FT_DSP.gitlink.net/master/html/functionlib/dsplib/matmulfusion.html

300 lines
43 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!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>MatMulFusion &mdash; 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="Attention" href="attention.html" />
<link rel="prev" title="LinSpace" href="linspace.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 class="current">
<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 current"><a class="reference internal" href="../index.html">算子库支持</a><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../supported_op.html">算子库支持情况</a></li>
<li class="toctree-l2"><a class="reference internal" href="../custom_op/index.html">自定义算子列表</a></li>
<li class="toctree-l2 current"><a class="reference internal" href="dsplib_index.html">DSP Library C API Reference</a><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="equal.html">Equal</a></li>
<li class="toctree-l3"><a class="reference internal" href="activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="expfusion.html">ExpFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="reverse_sequence.html">ReverseSequence</a></li>
<li class="toctree-l3"><a class="reference internal" href="reversev2.html">ReverseV2</a></li>
<li class="toctree-l3"><a class="reference internal" href="fillv2.html">FillV2</a></li>
<li class="toctree-l3"><a class="reference internal" href="squeeze.html">Squeeze</a></li>
<li class="toctree-l3"><a class="reference internal" href="unsqueeze.html">UnSqueeze</a></li>
<li class="toctree-l3"><a class="reference internal" href="expand_dims.html">ExpandDims</a></li>
<li class="toctree-l3"><a class="reference internal" href="leaky_relu.html">LeakyReLu</a></li>
<li class="toctree-l3"><a class="reference internal" href="lstm.html">LSTM</a></li>
<li class="toctree-l3"><a class="reference internal" href="scatter_elements.html">ScatterElements</a></li>
<li class="toctree-l3"><a class="reference internal" href="reduce.html">Reduce</a></li>
<li class="toctree-l3"><a class="reference internal" href="resize.html">Resize</a></li>
<li class="toctree-l3"><a class="reference internal" href="crop_and_resize.html">CropAndResize</a></li>
<li class="toctree-l3"><a class="reference internal" href="crop.html">Crop</a></li>
<li class="toctree-l3"><a class="reference internal" href="conv2d.html">Conv2d</a></li>
<li class="toctree-l3"><a class="reference internal" href="adder.html">Adder</a></li>
<li class="toctree-l3"><a class="reference internal" href="conv2d_transpose.html">Conv2dTranspose</a></li>
<li class="toctree-l3"><a class="reference internal" href="gru.html">GRU</a></li>
<li class="toctree-l3"><a class="reference internal" href="assert.html">Assert</a></li>
<li class="toctree-l3"><a class="reference internal" href="range.html">Range</a></li>
<li class="toctree-l3"><a class="reference internal" href="raggedrange.html">RaggedRange</a></li>
<li class="toctree-l3"><a class="reference internal" href="linspace.html">LinSpace</a></li>
<li class="toctree-l3 current"><a class="current reference internal" href="#">MatMulFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="attention.html">Attention</a></li>
<li class="toctree-l3"><a class="reference internal" href="floor.html">Floor</a></li>
<li class="toctree-l3"><a class="reference internal" href="floordiv.html">FloorDiv</a></li>
<li class="toctree-l3"><a class="reference internal" href="embeddinglookup.html">EmbeddingLookup</a></li>
<li class="toctree-l3"><a class="reference internal" href="eltwise.html">Eltwise</a></li>
<li class="toctree-l3"><a class="reference internal" href="adamweightdecay.html">AdamWeightDecay</a></li>
<li class="toctree-l3"><a class="reference internal" href="applymomentum.html">ApplyMomentum</a></li>
<li class="toctree-l3"><a class="reference internal" href="avgpoolinggrad.html">AvgPoolingGrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="batchtospace.html">BatchToSpace</a></li>
<li class="toctree-l3"><a class="reference internal" href="batchtospacend.html">BatchToSpaceND</a></li>
<li class="toctree-l3"><a class="reference internal" href="broadcastto.html">BroadcastTo</a></li>
<li class="toctree-l3"><a class="reference internal" href="depthtospace.html">DepthToSpace</a></li>
<li class="toctree-l3"><a class="reference internal" href="spacetodepth.html">SpaceToDepth</a></li>
<li class="toctree-l3"><a class="reference internal" href="spacetobatch.html">SpaceToBatch</a></li>
<li class="toctree-l3"><a class="reference internal" href="spacetobatchnd.html">SpaceToBatchND</a></li>
<li class="toctree-l3"><a class="reference internal" href="fusedbatchnorm.html">FusedBatchNorm</a></li>
<li class="toctree-l3"><a class="reference internal" href="groupnormfusion.html">GroupNormFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="conv2dbackpropinputfusion.html">Conv2DBackpropInputFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="conv2dbackpropfilterfusion.html">Conv2DBackpropFilterFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="sgd.html">SGD</a></li>
<li class="toctree-l3"><a class="reference internal" href="scalefusion.html">ScaleFusion</a></li>
</ul>
</li>
</ul>
</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">MatMulFusion</li>
<li class="wy-breadcrumbs-aside">
<a href="../../_sources/functionlib/dsplib/matmulfusion.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="matmulfusion">
<h1>MatMulFusion<a class="headerlink" href="#matmulfusion" title="Link to this heading"></a></h1>
<p>矩阵乘法融合(可选偏置和激活),计算:</p>
<div class="math notranslate nohighlight">
\[C = \operatorname{act}(A \times B + \text{bias})\]</div>
<p>其中 <code class="docutils literal notranslate"><span class="pre">A</span></code> 形状为 <span class="math notranslate nohighlight">\(M\times K\)</span><code class="docutils literal notranslate"><span class="pre">B</span></code><span class="math notranslate nohighlight">\(K\times N\)</span><code class="docutils literal notranslate"><span class="pre">C</span></code> 与可选的 <code class="docutils literal notranslate"><span class="pre">bias</span></code><span class="math notranslate nohighlight">\(M\times N\)</span>
