319 lines
61 KiB
HTML
319 lines
61 KiB
HTML
|
||
|
||
<!DOCTYPE html>
|
||
<html class="writer-html5" lang="zh-CN" data-content_root="../../">
|
||
<head>
|
||
<meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||
<title>GRU — MindSpore Signal+ 使用手册 alpha 文档</title>
|
||
<link rel="stylesheet" type="text/css" href="../../_static/pygments.css?v=03e43079" />
|
||
<link rel="stylesheet" type="text/css" href="../../_static/css/theme.css?v=e59714d7" />
|
||
<link rel="stylesheet" type="text/css" href="../../_static/table.css?v=72b86d3e" />
|
||
|
||
|
||
<script src="../../_static/jquery.js?v=5d32c60e"></script>
|
||
<script src="../../_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
|
||
<script src="../../_static/documentation_options.js?v=406e4f49"></script>
|
||
<script src="../../_static/doctools.js?v=9bcbadda"></script>
|
||
<script src="../../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||
<script src="../../_static/translations.js?v=beaddf03"></script>
|
||
<script async="async" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
|
||
<script src="../../_static/table.js?v=99ed15ba"></script>
|
||
<script src="../../_static/js/theme.js"></script>
|
||
<link rel="index" title="索引" href="../../genindex.html" />
|
||
<link rel="search" title="搜索" href="../../search.html" />
|
||
<link rel="next" title="Assert" href="assert.html" />
|
||
<link rel="prev" title="Conv2dTranspose" href="conv2d_transpose.html" />
|
||
</head>
|
||
|
||
<body class="wy-body-for-nav">
|
||
<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.html" class="icon icon-home">
|
||
MindSpore Signal+ 使用手册
|
||
</a>
|
||
<div role="search">
|
||
<form id="rtd-search-form" class="wy-form" action="../../search.html" method="get">
|
||
<input type="text" name="q" placeholder="搜索文档" aria-label="搜索文档" />
|
||
<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="导航菜单">
|
||
<ul>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../quickstart/index.html">快速入门</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../appdevelop/index.html">应用开发示例</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../index.html">算子库支持</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../refdoc/index.html">参考资料</a></li>
|
||
</ul>
|
||
|
||
</div>
|
||
</div>
|
||
</nav>
|
||
|
||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="移动版导航菜单" >
|
||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||
<a href="../../index.html">MindSpore Signal+ 使用手册</a>
|
||
</nav>
|
||
|
||
<div class="wy-nav-content">
|
||
<div class="rst-content">
|
||
<div role="navigation" aria-label="页面导航">
|
||
<ul class="wy-breadcrumbs">
|
||
<li><a href="../../index.html" class="icon icon-home" aria-label="Home"></a></li>
|
||
<li class="breadcrumb-item"><a href="../index.html">算子库支持</a></li>
|
||
<li class="breadcrumb-item"><a href="dsplib_index.html">DSP Library C API Reference</a></li>
|
||
<li class="breadcrumb-item active">GRU</li>
|
||
<li class="wy-breadcrumbs-aside">
|
||
<a href="../../_sources/functionlib/dsplib/gru.rst.txt" rel="nofollow"> 查看页面源码</a>
|
||
</li>
|
||
</ul>
|
||
<hr/>
|
||
</div>
|
||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||
<div itemprop="articleBody">
|
||
|
||
<section id="gru">
|
||
<h1>GRU<a class="headerlink" href="#gru" title="Link to this heading"></a></h1>
|
||
<p>将多层门控循环单元 (GRU) RNN 应用于输入序列。</p>
|
||
<p>GRU 网络模型中有两个门:更新门和重置门。将两个连续的时间节点表示为 <span class="math notranslate nohighlight">\(t - 1\)</span> 和 <span class="math notranslate nohighlight">\(t\)</span>。给定一个在时刻 <span class="math notranslate nohighlight">\(t\)</span> 的输入 <span class="math notranslate nohighlight">\(x_t\)</span>,一个隐藏状态 <span class="math notranslate nohighlight">\(h_{t-1}\)</span>,在时刻 <span class="math notranslate nohighlight">\(t\)</span> 的更新门和重置门使用门控制机制计算。更新门 <span class="math notranslate nohighlight">\(z_t\)</span> 用于控制前一时刻的状态信息被带入到当前状态中的程度,重置门 <span class="math notranslate nohighlight">\(r_t\)</span> 控制前一状态有多少信息被写入到当前候选集 <span class="math notranslate nohighlight">\(n_t\)</span> 上</p>
|
||
<p>对于输入序列中的每个元素,每一层计算以下函数:</p>
|
||
<div class="math notranslate nohighlight">
|
||
\begin{align*}
|
||
r_t &= \sigma(W_{ir}x_t + b_{ir} + W_{hr}h_{(t-1)} + b_{hr}) \\
|
||
z_t &= \sigma(W_{iz}x_t + b_{iz} + W_{hz}h_{(t-1)} + b_{hz}) \\
|
||
n_t &= \tanh(W_{in}x_t + b_{in} + r_t \odot (W_{hn}h_{(t-1)} + b_{hn})) \\
|
||
h_t &= (1-z_t) \odot n_t + z_t \odot h_{(t-1)}
|
||
\end{align*}</div><p>其中 <span class="math notranslate nohighlight">\(\sigma\)</span> 是 sigmoid 激活函数,<span class="math notranslate nohighlight">\(\odot\)</span> 是 Hadamard 积(逐元素乘积)。<span class="math notranslate nohighlight">\(W, b\)</span> 是公式中输出和输入之间的可学习权重。例如,<span class="math notranslate nohighlight">\(W_{ir}, b_{ir}\)</span> 是用于将输入 <span class="math notranslate nohighlight">\(x_t\)</span> 转换为 <span class="math notranslate nohighlight">\(r_t\)</span> 的权重和偏置。</p>
|
||
<p>注意,本算子中候选门 <span class="math notranslate nohighlight">\(n_t\)</span> 的计算与原始论文和Mindspore框架略有不同。在原始实现中,<span class="math notranslate nohighlight">\(r_t\)</span> 和上一隐藏状态 <span class="math notranslate nohighlight">\(h_{(t-1)}\)</span> 之间的 Hadamard 积 (<span class="math notranslate nohighlight">\(\odot\)</span>) 在与权重矩阵 <span class="math notranslate nohighlight">\(W\)</span> 相乘和加上偏置之前进行:</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[n_t = \tanh(W_{in}x_t + b_{in} + W_{hn}(r_t \odot h_{(t-1)}) + b_{hn})\]</div>
