<!doctype html><html lang="en" class="no-js"><head><meta charset="utf-8"> <!-- begin SEO --><title>Optimizing half precision winograd convolution on arm many-core processors - Dedong Xie</title><meta property="og:locale" content="en-US"><meta property="og:site_name" content="Dedong Xie"><meta property="og:title" content="Optimizing half precision winograd convolution on arm many-core processors"><link rel="canonical" href="https://ddxxdd-code.github.io/publication/2022-08-Optimizing_half_precision_winograd.md"><meta property="og:url" content="https://ddxxdd-code.github.io/publication/2022-08-Optimizing_half_precision_winograd.md"><meta property="og:description" content="Webpage hosted on Github Pages of Dedong Xie"><meta property="og:type" content="article"><meta property="article:published_time" content="2022-08-24T00:00:00-07:00"> <script type="application/ld+json"> { "@context" : "http://schema.org", "@type" : "Person", "name" : "Dedong Xie", "url" : "https://ddxxdd-code.github.io", "sameAs" : null } </script> <!-- end SEO --><link href="https://ddxxdd-code.github.io/feed.xml" type="application/atom+xml" rel="alternate" title="Dedong Xie Feed"> <!-- http://t.co/dKP3o1e --><meta name="HandheldFriendly" content="True"><meta name="MobileOptimized" content="320"><meta name="viewport" content="width=device-width, initial-scale=1.0"> <script> document.documentElement.className = document.documentElement.className.replace(/\bno-js\b/g, '') + ' js '; </script> <!-- For all browsers --><link rel="stylesheet" href="https://ddxxdd-code.github.io/assets/css/main.css"><meta http-equiv="cleartype" content="on"> <!-- start custom head snippets --><link rel="apple-touch-icon" sizes="57x57" href="https://ddxxdd-code.github.io/images/apple-touch-icon-57x57.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="60x60" href="https://ddxxdd-code.github.io/images/apple-touch-icon-60x60.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="72x72" href="https://ddxxdd-code.github.io/images/apple-touch-icon-72x72.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="76x76" href="https://ddxxdd-code.github.io/images/apple-touch-icon-76x76.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="114x114" href="https://ddxxdd-code.github.io/images/apple-touch-icon-114x114.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="120x120" href="https://ddxxdd-code.github.io/images/apple-touch-icon-120x120.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="144x144" href="https://ddxxdd-code.github.io/images/apple-touch-icon-144x144.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="152x152" href="https://ddxxdd-code.github.io/images/apple-touch-icon-152x152.png?v=M44lzPylqQ"><link rel="apple-touch-icon" sizes="180x180" href="https://ddxxdd-code.github.io/images/apple-touch-icon-180x180.png?v=M44lzPylqQ"><link rel="icon" type="image/png" href="https://ddxxdd-code.github.io/images/favicon-32x32.png?v=M44lzPylqQ" sizes="32x32"><link rel="icon" type="image/png" href="https://ddxxdd-code.github.io/images/android-chrome-192x192.png?v=M44lzPylqQ" sizes="192x192"><link rel="icon" type="image/png" href="https://ddxxdd-code.github.io/images/favicon-96x96.png?v=M44lzPylqQ" sizes="96x96"><link rel="icon" type="image/png" href="https://ddxxdd-code.github.io/images/favicon-16x16.png?v=M44lzPylqQ" sizes="16x16"><link rel="manifest" href="https://ddxxdd-code.github.io/images/manifest.json?v=M44lzPylqQ"><link rel="mask-icon" href="https://ddxxdd-code.github.io/images/safari-pinned-tab.svg?v=M44lzPylqQ" color="#000000"><link rel="shortcut icon" href="/images/favicon.ico?v=M44lzPylqQ"><meta name="msapplication-TileColor" content="#000000"><meta name="msapplication-TileImage" content="https://ddxxdd-code.github.io/images/mstile-144x144.png?v=M44lzPylqQ"><meta name="msapplication-config" content="https://ddxxdd-code.github.io/images/browserconfig.xml?v=M44lzPylqQ"><meta name="theme-color" content="#ffffff"><link rel="stylesheet" href="https://ddxxdd-code.github.io/assets/css/academicons.css"/> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ TeX: { equationNumbers: { autoNumber: "all" } } }); </script> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ tex2jax: { inlineMath: [ ['$','$'], ["\\(","\\)"] ], processEscapes: true } }); </script> <script src='https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.4/latest.js?config=TeX-MML-AM_CHTML' async></script> <!-- end custom head snippets --></head><body> <!--[if lt IE 9]><div class="notice--danger align-center" style="margin: 0;">You are using an <strong>outdated</strong> browser. Please <a href="http://browsehappy.com/">upgrade your browser</a> to improve your experience.