1173 lines
56 KiB
HTML
1173 lines
56 KiB
HTML
|
|
<!doctype html>
|
|
<html lang="en" class="no-js">
|
|
<head>
|
|
|
|
<meta charset="utf-8">
|
|
<meta name="viewport" content="width=device-width,initial-scale=1">
|
|
|
|
|
|
|
|
<link rel="canonical" href="https://openblas.net/docs/user_manual/">
|
|
|
|
|
|
<link rel="prev" href="../install/">
|
|
|
|
|
|
<link rel="next" href="../extensions/">
|
|
|
|
|
|
<link rel="icon" href="../logo.svg">
|
|
<meta name="generator" content="mkdocs-1.6.0, mkdocs-material-9.5.30">
|
|
|
|
|
|
|
|
<title>User manual - OpenBLAS</title>
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../assets/stylesheets/main.3cba04c6.min.css">
|
|
|
|
|
|
<link rel="stylesheet" href="../assets/stylesheets/palette.06af60db.min.css">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
|
|
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
|
|
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
|
|
|
|
|
|
|
|
<script>__md_scope=new URL("..",location),__md_hash=e=>[...e].reduce((e,_)=>(e<<5)-e+_.charCodeAt(0),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
</head>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<body dir="ltr" data-md-color-scheme="slate" data-md-color-primary="blue-grey" data-md-color-accent="indigo">
|
|
|
|
|
|
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
|
|
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
|
|
<label class="md-overlay" for="__drawer"></label>
|
|
<div data-md-component="skip">
|
|
|
|
|
|
<a href="#compiling-openblas" class="md-skip">
|
|
Skip to content
|
|
</a>
|
|
|
|
</div>
|
|
<div data-md-component="announce">
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<header class="md-header md-header--shadow" data-md-component="header">
|
|
<nav class="md-header__inner md-grid" aria-label="Header">
|
|
<a href=".." title="OpenBLAS" class="md-header__button md-logo" aria-label="OpenBLAS" data-md-component="logo">
|
|
|
|
<img src="../logo.svg" alt="logo">
|
|
|
|
</a>
|
|
<label class="md-header__button md-icon" for="__drawer">
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3V6m0 5h18v2H3v-2m0 5h18v2H3v-2Z"/></svg>
|
|
</label>
|
|
<div class="md-header__title" data-md-component="header-title">
|
|
<div class="md-header__ellipsis">
|
|
<div class="md-header__topic">
|
|
<span class="md-ellipsis">
|
|
OpenBLAS
|
|
</span>
|
|
</div>
|
|
<div class="md-header__topic" data-md-component="header-topic">
|
|
<span class="md-ellipsis">
|
|
|
|
User manual
|
|
|
|
</span>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
|
|
<form class="md-header__option" data-md-component="palette">
|
|
|
|
|
|
|
|
|
|
<input class="md-option" data-md-color-media="" data-md-color-scheme="slate" data-md-color-primary="blue-grey" data-md-color-accent="indigo" aria-label="Switch to light mode" type="radio" name="__palette" id="__palette_0">
|
|
|
|
<label class="md-header__button md-icon" title="Switch to light mode" for="__palette_1" hidden>
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 18c-.89 0-1.74-.2-2.5-.55C11.56 16.5 13 14.42 13 12c0-2.42-1.44-4.5-3.5-5.45C10.26 6.2 11.11 6 12 6a6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12 20 8.69Z"/></svg>
|
|
</label>
|
|
|
|
|
|
|
|
|
|
|
|
<input class="md-option" data-md-color-media="" data-md-color-scheme="default" data-md-color-primary="blue-grey" data-md-color-accent="indigo" aria-label="Switch to dark mode" type="radio" name="__palette" id="__palette_1">
|
|
|
|
<label class="md-header__button md-icon" title="Switch to dark mode" for="__palette_0" hidden>
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a4 4 0 0 0-4 4 4 4 0 0 0 4 4 4 4 0 0 0 4-4 4 4 0 0 0-4-4m0 10a6 6 0 0 1-6-6 6 6 0 0 1 6-6 6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12 20 8.69Z"/></svg>
|
|
</label>
|
|
|
|
|
|
</form>
|
|
|
|
|
|
|
|
<script>var media,input,key,value,palette=__md_get("__palette");if(palette&&palette.color){"(prefers-color-scheme)"===palette.color.media&&(media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']"),palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent"));for([key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
|
|
|
|
|
|
|
|
<label class="md-header__button md-icon" for="__search">
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
|
|
</label>
|
|
<div class="md-search" data-md-component="search" role="dialog">
|
|
<label class="md-search__overlay" for="__search"></label>
|
|
<div class="md-search__inner" role="search">
|
|
<form class="md-search__form" name="search">
|
|
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
|
|
<label class="md-search__icon md-icon" for="__search">
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12Z"/></svg>
|
|
</label>
|
|
<nav class="md-search__options" aria-label="Search">
|
|
|
|
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41Z"/></svg>
|
|
</button>
|
|
</nav>
|
|
|
|
</form>
|
|
<div class="md-search__output">
|
|
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
|
|
<div class="md-search-result" data-md-component="search-result">
|
|
<div class="md-search-result__meta">
|
|
Initializing search
|
|
</div>
|
|
<ol class="md-search-result__list" role="presentation"></ol>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
|
|
<div class="md-header__source">
|
|
<a href="https://github.com/OpenMathLib/OpenBLAS" title="Go to repository" class="md-source" data-md-component="source">
|
|
<div class="md-source__icon md-icon">
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.6.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z"/></svg>
|
|
</div>
|
|
<div class="md-source__repository">
|
|
GitHub
|
|
</div>
|
|
</a>
|
|
</div>
|
|
|
|
</nav>
|
|
|
|
</header>
|
|
|
|
<div class="md-container" data-md-component="container">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<main class="md-main" data-md-component="main">
|
|
<div class="md-main__inner md-grid">
|
|
|
|
|
|
|
|
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
|
|
<div class="md-sidebar__scrollwrap">
|
|
<div class="md-sidebar__inner">
|
|
|
|
|
|
|
|
|
|
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
|
<label class="md-nav__title" for="__drawer">
|
|
<a href=".." title="OpenBLAS" class="md-nav__button md-logo" aria-label="OpenBLAS" data-md-component="logo">
|
|
|
|
<img src="../logo.svg" alt="logo">
|
|
|
|
</a>
|
|
OpenBLAS
|
|
</label>
|
|
|
|
<div class="md-nav__source">
|
|
<a href="https://github.com/OpenMathLib/OpenBLAS" title="Go to repository" class="md-source" data-md-component="source">
|
|
<div class="md-source__icon md-icon">
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.6.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z"/></svg>
|
|
</div>
|
|
<div class="md-source__repository">
|
|
GitHub
|
|
</div>
|
|
</a>
|
|
</div>
|
|
|
|
<ul class="md-nav__list" data-md-scrollfix>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href=".." class="md-nav__link">
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