|
||
<p>本算子采用 PyTorch 实现方式,是在 <span class="math notranslate nohighlight">\(W_{hn}h_{(t-1)}\)</span> 之后完成的:</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[n_t = \tanh(W_{in}x_t + b_{in} + r_t \odot (W_{hn}h_{(t-1)} + b_{hn}))\]</div>
|
||
<dl class="simple">
|
||
<dt>输入:</dt><dd><ul class="simple">
|
||
<li><p><strong>input</strong> - 输入数据的地址。</p></li>
|
||
<li><p><strong>weight_g</strong> - 可学习的输入-隐藏权重的地址。</p></li>
|
||
<li><p><strong>weight_r</strong> - 可学习的隐藏-隐藏权重的地址。</p></li>
|
||
<li><p><strong>input_bias</strong> - 可学习的输入-隐藏偏置的地址。</p></li>
|
||
<li><p><strong>state_bias</strong> - 可学习的隐藏-隐藏偏置的地址。</p></li>
|
||
<li><p><strong>hidden_state</strong> - 初始隐藏状态的地址。</p></li>
|
||
<li><p><strong>buffer</strong> - 用于存储中间计算结果。</p></li>
|
||
<li><p><strong>gru_param</strong> - 算子计算所需参数的结构体。其各成员见下述。</p></li>
|
||
<li><p><strong>core_mask</strong> - 核掩码。</p></li>
|
||
</ul>
|
||
</dd>
|
||
</dl>
|
||
<p><strong>GruParameter定义:</strong></p>
|
||
<div class="highlight-c notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="k">typedef</span><span class="w"> </span><span class="k">struct</span><span class="w"> </span><span class="nc">GruParameter</span><span class="w"> </span><span class="p">{</span>
|
||
<span class="linenos"> 2</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">input_size_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 输入input中预期特征的数量</span>
|
||
<span class="linenos"> 3</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">hidden_size_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 隐藏状态h中的特征数量</span>
|
||
<span class="linenos"> 4</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">seq_len_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 输入batch中每个序列的长度</span>
|
||
<span class="linenos"> 5</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">batch_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 总批次数</span>
|
||
<span class="linenos"> 6</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">output_step_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 每次循环中output步长</span>
|
||
<span class="linenos"> 7</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">bidirectional_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 是否为双向GRU</span>
|
||
<span class="linenos"> 8</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">input_row_align_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 输入行对齐值</span>
|
||
<span class="linenos"> 9</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">input_col_align_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 输入列对齐值</span>
|
||
<span class="linenos">10</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">state_row_align_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 隐藏状态行对齐值</span>
|
||
<span class="linenos">11</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">state_col_align_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 隐藏状态列对齐值</span>
|
||
<span class="linenos">12</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">check_seq_len_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 进行计算的序列长度</span>
|
||
<span class="linenos">13</span><span class="p">}</span><span class="w"> </span><span class="n">GruParameter</span><span class="p">;</span>
|
||
</pre></div>
|
||
</div>
|
||
<dl class="simple">
|
||
<dt>输出:</dt><dd><ul class="simple">
|
||
<li><p><strong>output</strong> - 输出地址。</p></li>
|
||
<li><p><strong>hidden_state</strong> - 最终的隐藏状态。</p></li>
|
||
</ul>
|
||
</dd>
|
||
<dt>支持平台:</dt><dd><p><code class="docutils literal notranslate"><span class="pre">FT78NE</span></code>
|
||
<code class="docutils literal notranslate"><span class="pre">MT7004</span></code></p>
|
||
</dd>
|
||
</dl>
|
||
<div class="admonition note">
|
||
<p class="admonition-title">备注</p>
|
||
<ul class="simple">
|
||
<li><p>FT78NE 支持int8, fp32</p></li>
|
||
<li><p>MT7004 支持fp16, fp32</p></li>
|
||
</ul>
|
||
</div>
|
||
<p><strong>共享存储版本:</strong></p>
|
||
<dl class="c function">
|
||
<dt class="sig sig-object c" id="c.i8_Gru_s">
|
||
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">i8_Gru_s</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">output</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">input</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight_g</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight_r</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">input_bias</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">state_bias</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">hidden_state</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">buffer</span></span><span class="p"><span class="pre">[</span></span><span class="m"><span class="pre">4</span></span><span class="p"><span class="pre">]</span></span>, <span class="n"><span class="pre">GruParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">gru_param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.i8_Gru_s" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="c function">
|
||
<dt class="sig sig-object c" id="c.hp_Gru_s">
|
||