</div><![endif]--><div class="masthead"><div class="masthead__inner-wrap"><div class="masthead__menu"><nav id="site-nav" class="greedy-nav"> <button><div class="navicon"></div></button><ul class="visible-links"><li class="masthead__menu-item masthead__menu-item--lg"><a href="https://ddxxdd-code.github.io/">Dedong Xie</a></li><li class="masthead__menu-item"><a href="https://ddxxdd-code.github.io/publications/">Publication</a></li><li class="masthead__menu-item"><a href="https://ddxxdd-code.github.io/files/CV_Dedong_Xie.pdf">CV</a></li></ul><ul class="hidden-links hidden"></ul></nav></div></div></div><div id="main" role="main"><div class="sidebar sticky"><div itemscope itemtype="http://schema.org/Person"><div class="author__avatar"> <img src="https://ddxxdd-code.github.io/images/profile.jpg" class="author__avatar" alt="Dedong Xie (谢德东)"></div><div class="author__content"><h3 class="author__name">Dedong Xie (谢德东)</h3><p class="author__bio">2nd year Computer Science PhD student</p></div><div class="author__urls-wrapper"> <button class="btn btn--inverse">Follow</button><ul class="author__urls social-icons"><li><i class="fa fa-fw fa-map-marker" aria-hidden="true"></i> Seattle, WA. USA.</li><li><a href="mailto:dedongx@cs.washington.edu"><i class="fas fa-fw fa-envelope" aria-hidden="true"></i> Email</a></li><li><a href="https://www.linkedin.com/in/dedong-xie-547a501a8"><i class="fab fa-fw fa-linkedin" aria-hidden="true"></i> LinkedIn</a></li><li><a href="https://github.com/ddxxdd-code"><i class="fab fa-fw fa-github" aria-hidden="true"></i> Github</a></li><li><a href="https://scholar.google.com/citations?user=pcPvXJsAAAAJ&hl=en"><i class="fas fa-fw fa-graduation-cap"></i> Google Scholar</a></li><li><a href="https://orcid.org/my-orcid?orcid=0009-0005-7324-6110"><i class="ai ai-orcid-square ai-fw"></i> ORCID</a></li></ul></div></div></div><article class="page" itemscope itemtype="http://schema.org/CreativeWork"><meta itemprop="headline" content="Optimizing half precision winograd convolution on arm many-core processors"><meta itemprop="description" content=""><meta itemprop="datePublished" content="August 24, 2022"><div class="page__inner-wrap"><header><h1 class="page__title" itemprop="headline">Optimizing half precision winograd convolution on arm many-core processors</h1><p>Published in <i>APSys 2022</i>, 2022</p><p>Recommended citation: Dedong Xie, Zhen Jia, Zili Zhang, and Xin Jin. (2022). &quot;Optimizing half precision winograd convolution on arm many-core processors &quot; <i>Proceedings of the 13th ACM SIGOPS Asia-Pacific Workshop on Systems, APSys ’22</i>. pages 53–60, Virtual Event, Singapore. Association for Computing Machinery, 2022 <a href="http://academicpages.github.io/files/paper1.pdf"><u>http://academicpages.github.io/files/paper1.pdf</u></a></p></header><section class="page__content" itemprop="text"><p><a href="https://dl.acm.org/doi/10.1145/3546591.3547529">paper</a> <a href="https://drive.google.com/file/d/1ORxEp1757ryRkBKi0_n2Xf5hA5iQAEOQ/view">presentation</a> <a href="https://docs.google.com/presentation/d/1ibfGc3yWNl4SP4UOipCfzmaHFQHd5lpF/edit#slide=id.p1">slides</a> <a href="http://academicpages.github.io/files/paper1.pdf">code</a></p></section><footer class="page__meta"></footer><section class="page__share"><h4 class="page__share-title">Share on</h4><a href="https://twitter.com/intent/tweet?text=https://ddxxdd-code.github.io/publication/2022-08-Optimizing_half_precision_winograd.md" class="btn btn--twitter" title="Share on Twitter"><i class="fab fa-twitter" aria-hidden="true"></i><span> Twitter</span></a> <a href="https://www.facebook.com/sharer/sharer.php?u=https://ddxxdd-code.github.io/publication/2022-08-Optimizing_half_precision_winograd.md" class="btn btn--facebook" title="Share on Facebook"><i class="fab fa-facebook" aria-hidden="true"></i><span> Facebook</span></a> <a href="https://www.linkedin.com/shareArticle?mini=true&url=https://ddxxdd-code.github.io/publication/2022-08-Optimizing_half_precision_winograd.md" class="btn btn--linkedin" title="Share on LinkedIn"><i class="fab fa-linkedin" aria-hidden="true"></i><span> LinkedIn</span></a></section><nav class="pagination"> <a href="#" class="pagination--pager disabled">Previous</a> <a href="https://ddxxdd-code.github.io/_publications/publications.md" class="pagination--pager" title="Publications ">Next</a></nav></div></article></div><div class="page__footer"><footer> <!-- start custom footer snippets --> <a href="/sitemap/">Sitemap</a> <!-- end custom footer snippets --><div class="page__footer-follow"><ul class="social-icons"><li><strong>Follow:</strong></li><li><a href="http://github.com/ddxxdd-code"><i class="fab fa-github" aria-hidden="true"></i> GitHub</a></li><li><a href="https://ddxxdd-code.github.io/feed.xml"><i class="fa fa-fw fa-rss-square" aria-hidden="true"></i> Feed</a></li></ul></div><div class="page__footer-copyright">&copy; 2025 Dedong Xie. Powered by <a href="http://jekyllrb.com" rel="nofollow">Jekyll</a> &amp; <a href="https://github.com/academicpages/academicpages.github.io">AcademicPages</a>, a fork of <a href="https://mademistakes.com/work/minimal-mistakes-jekyll-theme/" rel="nofollow">Minimal Mistakes</a>.</div></footer></div><script src="https://ddxxdd-code.github.io/assets/js/main.min.js"></script> <script> (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) })(window,document,'script','//www.google-analytics.com/analytics.js','ga'); ga('create', '', 'auto'); ga('send', 'pageview'); </script></body></html>
