| <!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="Source of the Rust file `/root/.cargo/registry/src/github.com-1ecc6299db9ec823/matrixmultiply-0.1.15/src/sgemm_kernel.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>sgemm_kernel.rs - source</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceSerif4-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../FiraSans-Regular.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../FiraSans-Medium.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceCodePro-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceSerif4-Bold.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceCodePro-Semibold.ttf.woff2"><link rel="stylesheet" href="../../normalize.css"><link rel="stylesheet" href="../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" href="../../ayu.css" disabled><link rel="stylesheet" href="../../dark.css" disabled><link rel="stylesheet" href="../../light.css" id="themeStyle"><script id="default-settings" ></script><script src="../../storage.js"></script><script defer src="../../source-script.js"></script><script defer src="../../source-files.js"></script><script defer src="../../main.js"></script><noscript><link rel="stylesheet" href="../../noscript.css"></noscript><link rel="alternate icon" type="image/png" href="../../favicon-16x16.png"><link rel="alternate icon" type="image/png" href="../../favicon-32x32.png"><link rel="icon" type="image/svg+xml" href="../../favicon.svg"></head><body class="rustdoc source"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><a class="sidebar-logo" href="../../matrixmultiply/index.html"><div class="logo-container"><img class="rust-logo" src="../../rust-logo.svg" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../matrixmultiply/index.html"><img class="rust-logo" src="../../rust-logo.svg" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span> |
| <span id="2">2</span> |
| <span id="3">3</span> |
| <span id="4">4</span> |
| <span id="5">5</span> |
| <span id="6">6</span> |
| <span id="7">7</span> |
| <span id="8">8</span> |
| <span id="9">9</span> |
| <span id="10">10</span> |
| <span id="11">11</span> |
| <span id="12">12</span> |
| <span id="13">13</span> |
| <span id="14">14</span> |
| <span id="15">15</span> |
| <span id="16">16</span> |
| <span id="17">17</span> |
| <span id="18">18</span> |
| <span id="19">19</span> |
| <span id="20">20</span> |
| <span id="21">21</span> |
| <span id="22">22</span> |
| <span id="23">23</span> |
| <span id="24">24</span> |
| <span id="25">25</span> |
| <span id="26">26</span> |
| <span id="27">27</span> |
| <span id="28">28</span> |
| <span id="29">29</span> |
| <span id="30">30</span> |
| <span id="31">31</span> |
| <span id="32">32</span> |
| <span id="33">33</span> |
| <span id="34">34</span> |
| <span id="35">35</span> |
| <span id="36">36</span> |
| <span id="37">37</span> |
| <span id="38">38</span> |
| <span id="39">39</span> |
| <span id="40">40</span> |
| <span id="41">41</span> |
| <span id="42">42</span> |
| <span id="43">43</span> |
| <span id="44">44</span> |
| <span id="45">45</span> |
| <span id="46">46</span> |
| <span id="47">47</span> |
| <span id="48">48</span> |
| <span id="49">49</span> |
| <span id="50">50</span> |
| <span id="51">51</span> |
| <span id="52">52</span> |
| <span id="53">53</span> |
| <span id="54">54</span> |
| <span id="55">55</span> |
| <span id="56">56</span> |
| <span id="57">57</span> |
| <span id="58">58</span> |
| <span id="59">59</span> |
| <span id="60">60</span> |
| <span id="61">61</span> |
| <span id="62">62</span> |
| <span id="63">63</span> |
| <span id="64">64</span> |
| <span id="65">65</span> |
| <span id="66">66</span> |
| <span id="67">67</span> |
| <span id="68">68</span> |
| <span id="69">69</span> |
| <span id="70">70</span> |
| <span id="71">71</span> |
| <span id="72">72</span> |
| <span id="73">73</span> |
| <span id="74">74</span> |
| <span id="75">75</span> |
| <span id="76">76</span> |
| <span id="77">77</span> |
| <span id="78">78</span> |
| <span id="79">79</span> |
| <span id="80">80</span> |