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">hp_Gru_s</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">output</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">input</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight_g</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight_r</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">input_bias</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">state_bias</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">hidden_state</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">buffer</span></span><span class="p"><span class="pre">[</span></span><span class="m"><span class="pre">4</span></span><span class="p"><span class="pre">]</span></span>, <span class="n"><span class="pre">GruParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">gru_param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><span class="p"><span class="pre">;</span></span><a class="headerlink" href="#c.hp_Gru_s" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="c function">
|
||
<dt class="sig sig-object c" id="c.fp_Gru_s">
|
||
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">fp_Gru_s</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">output</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">input</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight_g</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight_r</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">input_bias</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">state_bias</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">hidden_state</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">buffer</span></span><span class="p"><span class="pre">[</span></span><span class="m"><span class="pre">4</span></span><span class="p"><span class="pre">]</span></span>, <span class="n"><span class="pre">GruParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">gru_param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><span class="p"><span class="pre">;</span></span><a class="headerlink" href="#c.fp_Gru_s" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<p><strong>C调用示例:</strong></p>
|
||
<div class="highlight-c notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="kt">void</span><span class="w"> </span><span class="nf">TestGruSMCFp32</span><span class="p">(</span><span class="kt">int</span><span class="w"> </span><span class="n">check_seq_len</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">seq_len</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">batch_size</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">input_size</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">bidirectional</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">hidden_size</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">core_mask</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
|
||
<span class="linenos"> 2</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">core_id</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">get_core_id</span><span class="p">();</span>
|
||
<span class="linenos"> 3</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">logic_core_id</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">GetLogicCoreId</span><span class="p">(</span><span class="n">core_mask</span><span class="p">,</span><span class="w"> </span><span class="n">core_id</span><span class="p">);</span>
|
||
<span class="linenos"> 4</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">core_num</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">GetCoreNum</span><span class="p">(</span><span class="n">core_mask</span><span class="p">);</span>
|
||
<span class="linenos"> 5</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">output</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x88000000</span><span class="p">;</span>
|
||
<span class="linenos"> 6</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">input</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x88100000</span><span class="p">;</span>
|
||
<span class="linenos"> 7</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">weight_g</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x88200000</span><span class="p">;</span>
|
||
<span class="linenos"> 8</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">weight_r</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x88300000</span><span class="p">;</span>
|
||
<span class="linenos"> 9</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">input_bias</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x88400000</span><span class="p">;</span>
|
||
<span class="linenos">10</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">state_bias</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x88500000</span><span class="p">;</span>
|
||
<span class="linenos">11</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">hidden_state</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x88600000</span><span class="p">;</span>
|
||
<span class="linenos">12</span><span class="w"> </span><span class="kt">float</span><span class="o">**</span><span class="w"> </span><span class="n">buffer</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="o">**</span><span class="p">)</span><span class="mh">0x88700000</span><span class="p">;</span>