激活 <code class="docutils literal notranslate"><span class="pre">act</span></code> 支持:</p>
<ul class="simple">
<li><p><code class="docutils literal notranslate"><span class="pre">0</span></code>: 无激活Identity</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">1</span></code>: ReLU</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">2</span></code>: ReLU6</p></li>
</ul>
<dl class="simple">
<dt>输入:</dt><dd><ul class="simple">
<li><p><strong>A</strong> - 输入矩阵 A行优先连续存储。大小 M×K。</p></li>
<li><p><strong>B</strong> - 输入矩阵 B行优先连续存储。大小 K×N。</p></li>
<li><p><strong>bias</strong> - 偏置矩阵(可为 NULL大小 M×N</p></li>
<li><p><strong>M, N, K</strong> - 维度参数。</p></li>
<li><p><strong>activation_type</strong> - 激活类型,取值 {0,1,2}。</p></li>
<li><p><strong>core_mask可选</strong> - 核掩码(仅适用于共享存储版本)。</p></li>
</ul>
</dd>
<dt>输出:</dt><dd><ul class="simple">
<li><p><strong>C</strong> - 输出矩阵(行优先,大小 M×N</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>复数类型的激活逐分量应用于实部与虚部。</p></li>
<li><p>请确保输入按行优先连续布局且不发生类型范围溢出int16/int32 计算未做饱和裁剪。</p></li>
<li><p>共享存储版本要求地址位于 GSM/DDR/SMC 等共享可见空间。</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.i16_matmulfusion_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">i16_matmulfusion_s</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">int16_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">A</span></span>, <span class="n"><span class="pre">int16_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">B</span></span>, <span class="n"><span class="pre">int16_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">C</span></span>, <span class="n"><span class="pre">int16_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">bias</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">M</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">N</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">K</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">activation_type</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.i16_matmulfusion_s" title="Link to this definition"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.i32_matmulfusion_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">i32_matmulfusion_s</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">int32_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">A</span></span>, <span class="n"><span class="pre">int32_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">B</span></span>, <span class="n"><span class="pre">int32_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">C</span></span>, <span class="n"><span class="pre">int32_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">bias</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">M</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">N</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">K</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">activation_type</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.i32_matmulfusion_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_matmulfusion_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_matmulfusion_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">A</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">B</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">C</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">bias</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">M</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">N</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">K</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">activation_type</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.fp_matmulfusion_s" title="Link to this definition"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.dp_matmulfusion_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">dp_matmulfusion_s</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">A</span></span>, <span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">B</span></span>, <span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">C</span></span>, <span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">bias</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">M</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">N</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">K</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">activation_type</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.dp_matmulfusion_s" title="Link to this definition"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.c64_matmulfusion_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">c64_matmulfusion_s</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">A</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">B</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">C</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">bias</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">M</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">N</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">K</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">activation_type</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.c64_matmulfusion_s" title="Link to this definition"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.c128_matmulfusion_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">c128_matmulfusion_s</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">A</span></span>, <span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">B</span></span>, <span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">C</span></span>, <span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">bias</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">M</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">N</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">K</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">activation_type</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.c128_matmulfusion_s" title="Link to this definition"></a><br /></dt>
