id="hardware"></span><h3>Hardware<a class="headerlink" href="#hardware" title="永久链接至标题">¶</a></h3>
<ul class="simple">
<li><code class="docutils literal"><span class="pre">__half</span></code> is supported on GPU with compute capability &gt;= 5.3.</li>
<li><code class="docutils literal"><span class="pre">__fp16</span></code> is supported as storage type for ARMv7-A, ARMv8-A, and above.</li>
<li><code class="docutils literal"><span class="pre">__fp16</span></code> is supported as arithmetic type after ARMv8.2-A (currently, the only microarchitecture implementing ARMv8.2-A is ARM Cortex-A75, which is announced in May 2017. There seems to be no application processors currently available on market that adopts this architecture. It is reported that Qualcomm Snapdragon 845 uses Cortex-A75 design and will be available in mobile devices in early 2018).</li>
</ul>
</div>
<div class="section" id="libraries">
<span id="libraries"></span><h3>Libraries<a class="headerlink" href="#libraries" title="永久链接至标题">¶</a></h3>
<ul class="simple">
<li><a class="reference external" href="https://github.com/RLovelett/eigen">Eigen</a> &gt;= 3.3 supports float16 calculation on both GPU and CPU using the <code class="docutils literal"><span class="pre">Eigen::half</span></code> class. It is mostly useful for Nvidia GPUs because of the overloaded arithmetic operators using cuda intrinsics. It falls back to using software emulation on CPU for calculation and there is no special treatment to ARM processors.</li>
<li><a class="reference external" href="https://github.com/ARM-software/ComputeLibrary">ARM compute library</a> &gt;= 17.02.01 supports NEON FP16 kernels (requires ARMv8.2-A CPU).</li>
</ul>
</div>
</div>
<div class="section" id="implementation">
<span id="implementation"></span><h2>Implementation<a class="headerlink" href="#implementation" title="永久链接至标题">¶</a></h2>
<p>The float16 class holds a 16-bit <code class="docutils literal"><span class="pre">uint16_t</span></code> data internally.</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">struct</span> <span class="n">float16</span> <span class="p">{</span>
  <span class="n">uint16_t</span> <span class="n">x</span><span class="p">;</span>
<span class="p">};</span>
</pre></div>
</div>
<p>float16 supports the following features:</p>
<ul class="simple">
<li>constructors / assignment operators that take input from primitive data types including bool, integers of various length, float, and double.</li>
<li>constructors / assignment operators that take input from <code class="docutils literal"><span class="pre">__half</span></code> on cuda, <code class="docutils literal"><span class="pre">float16_t</span></code> on ARM, and <code class="docutils literal"><span class="pre">Eigen::half</span></code> on Eigen.</li>
<li>conversion operators to primitive data types and half precision data types on cuda, ARM and Eigen.</li>
<li>overloaded arithmetic operators for cuda, arm, and non-arm cpu, respectively. These operators will take advantage of the cuda and ARM intrinsics on the corresponding hardware.</li>
</ul>
<p>To support the above features, two fundamental conversion functions are provided:</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">float16</span> <span class="n">float_to_half_rn</span><span class="p">(</span><span class="nb">float</span> <span class="n">f</span><span class="p">);</span>  <span class="o">//</span> <span class="n">convert</span> <span class="n">to</span> <span class="n">half</span> <span class="n">precision</span> <span class="ow">in</span> <span class="nb">round</span><span class="o">-</span><span class="n">to</span><span class="o">-</span><span class="n">nearest</span><span class="o">-</span><span class="n">even</span> <span class="n">mode</span>
<span class="nb">float</span> <span class="n">half_to_float</span><span class="p">(</span><span class="n">float16</span> <span class="n">h</span><span class="p">);</span>
</pre></div>
</div>
<p>which provides one-to-one conversion between float32 and float16. These twos functions will do different conversion routines based on the current hardware. CUDA/ARM instrinsics will be used when the corresonding hardware is available. If the hardware or compiler level does not support float32 to float16 conversion, software emulation will be performed to do the conversion.</p>
</div>
<div class="section" id="to-do">
<span id="to-do"></span><h2>To do<a class="headerlink" href="#to-do" title="永久链接至标题">¶</a></h2>
<p>After float16 class is available, some of the future items are below:</p>
<ul class="simple">
<li>Update pybind/tensor_py.h to bind c++ float16 with numpy float16.</li>
<li>Modify <code class="docutils literal"><span class="pre">GetKernelType()</span></code> method in <code class="docutils literal"><span class="pre">framework/operator.h</span></code> to make it compatible with float16.</li>
<li>Create a type-casting operator that can convert the data type in tensor between float16 and other types.</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>