|
||
<span class="linenos">13</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">output_hidden_state</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x88800000</span><span class="p">;</span>
|
||
<span class="linenos">14</span><span class="w"> </span><span class="n">GruParameter</span><span class="o">*</span><span class="w"> </span><span class="n">param</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="n">GruParameter</span><span class="o">*</span><span class="p">)</span><span class="mh">0x88900000</span><span class="p">;</span>
|
||
<span class="linenos">15</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">hidden_state_batch</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
|
||
<span class="linenos">16</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">num_directions</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
|
||
<span class="linenos">17</span><span class="w"> </span><span class="k">if</span><span class="w"> </span><span class="p">(</span><span class="n">bidirectional</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
|
||
<span class="linenos">18</span><span class="w"> </span><span class="n">hidden_state_batch</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">hidden_state_batch</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="mi">2</span><span class="p">;</span>
|
||
<span class="linenos">19</span><span class="w"> </span><span class="n">num_directions</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">num_directions</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="mi">2</span><span class="p">;</span>
|
||
<span class="linenos">20</span><span class="w"> </span><span class="p">}</span>
|
||
<span class="linenos">21</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">input_col_align</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">hidden_size</span><span class="p">;</span>
|
||
<span class="linenos">22</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">state_col_align</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">hidden_size</span><span class="p">;</span>
|
||
<span class="linenos">23</span><span class="w"> </span><span class="k">if</span><span class="w"> </span><span class="p">(</span><span class="n">logic_core_id</span><span class="w"> </span><span class="o">==</span><span class="w"> </span><span class="mi">0</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
|
||
<span class="linenos">24</span><span class="w"> </span><span class="n">memcpy</span><span class="p">(</span><span class="n">output_hidden_state</span><span class="p">,</span><span class="w"> </span><span class="n">hidden_state</span><span class="p">,</span><span class="w"> </span><span class="n">hidden_state_batch</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">batch_size</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">hidden_size</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="k">sizeof</span><span class="p">(</span><span class="kt">float</span><span class="p">));</span>
|
||
<span class="linenos">25</span><span class="w"> </span><span class="n">memcpy</span><span class="p">(</span><span class="n">check_output_hidden_state</span><span class="p">,</span><span class="w"> </span><span class="n">hidden_state</span><span class="p">,</span><span class="w"> </span><span class="n">hidden_state_batch</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">batch_size</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">hidden_size</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="k">sizeof</span><span class="p">(</span><span class="kt">float</span><span class="p">));</span>
|
||
<span class="linenos">26</span><span class="w"> </span><span class="n">buffer</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x88A00000</span><span class="p">;</span>
|
||
<span class="linenos">27</span><span class="w"> </span><span class="n">buffer</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x88B00000</span><span class="p">;</span>
|
||
<span class="linenos">28</span><span class="w"> </span><span class="n">buffer</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x88C00000</span><span class="p">;</span>
|
||
<span class="linenos">29</span><span class="w"> </span><span class="n">buffer</span><span class="p">[</span><span class="mi">3</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x88D00000</span><span class="p">;</span>
|
||
<span class="linenos">30</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">batch_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">batch_size</span><span class="p">;</span>
|
||
<span class="linenos">31</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">bidirectional_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">bidirectional</span><span class="p">;</span>
|
||
<span class="linenos">32</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">hidden_size_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">hidden_size</span><span class="p">;</span>
|
||
<span class="linenos">33</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">input_col_align_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">input_col_align</span><span class="p">;</span>
|
||