<dd><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="cp">#include</span><span class="w"> </span><span class="cpf">&lt;stdio.h&gt;</span>
<span class="linenos"> 2</span><span class="cp">#include</span><span class="w"> </span><span class="cpf">&lt;stdbool.h&gt;</span>
<span class="linenos"> 3</span>
<span class="linenos"> 4</span><span class="kt">int</span><span class="w"> </span><span class="nf">main</span><span class="p">(</span><span class="kt">int</span><span class="w"> </span><span class="n">argc</span><span class="p">,</span><span class="w"> </span><span class="kt">char</span><span class="o">*</span><span class="w"> </span><span class="n">argv</span><span class="p">[])</span><span class="w"> </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">A</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0xA0000000</span><span class="p">;</span><span class="w"> </span><span class="c1">// DDR</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">B</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0xA1000000</span><span class="p">;</span><span class="w"> </span><span class="c1">// DDR</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">C</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0xA2000000</span><span class="p">;</span><span class="w"> </span><span class="c1">// DDR</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">bias</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0xA3000000</span><span class="p">;</span><span class="w"> </span><span class="c1">// DDR可为 NULL</span>
<span class="linenos"> 9</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">M</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">512</span><span class="p">,</span><span class="w"> </span><span class="n">N</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">512</span><span class="p">,</span><span class="w"> </span><span class="n">K</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">512</span><span class="p">;</span>
<span class="linenos">10</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">activation_type</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span><span class="w"> </span><span class="c1">// ReLU</span>
<span class="linenos">11</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="mh">0xff</span><span class="p">;</span><span class="w"> </span><span class="c1">// 8 核</span>
<span class="hll"><span class="linenos">12</span><span class="w"> </span><span class="n">fp_matmulfusion_s</span><span class="p">(</span><span class="n">A</span><span class="p">,</span><span class="w"> </span><span class="n">B</span><span class="p">,</span><span class="w"> </span><span class="n">C</span><span class="p">,</span><span class="w"> </span><span class="n">bias</span><span class="p">,</span><span class="w"> </span><span class="n">M</span><span class="p">,</span><span class="w"> </span><span class="n">N</span><span class="p">,</span><span class="w"> </span><span class="n">K</span><span class="p">,</span><span class="w"> </span><span class="n">activation_type</span><span class="p">,</span><span class="w"> </span><span class="n">core_mask</span><span class="p">);</span>
</span><span class="linenos">13</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">14</span><span class="p">}</span>
</pre></div>
</div>
</dd></dl>
<p><strong>私有存储版本:</strong></p>
<dl class="c function">
<dt class="sig sig-object c" id="c.i16_matmulfusion_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">i16_matmulfusion_p</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">int16_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">A</span></span>, <span class="n"><span class="pre">int16_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">B</span></span>, <span class="n"><span class="pre">int16_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">C</span></span>, <span class="n"><span class="pre">int16_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">bias</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">M</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">N</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">K</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">activation_type</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.i16_matmulfusion_p" title="Link to this definition"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.i32_matmulfusion_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">i32_matmulfusion_p</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">int32_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">A</span></span>, <span class="n"><span class="pre">int32_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">B</span></span>, <span class="n"><span class="pre">int32_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">C</span></span>, <span class="n"><span class="pre">int32_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">bias</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">M</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">N</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">K</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">activation_type</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.i32_matmulfusion_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_matmulfusion_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_matmulfusion_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">A</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">B</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">C</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">bias</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">M</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">N</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">K</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">activation_type</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.fp_matmulfusion_p" title="Link to this