Home
|
|
</span>
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../install/" class="md-nav__link">
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
Install OpenBLAS
|
|
</span>
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item md-nav__item--active">
|
|
|
|
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
|
|
|
|
|
|
|
|
<label class="md-nav__link md-nav__link--active" for="__toc">
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
User manual
|
|
</span>
|
|
|
|
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<a href="./" class="md-nav__link md-nav__link--active">
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
User manual
|
|
</span>
|
|
|
|
|
|
</a>
|
|
|
|
|
|
|
|
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
|
|
|
|
|
|
|
|
|
|
<label class="md-nav__title" for="__toc">
|
|
<span class="md-nav__icon md-icon"></span>
|
|
Table of contents
|
|
</label>
|
|
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#compiling-openblas" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Compiling OpenBLAS
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Compiling OpenBLAS">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#normal-compile" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Normal compile
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#cross-compile" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Cross compile
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Cross compile">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#cross-compilation-examples" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Cross-compilation examples
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#building-a-debug-version" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Building a debug version
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#install-to-a-specific-directory" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Install to a specific directory
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#linking-to-openblas" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Linking to OpenBLAS
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Linking to OpenBLAS">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#link-a-shared-library" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Link a shared library
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#link-a-static-library" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Link a static library
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#code-examples" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Code examples
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Code examples">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#call-cblas-interface" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Call CBLAS interface
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#call-blas-fortran-interface" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Call BLAS Fortran interface
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#troubleshooting" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Troubleshooting
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../extensions/" class="md-nav__link">
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
Extensions
|
|
</span>
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../developers/" class="md-nav__link">
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
Developer manual
|
|
</span>
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../build_system/" class="md-nav__link">
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
Build system
|
|
</span>
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../distributing/" class="md-nav__link">
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
Redistributing OpenBLAS
|
|
</span>
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../ci/" class="md-nav__link">
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
CI jobs
|
|
</span>
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../about/" class="md-nav__link">
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
About
|
|
</span>
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../faq/" class="md-nav__link">
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
FAQ
|
|
</span>
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
</ul>
|
|
</nav>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
|
|
|
|
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
|
|
<div class="md-sidebar__scrollwrap">
|
|
<div class="md-sidebar__inner">
|
|
|
|
|
|
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
|
|
|
|
|
|
|
|
|
|
<label class="md-nav__title" for="__toc">
|
|
<span class="md-nav__icon md-icon"></span>
|
|
Table of contents
|
|
</label>
|
|
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#compiling-openblas" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Compiling OpenBLAS
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Compiling OpenBLAS">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#normal-compile" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Normal compile
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#cross-compile" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Cross compile
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Cross compile">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#cross-compilation-examples" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Cross-compilation examples
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#building-a-debug-version" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Building a debug version
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#install-to-a-specific-directory" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Install to a specific directory
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#linking-to-openblas" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Linking to OpenBLAS
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Linking to OpenBLAS">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#link-a-shared-library" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Link a shared library
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#link-a-static-library" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Link a static library
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#code-examples" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Code examples
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Code examples">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#call-cblas-interface" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Call CBLAS interface
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#call-blas-fortran-interface" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Call BLAS Fortran interface
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#troubleshooting" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
Troubleshooting
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
|
|
</nav>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
|
|
|
|
<div class="md-content" data-md-component="content">
|
|
<article class="md-content__inner md-typeset">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<h1>User manual</h1>
|
|
|
|
<p>This user manual covers compiling OpenBLAS itself, linking your code to OpenBLAS,
|
|
example code to use the C (CBLAS) and Fortran (BLAS) APIs, and some troubleshooting
|
|
tips. Compiling OpenBLAS is optional, since you may be able to install with a
|
|
package manager.</p>
|
|
<div class="admonition note blas api reference documentation">
|
|
<p class="admonition-title">Note</p>
|
|
<p>The OpenBLAS documentation does not contain API reference documentation for
|
|
BLAS or LAPACK, since these are standardized APIs, the documentation for
|
|
which can be found in other places. If you want to understand every BLAS
|
|
and LAPACK function and definition, we recommend reading the
|
|
<a href="http://netlib.org/blas/">Netlib BLAS </a> and <a href="http://netlib.org/lapack/">Netlib LAPACK</a>
|
|
documentation.</p>
|
|
<p>OpenBLAS does contain a limited number of functions that are non-standard,
|
|
these are documented at <a href="../extensions/">OpenBLAS extension functions</a>.</p>
|
|
</div>
|
|
<h2 id="compiling-openblas">Compiling OpenBLAS</h2>
|
|
<h3 id="normal-compile">Normal compile</h3>
|
|
<p>The default way to build and install OpenBLAS from source is with Make:
|
|
<div class="highlight"><pre><span></span><code>make # add `-j4` to compile in parallel with 4 processes
|
|
make install
|
|
</code></pre></div></p>
|
|
<p>By default, the CPU architecture is detected automatically when invoking
|
|
<code>make</code>, and the build is optimized for the detected CPU. To override the
|
|
autodetection, use the <code>TARGET</code> flag:</p>
|
|
<p><div class="highlight"><pre><span></span><code># `make TARGET=xxx` sets target CPU: e.g. for an Intel Nehalem CPU:
|
|
make TARGET=NEHALEM
|
|
</code></pre></div>
|
|
The full list of known target CPU architectures can be found in
|
|
<code>TargetList.txt</code> in the root of the repository.</p>
|
|
<h3 id="cross-compile">Cross compile</h3>
|
|
<p>For a basic cross-compilation with Make, three steps need to be taken:</p>
|
|
<ul>
|
|
<li>Set the <code>CC</code> and <code>FC</code> environment variables to select the cross toolchains
|
|
for C and Fortran.</li>
|
|
<li>Set the <code>HOSTCC</code> environment variable to select the host C compiler (i.e. the
|
|
regular C compiler for the machine on which you are invoking the build).</li>
|
|
<li>Set <code>TARGET</code> explicitly to the CPU architecture on which the produced
|
|
OpenBLAS binaries will be used.</li>
|
|
</ul>
|
|
<h4 id="cross-compilation-examples">Cross-compilation examples</h4>
|
|
<p>Compile the library for ARM Cortex-A9 linux on an x86-64 machine
|
|
<em>(note: install only <code>gnueabihf</code> versions of the cross toolchain - see
|
|
<a href="https://github.com/OpenMathLib/OpenBLAS/issues/936#issuecomment-237596847">this issue comment</a>
|
|
for why</em>):
|
|
<div class="highlight"><pre><span></span><code>make CC=arm-linux-gnueabihf-gcc FC=arm-linux-gnueabihf-gfortran HOSTCC=gcc TARGET=CORTEXA9
|
|
</code></pre></div></p>
|
|
<p>Compile OpenBLAS for a loongson3a CPU on an x86-64 machine:
|
|
<div class="highlight"><pre><span></span><code>make BINARY=64 CC=mips64el-unknown-linux-gnu-gcc FC=mips64el-unknown-linux-gnu-gfortran HOSTCC=gcc TARGET=LOONGSON3A
|
|
</code></pre></div></p>
|
|
<p>Compile OpenBLAS for loongson3a CPU with the <code>loongcc</code> (based on Open64) compiler on an x86-64 machine:
|
|
<div class="highlight"><pre><span></span><code>make CC=loongcc FC=loongf95 HOSTCC=gcc TARGET=LOONGSON3A CROSS=1 CROSS_SUFFIX=mips64el-st-linux-gnu- NO_LAPACKE=1 NO_SHARED=1 BINARY=32
|
|
</code></pre></div></p>
|
|
<h3 id="building-a-debug-version">Building a debug version</h3>
|
|
<p>Add <code>DEBUG=1</code> to your build command, e.g.:
|
|
<div class="highlight"><pre><span></span><code>make DEBUG=1
|
|
</code></pre></div></p>
|
|
<h3 id="install-to-a-specific-directory">Install to a specific directory</h3>
|
|
<div class="admonition note">
|
|
<p class="admonition-title">Note</p>
|
|
<p>Installing to a directory is optional; it is also possible to use the shared or static
|
|
libraries directly from the build directory.</p>
|
|
</div>
|
|
<p>Use <code>make install</code> with the <code>PREFIX</code> flag to install to a specific directory:</p>
|
|
<div class="highlight"><pre><span></span><code>make install PREFIX=/path/to/installation/directory
|
|
</code></pre></div>
|
|
<p>The default directory is <code>/opt/OpenBLAS</code>.</p>
|
|
<div class="admonition important">
|
|
<p class="admonition-title">Important</p>
|
|
<p>Note that any flags passed to <code>make</code> during build should also be passed to
|
|
<code>make install</code> to circumvent any install errors, i.e. some headers not
|
|
being copied over correctly.</p>
|
|
</div>
|
|
<p>For more detailed information on building/installing from source, please read
|
|
the <a href="../install/">Installation Guide</a>.</p>
|
|
<h2 id="linking-to-openblas">Linking to OpenBLAS</h2>
|
|
<p>OpenBLAS can be used as a shared or a static library.</p>
|
|
<h3 id="link-a-shared-library">Link a shared library</h3>
|
|
<p>The shared library is normally called <code>libopenblas.so</code>, but not that the name
|
|
may be different as a result of build flags used or naming choices by a distro
|
|
packager (see [distributing.md] for details). To link a shared library named
|
|
<code>libopenblas.so</code>, the flag <code>-lopenblas</code> is needed. To find the OpenBLAS headers,
|
|
a <code>-I/path/to/includedir</code> is needed. And unless the library is installed in a
|
|
directory that the linker searches by default, also <code>-L</code> and <code>-Wl,-rpath</code> flags
|
|
are needed. For a source file <code>test.c</code> (e.g., the example code under <em>Call
|
|
CBLAS interface</em> further down), the shared library can then be linked with:
|
|
<div class="highlight"><pre><span></span><code>gcc -o test test.c -I/your_path/OpenBLAS/include/ -L/your_path/OpenBLAS/lib -Wl,-rpath,/your_path/OpenBLAS/lib -lopenblas
|
|
</code></pre></div></p>
|
|
<p>The <code>-Wl,-rpath,/your_path/OpenBLAS/lib</code> linker flag can be omitted if you
|
|
ran <code>ldconfig</code> to update linker cache, put <code>/your_path/OpenBLAS/lib</code> in
|
|
<code>/etc/ld.so.conf</code> or a file in <code>/etc/ld.so.conf.d</code>, or installed OpenBLAS in a
|
|
location that is part of the <code>ld.so</code> default search path (usually <code>/lib</code>,
|
|
<code>/usr/lib</code> and <code>/usr/local/lib</code>). Alternatively, you can set the environment
|
|
variable <code>LD_LIBRARY_PATH</code> to point to the folder that contains <code>libopenblas.so</code>.
|
|
Otherwise, the build may succeed but at runtime loading the library will fail
|
|
with a message like:
|
|
<div class="highlight"><pre><span></span><code>cannot open shared object file: no such file or directory
|
|
</code></pre></div></p>
|
|
<p>More flags may be needed, depending on how OpenBLAS was built:</p>
|
|
<ul>
|
|
<li>If <code>libopenblas</code> is multi-threaded, please add <code>-lpthread</code>.</li>
|
|
<li>If the library contains LAPACK functions (usually also true), please add
|
|
<code>-lgfortran</code> (other Fortran libraries may also be needed, e.g. <code>-lquadmath</code>).
|
|
Note that if you only make calls to LAPACKE routines, i.e. your code has
|
|
<code>#include "lapacke.h"</code> and makes calls to methods like <code>LAPACKE_dgeqrf</code>,
|
|
then <code>-lgfortran</code> is not needed.</li>
|
|
</ul>
|
|
<div class="admonition tip use pkg-config">
|
|
<p class="admonition-title">Tip</p>
|
|
<p>Usually a pkg-config file (e.g., <code>openblas.pc</code>) is installed together
|
|
with a <code>libopenblas</code> shared library. pkg-config is a tool that will
|
|
tell you the exact flags needed for linking. For example:</p>
|
|
<div class="highlight"><pre><span></span><code>$ pkg-config --cflags openblas
|
|
-I/usr/local/include
|
|
$ pkg-config --libs openblas
|
|
-L/usr/local/lib -lopenblas
|
|
</code></pre></div>
|
|
</div>
|
|
<h3 id="link-a-static-library">Link a static library</h3>
|
|
<p>Linking a static library is simpler - add the path to the static OpenBLAS
|
|
library to the compile command:
|
|
<div class="highlight"><pre><span></span><code>gcc -o test test.c /your/path/libopenblas.a
|
|
</code></pre></div></p>
|
|
<h2 id="code-examples">Code examples</h2>
|
|
<h3 id="call-cblas-interface">Call CBLAS interface</h3>
|
|
<p>This example shows calling <code>cblas_dgemm</code> in C:</p>
|
|
<!-- Source: https://gist.github.com/xianyi/6930656 -->
|
|
<div class="highlight"><pre><span></span><code><span class="cp">#include</span><span class="w"> </span><span class="cpf"><cblas.h></span>
|
|
<span class="cp">#include</span><span class="w"> </span><span class="cpf"><stdio.h></span>
|
|
|
|
<span class="kt">void</span><span class="w"> </span><span class="nf">main</span><span class="p">()</span>
|
|
<span class="p">{</span>
|
|
<span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">i</span><span class="o">=</span><span class="mi">0</span><span class="p">;</span>
|
|
<span class="w"> </span><span class="kt">double</span><span class="w"> </span><span class="n">A</span><span class="p">[</span><span class="mi">6</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">{</span><span class="mf">1.0</span><span class="p">,</span><span class="mf">2.0</span><span class="p">,</span><span class="mf">1.0</span><span class="p">,</span><span class="mf">-3.0</span><span class="p">,</span><span class="mf">4.0</span><span class="p">,</span><span class="mf">-1.0</span><span class="p">};</span><span class="w"> </span>
|
|
<span class="w"> </span><span class="kt">double</span><span class="w"> </span><span class="n">B</span><span class="p">[</span><span class="mi">6</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">{</span><span class="mf">1.0</span><span class="p">,</span><span class="mf">2.0</span><span class="p">,</span><span class="mf">1.0</span><span class="p">,</span><span class="mf">-3.0</span><span class="p">,</span><span class="mf">4.0</span><span class="p">,</span><span class="mf">-1.0</span><span class="p">};</span><span class="w"> </span>
|
|
<span class="w"> </span><span class="kt">double</span><span class="w"> </span><span class="n">C</span><span class="p">[</span><span class="mi">9</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">{</span><span class="mf">.5</span><span class="p">,</span><span class="mf">.5</span><span class="p">,</span><span class="mf">.5</span><span class="p">,</span><span class="mf">.5</span><span class="p">,</span><span class="mf">.5</span><span class="p">,</span><span class="mf">.5</span><span class="p">,</span><span class="mf">.5</span><span class="p">,</span><span class="mf">.5</span><span class="p">,</span><span class="mf">.5</span><span class="p">};</span><span class="w"> </span>
|
|
<span class="w"> </span><span class="n">cblas_dgemm</span><span class="p">(</span><span class="n">CblasColMajor</span><span class="p">,</span><span class="w"> </span><span class="n">CblasNoTrans</span><span class="p">,</span><span class="w"> </span><span class="n">CblasTrans</span><span class="p">,</span><span class="mi">3</span><span class="p">,</span><span class="mi">3</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">1</span><span class="p">,</span><span class="n">A</span><span class="p">,</span><span class="w"> </span><span class="mi">3</span><span class="p">,</span><span class="w"> </span><span class="n">B</span><span class="p">,</span><span class="w"> </span><span class="mi">3</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="n">C</span><span class="p">,</span><span class="mi">3</span><span class="p">);</span>
|
|
|
|
<span class="w"> </span><span class="k">for</span><span class="p">(</span><span class="n">i</span><span class="o">=</span><span class="mi">0</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="o"><</span><span class="mi">9</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="o">++</span><span class="p">)</span>
|
|
<span class="w"> </span><span class="n">printf</span><span class="p">(</span><span class="s">"%lf "</span><span class="p">,</span><span class="w"> </span><span class="n">C</span><span class="p">[</span><span class="n">i</span><span class="p">]);</span>
|
|
<span class="w"> </span><span class="n">printf</span><span class="p">(</span><span class="s">"</span><span class="se">\n</span><span class="s">"</span><span class="p">);</span>
|
|
<span class="p">}</span>
|
|
</code></pre></div>
|
|
<p>To compile this file, save it as <code>test_cblas_dgemm.c</code> and then run:
|
|
<div class="highlight"><pre><span></span><code>gcc -o test_cblas_open test_cblas_dgemm.c -I/your_path/OpenBLAS/include/ -L/your_path/OpenBLAS/lib -lopenblas -lpthread -lgfortran
|
|
</code></pre></div>
|
|
will result in a <code>test_cblas_open</code> executable.</p>
|
|
<h3 id="call-blas-fortran-interface">Call BLAS Fortran interface</h3>
|
|
<p>This example shows calling the <code>dgemm</code> Fortran interface in C:</p>
|
|
<!-- Source: https://gist.github.com/xianyi/5780018 -->
|
|
<div class="highlight"><pre><span></span><code><span class="cp">#include</span><span class="w"> </span><span class="cpf">"stdio.h"</span>
|
|
<span class="cp">#include</span><span class="w"> </span><span class="cpf">"stdlib.h"</span>
|
|
<span class="cp">#include</span><span class="w"> </span><span class="cpf">"sys/time.h"</span>
|
|
<span class="cp">#include</span><span class="w"> </span><span class="cpf">"time.h"</span>
|
|
|
|
<span class="k">extern</span><span class="w"> </span><span class="kt">void</span><span class="w"> </span><span class="nf">dgemm_</span><span class="p">(</span><span class="kt">char</span><span class="o">*</span><span class="p">,</span><span class="w"> </span><span class="kt">char</span><span class="o">*</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="o">*</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="o">*</span><span class="p">,</span><span class="kt">int</span><span class="o">*</span><span class="p">,</span><span class="w"> </span><span class="kt">double</span><span class="o">*</span><span class="p">,</span><span class="w"> </span><span class="kt">double</span><span class="o">*</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="o">*</span><span class="p">,</span><span class="w"> </span><span class="kt">double</span><span class="o">*</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="o">*</span><span class="p">,</span><span class="w"> </span><span class="kt">double</span><span class="o">*</span><span class="p">,</span><span class="w"> </span><span class="kt">double</span><span class="o">*</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="o">*</span><span class="p">);</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="p">{</span>
|
|
<span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">i</span><span class="p">;</span>
|
|
<span class="w"> </span><span class="n">printf</span><span class="p">(</span><span class="s">"test!</span><span class="se">\n</span><span class="s">"</span><span class="p">);</span>
|
|
<span class="w"> </span><span class="k">if</span><span class="p">(</span><span class="n">argc</span><span class="o"><</span><span class="mi">4</span><span class="p">){</span>
|
|
<span class="w"> </span><span class="n">printf</span><span class="p">(</span><span class="s">"Input Error</span><span class="se">\n</span><span class="s">"</span><span class="p">);</span>
|
|
<span class="w"> </span><span class="k">return</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
|
|
<span class="w"> </span><span class="p">}</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="n">atoi</span><span class="p">(</span><span class="n">argv</span><span class="p">[</span><span class="mi">1</span><span class="p">]);</span>
|
|
<span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">n</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">atoi</span><span class="p">(</span><span class="n">argv</span><span class="p">[</span><span class="mi">2</span><span class="p">]);</span>
|
|
<span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">k</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">atoi</span><span class="p">(</span><span class="n">argv</span><span class="p">[</span><span class="mi">3</span><span class="p">]);</span>
|
|
<span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">sizeofa</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">m</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">k</span><span class="p">;</span>
|
|
<span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">sizeofb</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">k</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">n</span><span class="p">;</span>
|
|
<span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">sizeofc</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">m</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">n</span><span class="p">;</span>
|
|
<span class="w"> </span><span class="kt">char</span><span class="w"> </span><span class="n">ta</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="sc">'N'</span><span class="p">;</span>
|
|
<span class="w"> </span><span class="kt">char</span><span class="w"> </span><span class="n">tb</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="sc">'N'</span><span class="p">;</span>
|
|
<span class="w"> </span><span class="kt">double</span><span class="w"> </span><span class="n">alpha</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mf">1.2</span><span class="p">;</span>
|
|
<span class="w"> </span><span class="kt">double</span><span class="w"> </span><span class="n">beta</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mf">0.001</span><span class="p">;</span>
|
|
|
|
<span class="w"> </span><span class="k">struct</span><span class="w"> </span><span class="nc">timeval</span><span class="w"> </span><span class="n">start</span><span class="p">,</span><span class="n">finish</span><span class="p">;</span>
|
|
<span class="w"> </span><span class="kt">double</span><span class="w"> </span><span class="n">duration</span><span class="p">;</span>
|
|
|
|
<span class="w"> </span><span class="kt">double</span><span class="o">*</span><span class="w"> </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="o">*</span><span class="p">)</span><span class="n">malloc</span><span class="p">(</span><span class="k">sizeof</span><span class="p">(</span><span class="kt">double</span><span class="p">)</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">sizeofa</span><span class="p">);</span>
|
|
<span class="w"> </span><span class="kt">double</span><span class="o">*</span><span class="w"> </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="o">*</span><span class="p">)</span><span class="n">malloc</span><span class="p">(</span><span class="k">sizeof</span><span class="p">(</span><span class="kt">double</span><span class="p">)</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">sizeofb</span><span class="p">);</span>
|
|
<span class="w"> </span><span class="kt">double</span><span class="o">*</span><span class="w"> </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="o">*</span><span class="p">)</span><span class="n">malloc</span><span class="p">(</span><span class="k">sizeof</span><span class="p">(</span><span class="kt">double</span><span class="p">)</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">sizeofc</span><span class="p">);</span>
|
|
|
|
<span class="w"> </span><span class="n">srand</span><span class="p">((</span><span class="kt">unsigned</span><span class="p">)</span><span class="n">time</span><span class="p">(</span><span class="nb">NULL</span><span class="p">));</span>
|
|
|
|
<span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="p">(</span><span class="n">i</span><span class="o">=</span><span class="mi">0</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="o"><</span><span class="n">sizeofa</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="o">++</span><span class="p">)</span>
|
|
<span class="w"> </span><span class="n">A</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">i</span><span class="o">%</span><span class="mi">3</span><span class="o">+</span><span class="mi">1</span><span class="p">;</span><span class="c1">//(rand()%100)/10.0;</span>
|
|
|
|
<span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="p">(</span><span class="n">i</span><span class="o">=</span><span class="mi">0</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="o"><</span><span class="n">sizeofb</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="o">++</span><span class="p">)</span>
|
|
<span class="w"> </span><span class="n">B</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">i</span><span class="o">%</span><span class="mi">3</span><span class="o">+</span><span class="mi">1</span><span class="p">;</span><span class="c1">//(rand()%100)/10.0;</span>
|
|
|
|
<span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="p">(</span><span class="n">i</span><span class="o">=</span><span class="mi">0</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="o"><</span><span class="n">sizeofc</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="o">++</span><span class="p">)</span>
|
|
<span class="w"> </span><span class="n">C</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">i</span><span class="o">%</span><span class="mi">3</span><span class="o">+</span><span class="mi">1</span><span class="p">;</span><span class="c1">//(rand()%100)/10.0;</span>
|
|
<span class="w"> </span><span class="c1">//#if 0</span>
|
|
<span class="w"> </span><span class="n">printf</span><span class="p">(</span><span class="s">"m=%d,n=%d,k=%d,alpha=%lf,beta=%lf,sizeofc=%d</span><span class="se">\n</span><span class="s">"</span><span class="p">,</span><span class="n">m</span><span class="p">,</span><span class="n">n</span><span class="p">,</span><span class="n">k</span><span class="p">,</span><span class="n">alpha</span><span class="p">,</span><span class="n">beta</span><span class="p">,</span><span class="n">sizeofc</span><span class="p">);</span>
|
|
<span class="w"> </span><span class="n">gettimeofday</span><span class="p">(</span><span class="o">&</span><span class="n">start</span><span class="p">,</span><span class="w"> </span><span class="nb">NULL</span><span class="p">);</span>
|
|