<span class="linenos">34</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">input_size_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">input_size</span><span class="p">;</span>
|
||
<span class="linenos">35</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">output_step_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">batch_size</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">hidden_size</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">num_directions</span><span class="p">;</span>
|
||
<span class="linenos">36</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">seq_len_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">seq_len</span><span class="p">;</span>
|
||
<span class="linenos">37</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">state_col_align_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">state_col_align</span><span class="p">;</span>
|
||
<span class="linenos">38</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">check_seq_len_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">check_seq_len</span><span class="p">;</span>
|
||
<span class="linenos">39</span><span class="w"> </span><span class="p">}</span>
|
||
<span class="linenos">40</span><span class="w"> </span><span class="n">sys_bar</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span><span class="w"> </span><span class="n">core_num</span><span class="p">);</span><span class="w"> </span><span class="c1">// 初始化参数完成后进行同步</span>
|
||
<span class="hll"><span class="linenos">41</span><span class="w"> </span><span class="n">fp_Gru_s</span><span class="p">(</span><span class="n">output</span><span class="p">,</span><span class="w"> </span><span class="n">input</span><span class="p">,</span><span class="w"> </span><span class="n">weight_g</span><span class="p">,</span><span class="w"> </span><span class="n">weight_r</span><span class="p">,</span><span class="w"> </span><span class="n">input_bias</span><span class="p">,</span><span class="w"> </span><span class="n">state_bias</span><span class="p">,</span><span class="w"> </span><span class="n">output_hidden_state</span><span class="p">,</span><span class="w"> </span><span class="n">buffer</span><span class="p">,</span><span class="w"> </span><span class="n">param</span><span class="p">,</span><span class="w"> </span><span class="n">core_mask</span><span class="p">);</span>
|
||
</span><span class="linenos">42</span><span class="p">}</span>
|
||
<span class="linenos">43</span>
|
||
<span class="linenos">44</span><span class="kt">void</span><span class="w"> </span><span class="nf">main</span><span class="p">()</span><span class="w"> </span><span class="p">{</span>
|
||
<span class="linenos">45</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">check_seq_len</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">2</span><span class="p">;</span>
|
||
<span class="linenos">46</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">seq_len</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">2</span><span class="p">;</span>
|
||
<span class="linenos">47</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">batch_size</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">2</span><span class="p">;</span>
|
||
<span class="linenos">48</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">input_size</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">2</span><span class="p">;</span>
|
||
<span class="linenos">49</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">bidirectional</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span>
|
||
<span class="linenos">50</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">hidden_size</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">2</span><span class="p">;</span>
|
||
<span class="linenos">51</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">core_mask</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mb">0b1111</span><span class="p">;</span>
|
||
<span class="linenos">52</span><span class="w"> </span><span class="n">TestGruSMCFp32</span><span class="p">(</span><span class="n">check_seq_len</span><span class="p">,</span><span class="w"> </span><span class="n">seq_len</span><span class="p">,</span><span class="w"> </span><span class="n">batch_size</span><span class="p">,</span><span class="w"> </span><span class="n">input_size</span><span class="p">,</span><span class="w"> </span><span class="n">bidirectional</span><span class="p">,</span><span class="w"> </span><span class="n">hidden_size</span><span class="p">,</span><span class="w"> </span><span class="n">core_mask</span><span class="p">);</span>
|
||
<span class="linenos">53</span><span class="p">}</span>
|
||
</pre></div>
|
||
</div>
|
||
<p><strong>私有存储版本:</strong></p>
|
||
<dl class="c function">
|
||
<dt class="sig sig-object c" id="c.i8_Gru_p">
|
||
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">i8_Gru_p</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">output</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">input</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight_g</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight_r</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">input_bias</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">state_bias</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">hidden_state</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">buffer</span></span><span class="p"><span class="pre">[</span></span><span class="m"><span class="pre">4</span></span><span class="p"><span class="pre">]</span></span>, <span class="n"><span class="pre">GruParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">gru_param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.i8_Gru_p" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="c function">
|
||
<dt class="sig sig-object c" id="c.hp_Gru_p">
|
||
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">hp_Gru_p</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">output</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">input</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight_g</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight_r</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">input_bias</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">state_bias</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">hidden_state</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">buffer</span></span><span class="p"><span class="pre">[</span></span><span class="m"><span class="pre">4</span></span><span class="p"><span class="pre">]</span></span>, <span class="n"><span class="pre">GruParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">gru_param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><span class="p"><span class="pre">;</span></span><a class="headerlink" href="#c.hp_Gru_p" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="c function">
|
||
<dt class="sig sig-object c" id="c.fp_Gru_p">
|
||
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">fp_Gru_p</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">output</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">input</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight_g</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight_r</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">input_bias</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">state_bias</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">hidden_state</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">buffer</span></span><span class="p"><span class="pre">[</span></span><span class="m"><span class="pre">4</span></span><span class="p"><span class="pre">]</span></span>, <span class="n"><span class="pre">GruParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">gru_param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><span class="p"><span class="pre">;</span></span><a class="headerlink" href="#c.fp_Gru_p" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<p><strong>C调用示例:</strong></p>
|
||
<div class="highlight-c notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="kt">void</span><span class="w"> </span><span class="nf">TestGruL2Fp32</span><span class="p">(</span><span class="kt">int</span><span class="w"> </span><span class="n">check_seq_len</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">seq_len</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">batch_size</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">input_size</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">bidirectional</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">hidden_size</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">core_mask</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
|
||
<span class="linenos"> 2</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">output</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10000000</span><span class="p">;</span><span class="w"> </span><span class="c1">// 私有存储版本地址设置在AM内</span>
|
||
<span class="linenos"> 3</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">input</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10004000</span><span class="p">;</span>
|
||
<span class="linenos"> 4</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">weight_g</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10008000</span><span class="p">;</span>
|
||
<span class="linenos"> 5</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">weight_r</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x1000C000</span><span class="p">;</span>
|
||
<span class="linenos"> 6</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">input_bias</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10010000</span><span class="p">;</span>
|
||
<span class="linenos"> 7</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">state_bias</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10014000</span><span class="p">;</span>
|
||
<span class="linenos"> 8</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">hidden_state</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10018000</span><span class="p">;</span>
|
||
<span class="linenos"> 9</span><span class="w"> </span><span class="kt">float</span><span class="o">**</span><span class="w"> </span><span class="n">buffer</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="o">**</span><span class="p">)</span><span class="mh">0x1001C000</span><span class="p">;</span>
|
||
<span class="linenos">10</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">output_hidden_state</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10020000</span><span class="p">;</span>
|
||
<span class="linenos">11</span><span class="w"> </span><span class="n">GruParameter</span><span class="o">*</span><span class="w"> </span><span class="n">param</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="n">GruParameter</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10024000</span><span class="p">;</span>
|
||
<span class="linenos">12</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">hidden_state_batch</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
|
||
<span class="linenos">13</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">num_directions</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
|
||
<span class="linenos">14</span><span class="w"> </span><span class="k">if</span><span class="w"> </span><span class="p">(</span><span class="n">bidirectional</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
|
||
<span class="linenos">15</span><span class="w"> </span><span class="n">hidden_state_batch</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">hidden_state_batch</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="mi">2</span><span class="p">;</span>
|
||
<span class="linenos">16</span><span class="w"> </span><span class="n">num_directions</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">num_directions</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="mi">2</span><span class="p">;</span>
|
||
<span class="linenos">17</span><span class="w"> </span><span class="p">}</span>
|
||
<span class="linenos">18</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">input_col_align</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">hidden_size</span><span class="p">;</span>
|
||
<span class="linenos">19</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">state_col_align</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">hidden_size</span><span class="p">;</span>
|
||
<span class="linenos">20</span><span class="w"> </span><span class="n">memcpy</span><span class="p">(</span><span class="n">output_hidden_state</span><span class="p">,</span><span class="w"> </span><span class="n">hidden_state</span><span class="p">,</span><span class="w"> </span><span class="n">hidden_state_batch</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">batch_size</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">hidden_size</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="k">sizeof</span><span class="p">(</span><span class="kt">float</span><span class="p">));</span>
|
||
<span class="linenos">21</span><span class="w"> </span><span class="n">memcpy</span><span class="p">(</span><span class="n">check_output_hidden_state</span><span class="p">,</span><span class="w"> </span><span class="n">hidden_state</span><span class="p">,</span><span class="w"> </span><span class="n">hidden_state_batch</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">batch_size</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">hidden_size</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="k">sizeof</span><span class="p">(</span><span class="kt">float</span><span class="p">));</span>
|
||
<span class="linenos">22</span><span class="w"> </span><span class="n">buffer</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10030000</span><span class="p">;</span>
|
||
<span class="linenos">23</span><span class="w"> </span><span class="n">buffer</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10034000</span><span class="p">;</span>
|
||
<span class="linenos">24</span><span class="w"> </span><span class="n">buffer</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10038000</span><span class="p">;</span>
|
||
<span class="linenos">25</span><span class="w"> </span><span class="n">buffer</span><span class="p">[</span><span class="mi">3</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)</span><span class="mh">0x1003C000</span><span class="p">;</span>
|
||
<span class="linenos">26</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">batch_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">batch_size</span><span class="p">;</span>
|
||
<span class="linenos">27</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">bidirectional_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">bidirectional</span><span class="p">;</span>
|
||
<span class="linenos">28</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">hidden_size_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">hidden_size</span><span class="p">;</span>
|
||
<span class="linenos">29</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">input_col_align_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">input_col_align</span><span class="p">;</span>
|
||
<span class="linenos">30</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">input_size_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">input_size</span><span class="p">;</span>
|
||
<span class="linenos">31</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">output_step_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">batch_size</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">hidden_size</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">num_directions</span><span class="p">;</span>
|
||
<span class="linenos">32</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">seq_len_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">seq_len</span><span class="p">;</span>
|
||
<span class="linenos">33</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">state_col_align_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">state_col_align</span><span class="p">;</span>
|
||
<span class="linenos">34</span><span class="w"> </span><span class="n">param</span><span class="o">-></span><span class="n">check_seq_len_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">check_seq_len</span><span class="p">;</span>
|
||
<span class="hll"><span class="linenos">35</span><span class="w"> </span><span class="n">fp_Gru_p</span><span class="p">(</span><span class="n">output</span><span class="p">,</span><span class="w"> </span><span class="n">input</span><span class="p">,</span><span class="w"> </span><span class="n">weight_g</span><span class="p">,</span><span class="w"> </span><span class="n">weight_r</span><span class="p">,</span><span class="w"> </span><span class="n">input_bias</span><span class="p">,</span><span class="w"> </span><span class="n">state_bias</span><span class="p">,</span><span class="w"> </span><span class="n">output_hidden_state</span><span class="p">,</span><span class="w"> </span><span class="n">buffer</span><span class="p">,</span><span class="w"> </span><span class="n">param</span><span class="p">,</span><span class="w"> </span><span class="n">core_mask</span><span class="p">);</span>
|
||
</span><span class="linenos">36</span><span class="p">}</span>
|
||
<span class="linenos">37</span>
|
||
<span class="linenos">38</span><span class="kt">void</span><span class="w"> </span><span class="nf">main</span><span class="p">()</span><span class="w"> </span><span class="p">{</span>
|
||
<span class="linenos">39</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">check_seq_len</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">2</span><span class="p">;</span>
|
||
<span class="linenos">40</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">seq_len</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">2</span><span class="p">;</span>
|
||
<span class="linenos">41</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">batch_size</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">2</span><span class="p">;</span>
|
||
<span class="linenos">42</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">input_size</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">2</span><span class="p">;</span>
|
||
<span class="linenos">43</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">bidirectional</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span>
|
||
<span class="linenos">44</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">hidden_size</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">2</span><span class="p">;</span>
|
||
<span class="linenos">45</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">core_mask</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mb">0b0001</span><span class="p">;</span><span class="w"> </span><span class="c1">// 私有存储版本只能设置为一个核心启动</span>
|
||
<span class="linenos">46</span><span class="w"> </span><span class="n">TestGruL2Fp32</span><span class="p">(</span><span class="n">check_seq_len</span><span class="p">,</span><span class="w"> </span><span class="n">seq_len</span><span class="p">,</span><span class="w"> </span><span class="n">batch_size</span><span class="p">,</span><span class="w"> </span><span class="n">input_size</span><span class="p">,</span><span class="w"> </span><span class="n">bidirectional</span><span class="p">,</span><span class="w"> </span><span class="n">hidden_size</span><span class="p">,</span><span class="w"> </span><span class="n">core_mask</span><span class="p">);</span>
|
||
<span class="linenos">47</span><span class="w"> </span><span class="k">return</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span>
|
||
<span class="linenos">48</span><span class="p">}</span>
|
||
</pre></div>
|
||
</div>
|
||
</section>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
<footer><div class="rst-footer-buttons" role="navigation" aria-label="页脚">
|
||
<a href="conv2d_transpose.html" class="btn btn-neutral float-left" title="Conv2dTranspose" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> 上一页</a>
|
||
<a href="assert.html" class="btn btn-neutral float-right" title="Assert" accesskey="n" rel="next">下一页 <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
|
||
</div>
|
||
|
||
<hr/>
|
||
|
||
<div role="contentinfo">
|
||
<p>© 版权所有 2025 - 2026, NUDT-674。</p>
|
||
</div>
|
||
|
||
利用 <a href="https://www.sphinx-doc.org/">Sphinx</a> 构建,使用的
|
||
<a href="https://github.com/readthedocs/sphinx_rtd_theme">主题</a>
|
||
由 <a href="https://readthedocs.org">Read the Docs</a> 开发.
|
||
|
||
|
||
</footer>
|
||
</div>
|
||
</div>
|
||
</section>
|
||
</div>
|
||
<script>
|
||
jQuery(function () {
|
||
SphinxRtdTheme.Navigation.enable(true);
|
||
});
|
||
</script>
|
||
|
||
</body>
|
||
</html> |