definition"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.dp_matmulfusion_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">dp_matmulfusion_p</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">A</span></span>, <span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">B</span></span>, <span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">C</span></span>, <span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">bias</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">M</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">N</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">K</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">activation_type</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.dp_matmulfusion_p" title="Link to this definition"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.c64_matmulfusion_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">c64_matmulfusion_p</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">A</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">B</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">C</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">bias</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">M</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">N</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">K</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">activation_type</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.c64_matmulfusion_p" title="Link to this definition"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.c128_matmulfusion_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">c128_matmulfusion_p</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">A</span></span>, <span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">B</span></span>, <span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">C</span></span>, <span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="kt"><span class="pre">complex</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">bias</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">M</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">N</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">K</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">activation_type</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.c128_matmulfusion_p" title="Link to this definition"></a><br /></dt>
<dd><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="cp">#include</span><span class="w"> </span><span class="cpf">&lt;stdio.h&gt;</span>
<span class="linenos"> 2</span>
<span class="linenos"> 3</span><span class="kt">int</span><span class="w"> </span><span class="nf">main</span><span class="p">(</span><span class="kt">int</span><span class="w"> </span><span class="n">argc</span><span class="p">,</span><span class="w"> </span><span class="kt">char</span><span class="o">*</span><span class="w"> </span><span class="n">argv</span><span class="p">[])</span><span class="w"> </span><span class="p">{</span>
<span class="linenos"> 4</span><span class="w"> </span><span class="kt">double</span><span class="w"> </span><span class="o">*</span><span class="n">A</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">double</span><span class="w"> </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">// L2</span>
<span class="linenos"> 5</span><span class="w"> </span><span class="kt">double</span><span class="w"> </span><span class="o">*</span><span class="n">B</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">double</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0x10020000</span><span class="p">;</span><span class="w"> </span><span class="c1">// L2</span>
<span class="linenos"> 6</span><span class="w"> </span><span class="kt">double</span><span class="w"> </span><span class="o">*</span><span class="n">C</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">double</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0x10040000</span><span class="p">;</span><span class="w"> </span><span class="c1">// L2/DDR</span>
<span class="linenos"> 7</span><span class="w"> </span><span class="kt">double</span><span class="w"> </span><span class="o">*</span><span class="n">bias</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="nb">NULL</span><span class="p">;</span><span class="w"> </span><span class="c1">// 可为 NULL</span>
<span class="linenos"> 8</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">M</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">128</span><span class="p">,</span><span class="w"> </span><span class="n">N</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">128</span><span class="p">,</span><span class="w"> </span><span class="n">K</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">128</span><span class="p">;</span>
<span class="linenos"> 9</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">activation_type</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="c1">// None</span>
<span class="hll"><span class="linenos">10</span><span class="w"> </span><span class="n">dp_matmulfusion_p</span><span class="p">(</span><span class="n">A</span><span class="p">,</span><span class="w"> </span><span class="n">B</span><span class="p">,</span><span class="w"> </span><span class="n">C</span><span class="p">,</span><span class="w"> </span><span class="n">bias</span><span class="p">,</span><span class="w"> </span><span class="n">M</span><span class="p">,</span><span class="w"> </span><span class="n">N</span><span class="p">,</span><span class="w"> </span><span class="n">K</span><span class="p">,</span><span class="w"> </span><span class="n">activation_type</span><span class="p">);</span>
</span><span class="linenos">11</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">12</span><span class="p">}</span>
</pre></div>
</div>
</dd></dl>
</section>
</div>
</div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="页脚">
<a href="linspace.html" class="btn btn-neutral float-left" title="LinSpace" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> 上一页</a>
<a href="attention.html" class="btn btn-neutral float-right" title="Attention" 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>&#169; 版权所有 2025 - 2025, 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>
<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>