| <span id="81">81</span> |
| <span id="82">82</span> |
| <span id="83">83</span> |
| <span id="84">84</span> |
| <span id="85">85</span> |
| <span id="86">86</span> |
| <span id="87">87</span> |
| <span id="88">88</span> |
| <span id="89">89</span> |
| <span id="90">90</span> |
| <span id="91">91</span> |
| <span id="92">92</span> |
| <span id="93">93</span> |
| <span id="94">94</span> |
| <span id="95">95</span> |
| <span id="96">96</span> |
| <span id="97">97</span> |
| <span id="98">98</span> |
| <span id="99">99</span> |
| <span id="100">100</span> |
| <span id="101">101</span> |
| <span id="102">102</span> |
| <span id="103">103</span> |
| <span id="104">104</span> |
| <span id="105">105</span> |
| <span id="106">106</span> |
| <span id="107">107</span> |
| <span id="108">108</span> |
| <span id="109">109</span> |
| <span id="110">110</span> |
| <span id="111">111</span> |
| <span id="112">112</span> |
| <span id="113">113</span> |
| <span id="114">114</span> |
| <span id="115">115</span> |
| <span id="116">116</span> |
| <span id="117">117</span> |
| <span id="118">118</span> |
| <span id="119">119</span> |
| <span id="120">120</span> |
| <span id="121">121</span> |
| </pre><pre class="rust"><code><span class="comment">// Copyright 2016 bluss |
| // |
| // Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or |
| // http://www.apache.org/licenses/LICENSE-2.0> or the MIT license |
| // <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your |
| // option. This file may not be copied, modified, or distributed |
| // except according to those terms. |
| |
| </span><span class="kw">use </span>kernel::GemmKernel; |
| <span class="kw">use </span>archparam; |
| |
| <span class="kw">pub enum </span>Gemm { } |
| |
| <span class="kw">pub type </span>T = f32; |
| |
| <span class="kw">const </span>MR: usize = <span class="macro">if_cfg!</span>(sgemm_8x8, usize, <span class="number">8</span>, <span class="number">4</span>); |
| <span class="kw">const </span>NR: usize = <span class="number">8</span>; |
| |
| <span class="attribute">#[cfg(sgemm_8x8)] |
| </span><span class="macro">macro_rules! </span>loop_m { (<span class="macro-nonterminal">$i</span>:ident, <span class="macro-nonterminal">$e</span>:expr) => { <span class="macro">loop8!</span>(<span class="macro-nonterminal">$i</span>, <span class="macro-nonterminal">$e</span>) }; } |
| <span class="attribute">#[cfg(not(sgemm_8x8))] |
| </span><span class="macro">macro_rules! </span>loop_m { (<span class="macro-nonterminal">$i</span>:ident, <span class="macro-nonterminal">$e</span>:expr) => { <span class="macro">loop4!</span>(<span class="macro-nonterminal">$i</span>, <span class="macro-nonterminal">$e</span>) }; } |
| |
| <span class="macro">macro_rules! </span>loop_n { (<span class="macro-nonterminal">$j</span>:ident, <span class="macro-nonterminal">$e</span>:expr) => { <span class="macro">loop8!</span>(<span class="macro-nonterminal">$j</span>, <span class="macro-nonterminal">$e</span>) }; } |
| |
| <span class="kw">impl </span>GemmKernel <span class="kw">for </span>Gemm { |
| <span class="kw">type </span>Elem = T; |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>align_to() -> usize { <span class="number">0 </span>} |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>mr() -> usize { MR } |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>nr() -> usize { NR } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>always_masked() -> bool { <span class="bool-val">true </span>} |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>nc() -> usize { archparam::S_NC } |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>kc() -> usize { archparam::S_KC } |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>mc() -> usize { archparam::S_MC } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">unsafe fn </span>kernel( |
| k: usize, |
| alpha: T, |
| a: <span class="kw-2">*const </span>T, |
| b: <span class="kw-2">*const </span>T, |
| beta: T, |
| c: <span class="kw-2">*mut </span>T, rsc: isize, csc: isize) { |
| kernel(k, alpha, a, b, beta, c, rsc, csc) |