<span class="w"> </span><span class="n">dgemm_</span><span class="p">(</span><span class="o">&</span><span class="n">ta</span><span class="p">,</span><span class="w"> </span><span class="o">&</span><span class="n">tb</span><span class="p">,</span><span class="w"> </span><span class="o">&</span><span class="n">m</span><span class="p">,</span><span class="w"> </span><span class="o">&</span><span class="n">n</span><span class="p">,</span><span class="w"> </span><span class="o">&</span><span class="n">k</span><span class="p">,</span><span class="w"> </span><span class="o">&</span><span class="n">alpha</span><span class="p">,</span><span class="w"> </span><span class="n">A</span><span class="p">,</span><span class="w"> </span><span class="o">&</span><span class="n">m</span><span class="p">,</span><span class="w"> </span><span class="n">B</span><span class="p">,</span><span class="w"> </span><span class="o">&</span><span class="n">k</span><span class="p">,</span><span class="w"> </span><span class="o">&</span><span class="n">beta</span><span class="p">,</span><span class="w"> </span><span class="n">C</span><span class="p">,</span><span class="w"> </span><span class="o">&</span><span class="n">m</span><span class="p">);</span>
|
|
<span class="w"> </span><span class="n">gettimeofday</span><span class="p">(</span><span class="o">&</span><span class="n">finish</span><span class="p">,</span><span class="w"> </span><span class="nb">NULL</span><span class="p">);</span>
|
|
|
|
<span class="w"> </span><span class="n">duration</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">((</span><span class="kt">double</span><span class="p">)(</span><span class="n">finish</span><span class="p">.</span><span class="n">tv_sec</span><span class="o">-</span><span class="n">start</span><span class="p">.</span><span class="n">tv_sec</span><span class="p">)</span><span class="o">*</span><span class="mi">1000000</span><span class="w"> </span><span class="o">+</span><span class="w"> </span><span class="p">(</span><span class="kt">double</span><span class="p">)(</span><span class="n">finish</span><span class="p">.</span><span class="n">tv_usec</span><span class="o">-</span><span class="n">start</span><span class="p">.</span><span class="n">tv_usec</span><span class="p">))</span><span class="w"> </span><span class="o">/</span><span class="w"> </span><span class="mi">1000000</span><span class="p">;</span>
|
|
<span class="w"> </span><span class="kt">double</span><span class="w"> </span><span class="n">gflops</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mf">2.0</span><span class="w"> </span><span class="o">*</span><span class="w"> </span><span class="n">m</span><span class="w"> </span><span class="o">*</span><span class="n">n</span><span class="o">*</span><span class="n">k</span><span class="p">;</span>
|
|
<span class="w"> </span><span class="n">gflops</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">gflops</span><span class="o">/</span><span class="n">duration</span><span class="o">*</span><span class="mf">1.0e-6</span><span class="p">;</span>
|
|
|
|
<span class="w"> </span><span class="kt">FILE</span><span class="w"> </span><span class="o">*</span><span class="n">fp</span><span class="p">;</span>
|
|
<span class="w"> </span><span class="n">fp</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">fopen</span><span class="p">(</span><span class="s">"timeDGEMM.txt"</span><span class="p">,</span><span class="w"> </span><span class="s">"a"</span><span class="p">);</span>
|
|
<span class="w"> </span><span class="n">fprintf</span><span class="p">(</span><span class="n">fp</span><span class="p">,</span><span class="w"> </span><span class="s">"%dx%dx%d</span><span class="se">\t</span><span class="s">%lf s</span><span class="se">\t</span><span class="s">%lf MFLOPS</span><span class="se">\n</span><span class="s">"</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">duration</span><span class="p">,</span><span class="w"> </span><span class="n">gflops</span><span class="p">);</span>
|
|
<span class="w"> </span><span class="n">fclose</span><span class="p">(</span><span class="n">fp</span><span class="p">);</span>
|
|
|
|
<span class="w"> </span><span class="n">free</span><span class="p">(</span><span class="n">A</span><span class="p">);</span>
|
|
<span class="w"> </span><span class="n">free</span><span class="p">(</span><span class="n">B</span><span class="p">);</span>
|
|
<span class="w"> </span><span class="n">free</span><span class="p">(</span><span class="n">C</span><span class="p">);</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="p">}</span>
|
|
</code></pre></div>
|
|
<p>To compile this file, save it as <code>time_dgemm.c</code> and then run:
|
|
<div class="highlight"><pre><span></span><code>gcc -o time_dgemm time_dgemm.c /your/path/libopenblas.a -lpthread
|
|
</code></pre></div>
|
|
You can then run it as: <code>./time_dgemm <m> <n> <k></code>, with <code>m</code>, <code>n</code>, and <code>k</code> input
|
|
parameters to the <code>time_dgemm</code> executable.</p>
|
|
<div class="admonition note">
|
|
<p class="admonition-title">Note</p>
|
|
<p>When calling the Fortran interface from C, you have to deal with symbol name
|
|
differences caused by compiler conventions. That is why the <code>dgemm_</code> function
|
|
call in the example above has a trailing underscore. This is what it looks like
|
|
when using <code>gcc</code>/<code>gfortran</code>, however such details may change for different
|
|
compilers. Hence it requires extra support code. The CBLAS interface may be
|
|
more portable when writing C code.</p>
|
|
<p>When writing code that needs to be portable and work across different
|
|
platforms and compilers, the above code example is not recommended for
|
|
usage. Instead, we advise looking at how OpenBLAS (or BLAS in general, since
|
|
this problem isn't specific to OpenBLAS) functions are called in widely
|
|
used projects like Julia, SciPy, or R.</p>
|
|
</div>
|
|
<h2 id="troubleshooting">Troubleshooting</h2>
|
|
<ul>
|
|
<li>Please read the <a href="../faq/">FAQ</a> first, your problem may be described there.</li>
|
|
<li>Please ensure you are using a recent enough compiler, that supports the
|
|
features your CPU provides (example: GCC versions before 4.6 were known to
|
|
not support AVX kernels, and before 6.1 AVX512CD kernels).</li>
|
|
<li>The number of CPU cores supported by default is <=256. On Linux x86-64, there
|
|
is experimental support for up to 1024 cores and 128 NUMA nodes if you build
|
|
the library with <code>BIGNUMA=1</code>.</li>
|
|
<li>OpenBLAS does not set processor affinity by default. On Linux, you can enable
|
|
processor affinity by commenting out the line <code>NO_AFFINITY=1</code> in
|
|
<code>Makefile.rule</code>.</li>
|
|
<li>On Loongson 3A, <code>make test</code> is known to fail with a <code>pthread_create</code> error
|
|
and an <code>EAGAIN</code> error code. However, it will be OK when you run the same
|
|
testcase in a shell.</li>
|
|
</ul>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<aside class="md-source-file">
|
|
|
|
|
|
<span class="md-source-file__fact">
|
|
<span class="md-icon" title="Last update">
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M21 13.1c-.1 0-.3.1-.4.2l-1 1 2.1 2.1 1-1c.2-.2.2-.6 0-.8l-1.3-1.3c-.1-.1-.2-.2-.4-.2m-1.9 1.8-6.1 6V23h2.1l6.1-6.1-2.1-2M12.5 7v5.2l4 2.4-1 1L11 13V7h1.5M11 21.9c-5.1-.5-9-4.8-9-9.9C2 6.5 6.5 2 12 2c5.3 0 9.6 4.1 10 9.3-.3-.1-.6-.2-1-.2s-.7.1-1 .2C19.6 7.2 16.2 4 12 4c-4.4 0-8 3.6-8 8 0 4.1 3.1 7.5 7.1 7.9l-.1.2v1.8Z"/></svg>
|
|
</span>
|
|
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date">July 2, 2024</span>
|
|
</span>
|
|
|
|
|
|
|
|
|
|
<span class="md-source-file__fact">
|
|
<span class="md-icon" title="Created">
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M14.47 15.08 11 13V7h1.5v5.25l3.08 1.83c-.41.28-.79.62-1.11 1m-1.39 4.84c-.36.05-.71.08-1.08.08-4.42 0-8-3.58-8-8s3.58-8 8-8 8 3.58 8 8c0 .37-.03.72-.08 1.08.69.1 1.33.32 1.92.64.1-.56.16-1.13.16-1.72 0-5.5-4.5-10-10-10S2 6.5 2 12s4.47 10 10 10c.59 0 1.16-.06 1.72-.16-.32-.59-.54-1.23-.64-1.92M18 15v3h-3v2h3v3h2v-3h3v-2h-3v-3h-2Z"/></svg>
|
|
</span>
|
|
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date">August 4, 2023</span>
|
|
</span>
|
|
|
|
|
|
|
|
|
|
</aside>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
</article>
|
|
</div>
|
|
|
|
|
|
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
|
|
</div>
|
|
|
|
</main>
|
|
|
|
<footer class="md-footer">
|
|
|
|
<div class="md-footer-meta md-typeset">
|
|
<div class="md-footer-meta__inner md-grid">
|
|
<div class="md-copyright">
|
|
|
|
<div class="md-copyright__highlight">
|
|
Copyright © 2012- OpenBLAS contributors
|
|
</div>
|
|
|
|
|
|
Made with
|
|
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
|
|
Material for MkDocs
|
|
</a>
|
|
|
|
</div>
|
|
|
|
<div class="md-social">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<a href="https://github.com/OpenMathLib/OpenBLAS" target="_blank" rel="noopener" title="github.com" class="md-social__link">
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 496 512"><!--! Font Awesome Free 6.6.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6zm-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3zm44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9zM244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8zM97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1zm-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7zm32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1zm-11.4-14.7c-1.6 1-1.6 3.6 0 5.9 1.6 2.3 4.3 3.3 5.6 2.3 1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2z"/></svg>
|
|
</a>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<a href="https://github.com/OpenMathLib/OpenBLAS/LICENSE" target="_blank" rel="noopener" title="github.com" class="md-social__link">
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9 10a3.04 3.04 0 0 1 3-3 3.04 3.04 0 0 1 3 3 3.04 3.04 0 0 1-3 3 3.04 3.04 0 0 1-3-3m3 9 4 1v-3.08A7.54 7.54 0 0 1 12 18a7.54 7.54 0 0 1-4-1.08V20m4-16a5.78 5.78 0 0 0-4.24 1.74A5.78 5.78 0 0 0 6 10a5.78 5.78 0 0 0 1.76 4.23A5.78 5.78 0 0 0 12 16a5.78 5.78 0 0 0 4.24-1.77A5.78 5.78 0 0 0 18 10a5.78 5.78 0 0 0-1.76-4.26A5.78 5.78 0 0 0 12 4m8 6a8.04 8.04 0 0 1-.57 2.8A7.84 7.84 0 0 1 18 15.28V23l-6-2-6 2v-7.72A7.9 7.9 0 0 1 4 10a7.68 7.68 0 0 1 2.33-5.64A7.73 7.73 0 0 1 12 2a7.73 7.73 0 0 1 5.67 2.36A7.68 7.68 0 0 1 20 10Z"/></svg>
|
|
</a>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
</footer>
|
|
|
|
</div>
|
|
<div class="md-dialog" data-md-component="dialog">
|
|
<div class="md-dialog__inner md-typeset"></div>
|
|
</div>
|
|
|
|
|
|
<script id="__config" type="application/json">{"base": "..", "features": ["header.autohide"], "search": "../assets/javascripts/workers/search.b8dbb3d2.min.js", "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}}</script>
|
|
|
|
|
|
<script src="../assets/javascripts/bundle.fe8b6f2b.min.js"></script>
|
|
|
|
|
|
</body>
|
|
</html> |