| } |
| } |
| |
| <span class="doccomment">/// matrix multiplication kernel |
| /// |
| /// This does the matrix multiplication: |
| /// |
| /// C ← α A B + β C |
| /// |
| /// + k: length of data in a, b |
| /// + a, b are packed |
| /// + c has general strides |
| /// + rsc: row stride of c |
| /// + csc: col stride of c |
| /// + if beta is 0, then c does not need to be initialized |
| </span><span class="attribute">#[inline(always)] |
| </span><span class="kw">pub unsafe fn </span>kernel(k: usize, alpha: T, a: <span class="kw-2">*const </span>T, b: <span class="kw-2">*const </span>T, |
| beta: T, c: <span class="kw-2">*mut </span>T, rsc: isize, csc: isize) |
| { |
| <span class="comment">// using `uninitialized` is a workaround for issue https://github.com/bluss/matrixmultiply/issues/9 |
| </span><span class="kw">let </span><span class="kw-2">mut </span>ab: [[T; NR]; MR] = ::std::mem::uninitialized(); |
| <span class="kw">let </span><span class="kw-2">mut </span>a = a; |
| <span class="kw">let </span><span class="kw-2">mut </span>b = b; |
| <span class="macro">debug_assert_eq!</span>(beta, <span class="number">0.</span>); <span class="comment">// always masked |
| </span><span class="macro">loop_m!</span>(i, <span class="macro">loop_n!</span>(j, ab[i][j] = <span class="number">0.</span>)); |
| |
| <span class="comment">// Compute matrix multiplication into ab[i][j] |
| </span><span class="macro">unroll_by!</span>(<span class="number">5 </span>=> k, { |
| <span class="macro">loop_m!</span>(i, <span class="macro">loop_n!</span>(j, ab[i][j] += at(a, i) * at(b, j))); |
| |
| a = a.offset(MR <span class="kw">as </span>isize); |
| b = b.offset(NR <span class="kw">as </span>isize); |
| }); |
| |
| <span class="macro">macro_rules! </span>c { |
| (<span class="macro-nonterminal">$i</span>:expr, <span class="macro-nonterminal">$j</span>:expr) => (c.offset(rsc * <span class="macro-nonterminal">$i </span><span class="kw">as </span>isize + csc * <span class="macro-nonterminal">$j </span><span class="kw">as </span>isize)); |
| } |
| |
| <span class="comment">// set C = α A B |
| </span><span class="macro">loop_n!</span>(j, <span class="macro">loop_m!</span>(i, <span class="kw-2">*</span><span class="macro">c!</span>[i, j] = alpha * ab[i][j])); |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">unsafe fn </span>at(ptr: <span class="kw-2">*const </span>T, i: usize) -> T { |
| <span class="kw-2">*</span>ptr.offset(i <span class="kw">as </span>isize) |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_gemm_kernel() { |
| <span class="kw">let </span><span class="kw-2">mut </span>a = [<span class="number">1.</span>; <span class="number">16</span>]; |
| <span class="kw">let </span><span class="kw-2">mut </span>b = [<span class="number">0.</span>; <span class="number">32</span>]; |
| <span class="kw">for </span>(i, x) <span class="kw">in </span>a.iter_mut().enumerate() { |
| <span class="kw-2">*</span>x = i <span class="kw">as </span>f32; |
| } |
| |
| <span class="kw">for </span>i <span class="kw">in </span><span class="number">0</span>..<span class="number">4 </span>{ |
| b[i + i * <span class="number">8</span>] = <span class="number">1.</span>; |
| } |
| <span class="kw">let </span><span class="kw-2">mut </span>c = [<span class="number">0.</span>; <span class="number">32</span>]; |
| <span class="kw">unsafe </span>{ |
| kernel(<span class="number">4</span>, <span class="number">1.</span>, <span class="kw-2">&</span>a[<span class="number">0</span>], <span class="kw-2">&</span>b[<span class="number">0</span>], <span class="number">0.</span>, <span class="kw-2">&mut </span>c[<span class="number">0</span>], <span class="number">1</span>, <span class="number">4</span>); |
| <span class="comment">// col major C |
| </span>} |
| <span class="macro">assert_eq!</span>(<span class="kw-2">&</span>a, <span class="kw-2">&</span>c[..<span class="number">16</span>]); |
| } |
| |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="matrixmultiply" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |