Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–8 of 8 results for author: <span class="mathjax">Jindariani, S</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Jindariani%2C+S">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Jindariani, S"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Jindariani%2C+S&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Jindariani, S"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2110.13041">arXiv:2110.13041</a> <span> [<a href="https://arxiv.org/pdf/2110.13041">pdf</a>, <a href="https://arxiv.org/format/2110.13041">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Data Analysis, Statistics and Probability">physics.data-an</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Instrumentation and Detectors">physics.ins-det</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.3389/fdata.2022.787421">10.3389/fdata.2022.787421 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Applications and Techniques for Fast Machine Learning in Science </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Deiana%2C+A+M">Allison McCarn Deiana</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/cs?searchtype=author&query=Agar%2C+J">Joshua Agar</a>, <a href="/search/cs?searchtype=author&query=Blott%2C+M">Michaela Blott</a>, <a href="/search/cs?searchtype=author&query=Di+Guglielmo%2C+G">Giuseppe Di Guglielmo</a>, <a href="/search/cs?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/cs?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/cs?searchtype=author&query=Hauck%2C+S">Scott Hauck</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Mia Liu</a>, <a href="/search/cs?searchtype=author&query=Neubauer%2C+M+S">Mark S. Neubauer</a>, <a href="/search/cs?searchtype=author&query=Ngadiuba%2C+J">Jennifer Ngadiuba</a>, <a href="/search/cs?searchtype=author&query=Ogrenci-Memik%2C+S">Seda Ogrenci-Memik</a>, <a href="/search/cs?searchtype=author&query=Pierini%2C+M">Maurizio Pierini</a>, <a href="/search/cs?searchtype=author&query=Aarrestad%2C+T">Thea Aarrestad</a>, <a href="/search/cs?searchtype=author&query=Bahr%2C+S">Steffen Bahr</a>, <a href="/search/cs?searchtype=author&query=Becker%2C+J">Jurgen Becker</a>, <a href="/search/cs?searchtype=author&query=Berthold%2C+A">Anne-Sophie Berthold</a>, <a href="/search/cs?searchtype=author&query=Bonventre%2C+R+J">Richard J. Bonventre</a>, <a href="/search/cs?searchtype=author&query=Bravo%2C+T+E+M">Tomas E. Muller Bravo</a>, <a href="/search/cs?searchtype=author&query=Diefenthaler%2C+M">Markus Diefenthaler</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+Z">Zhen Dong</a>, <a href="/search/cs?searchtype=author&query=Fritzsche%2C+N">Nick Fritzsche</a>, <a href="/search/cs?searchtype=author&query=Gholami%2C+A">Amir Gholami</a>, <a href="/search/cs?searchtype=author&query=Govorkova%2C+E">Ekaterina Govorkova</a>, <a href="/search/cs?searchtype=author&query=Hazelwood%2C+K+J">Kyle J Hazelwood</a> , et al. (62 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2110.13041v1-abstract-short" style="display: inline;"> In this community review report, we discuss applications and techniques for fast machine learning (ML) in science -- the concept of integrating power ML methods into the real-time experimental data processing loop to accelerate scientific discovery. The material for the report builds on two workshops held by the Fast ML for Science community and covers three main areas: applications for fast ML ac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.13041v1-abstract-full').style.display = 'inline'; document.getElementById('2110.13041v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2110.13041v1-abstract-full" style="display: none;"> In this community review report, we discuss applications and techniques for fast machine learning (ML) in science -- the concept of integrating power ML methods into the real-time experimental data processing loop to accelerate scientific discovery. The material for the report builds on two workshops held by the Fast ML for Science community and covers three main areas: applications for fast ML across a number of scientific domains; techniques for training and implementing performant and resource-efficient ML algorithms; and computing architectures, platforms, and technologies for deploying these algorithms. We also present overlapping challenges across the multiple scientific domains where common solutions can be found. This community report is intended to give plenty of examples and inspiration for scientific discovery through integrated and accelerated ML solutions. This is followed by a high-level overview and organization of technical advances, including an abundance of pointers to source material, which can enable these breakthroughs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.13041v1-abstract-full').style.display = 'none'; document.getElementById('2110.13041v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">66 pages, 13 figures, 5 tables</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> FERMILAB-PUB-21-502-AD-E-SCD </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Front. Big Data 5, 787421 (2022) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.05579">arXiv:2103.05579</a> <span> [<a href="https://arxiv.org/pdf/2103.05579">pdf</a>, <a href="https://arxiv.org/format/2103.05579">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Instrumentation and Detectors">physics.ins-det</span> </div> </div> <p class="title is-5 mathjax"> hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fahim%2C+F">Farah Fahim</a>, <a href="/search/cs?searchtype=author&query=Hawks%2C+B">Benjamin Hawks</a>, <a href="/search/cs?searchtype=author&query=Herwig%2C+C">Christian Herwig</a>, <a href="/search/cs?searchtype=author&query=Hirschauer%2C+J">James Hirschauer</a>, <a href="/search/cs?searchtype=author&query=Jindariani%2C+S">Sergo Jindariani</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/cs?searchtype=author&query=Carloni%2C+L+P">Luca P. Carloni</a>, <a href="/search/cs?searchtype=author&query=Di+Guglielmo%2C+G">Giuseppe Di Guglielmo</a>, <a href="/search/cs?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/cs?searchtype=author&query=Krupa%2C+J">Jeffrey Krupa</a>, <a href="/search/cs?searchtype=author&query=Rankin%2C+D">Dylan Rankin</a>, <a href="/search/cs?searchtype=author&query=Valentin%2C+M+B">Manuel Blanco Valentin</a>, <a href="/search/cs?searchtype=author&query=Hester%2C+J">Josiah Hester</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+Y">Yingyi Luo</a>, <a href="/search/cs?searchtype=author&query=Mamish%2C+J">John Mamish</a>, <a href="/search/cs?searchtype=author&query=Orgrenci-Memik%2C+S">Seda Orgrenci-Memik</a>, <a href="/search/cs?searchtype=author&query=Aarrestad%2C+T">Thea Aarrestad</a>, <a href="/search/cs?searchtype=author&query=Javed%2C+H">Hamza Javed</a>, <a href="/search/cs?searchtype=author&query=Loncar%2C+V">Vladimir Loncar</a>, <a href="/search/cs?searchtype=author&query=Pierini%2C+M">Maurizio Pierini</a>, <a href="/search/cs?searchtype=author&query=Pol%2C+A+A">Adrian Alan Pol</a>, <a href="/search/cs?searchtype=author&query=Summers%2C+S">Sioni Summers</a>, <a href="/search/cs?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/cs?searchtype=author&query=Hauck%2C+S">Scott Hauck</a>, <a href="/search/cs?searchtype=author&query=Hsu%2C+S">Shih-Chieh Hsu</a> , et al. (5 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2103.05579v3-abstract-short" style="display: inline;"> Accessible machine learning algorithms, software, and diagnostic tools for energy-efficient devices and systems are extremely valuable across a broad range of application domains. In scientific domains, real-time near-sensor processing can drastically improve experimental design and accelerate scientific discoveries. To support domain scientists, we have developed hls4ml, an open-source software-h… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.05579v3-abstract-full').style.display = 'inline'; document.getElementById('2103.05579v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.05579v3-abstract-full" style="display: none;"> Accessible machine learning algorithms, software, and diagnostic tools for energy-efficient devices and systems are extremely valuable across a broad range of application domains. In scientific domains, real-time near-sensor processing can drastically improve experimental design and accelerate scientific discoveries. To support domain scientists, we have developed hls4ml, an open-source software-hardware codesign workflow to interpret and translate machine learning algorithms for implementation with both FPGA and ASIC technologies. We expand on previous hls4ml work by extending capabilities and techniques towards low-power implementations and increased usability: new Python APIs, quantization-aware pruning, end-to-end FPGA workflows, long pipeline kernels for low power, and new device backends include an ASIC workflow. Taken together, these and continued efforts in hls4ml will arm a new generation of domain scientists with accessible, efficient, and powerful tools for machine-learning-accelerated discovery. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.05579v3-abstract-full').style.display = 'none'; document.getElementById('2103.05579v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 8 figures, TinyML Research Symposium 2021</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> FERMILAB-CONF-21-080-SCD </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.05108">arXiv:2101.05108</a> <span> [<a href="https://arxiv.org/pdf/2101.05108">pdf</a>, <a href="https://arxiv.org/format/2101.05108">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Instrumentation and Detectors">physics.ins-det</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1088/2632-2153/ac0ea1">10.1088/2632-2153/ac0ea1 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Fast convolutional neural networks on FPGAs with hls4ml </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Aarrestad%2C+T">Thea Aarrestad</a>, <a href="/search/cs?searchtype=author&query=Loncar%2C+V">Vladimir Loncar</a>, <a href="/search/cs?searchtype=author&query=Ghielmetti%2C+N">Nicol貌 Ghielmetti</a>, <a href="/search/cs?searchtype=author&query=Pierini%2C+M">Maurizio Pierini</a>, <a href="/search/cs?searchtype=author&query=Summers%2C+S">Sioni Summers</a>, <a href="/search/cs?searchtype=author&query=Ngadiuba%2C+J">Jennifer Ngadiuba</a>, <a href="/search/cs?searchtype=author&query=Petersson%2C+C">Christoffer Petersson</a>, <a href="/search/cs?searchtype=author&query=Linander%2C+H">Hampus Linander</a>, <a href="/search/cs?searchtype=author&query=Iiyama%2C+Y">Yutaro Iiyama</a>, <a href="/search/cs?searchtype=author&query=Di+Guglielmo%2C+G">Giuseppe Di Guglielmo</a>, <a href="/search/cs?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/cs?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/cs?searchtype=author&query=Rankin%2C+D">Dylan Rankin</a>, <a href="/search/cs?searchtype=author&query=Jindariani%2C+S">Sergo Jindariani</a>, <a href="/search/cs?searchtype=author&query=Pedro%2C+K">Kevin Pedro</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Mia Liu</a>, <a href="/search/cs?searchtype=author&query=Kreinar%2C+E">Edward Kreinar</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Z">Zhenbin Wu</a>, <a href="/search/cs?searchtype=author&query=Hoang%2C+D">Duc Hoang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2101.05108v2-abstract-short" style="display: inline;"> We introduce an automated tool for deploying ultra low-latency, low-power deep neural networks with convolutional layers on FPGAs. By extending the hls4ml library, we demonstrate an inference latency of $5\,渭$s using convolutional architectures, targeting microsecond latency applications like those at the CERN Large Hadron Collider. Considering benchmark models trained on the Street View House Num… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.05108v2-abstract-full').style.display = 'inline'; document.getElementById('2101.05108v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.05108v2-abstract-full" style="display: none;"> We introduce an automated tool for deploying ultra low-latency, low-power deep neural networks with convolutional layers on FPGAs. By extending the hls4ml library, we demonstrate an inference latency of $5\,渭$s using convolutional architectures, targeting microsecond latency applications like those at the CERN Large Hadron Collider. Considering benchmark models trained on the Street View House Numbers Dataset, we demonstrate various methods for model compression in order to fit the computational constraints of a typical FPGA device used in trigger and data acquisition systems of particle detectors. In particular, we discuss pruning and quantization-aware training, and demonstrate how resource utilization can be significantly reduced with little to no loss in model accuracy. We show that the FPGA critical resource consumption can be reduced by 97% with zero loss in model accuracy, and by 99% when tolerating a 6% accuracy degradation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.05108v2-abstract-full').style.display = 'none'; document.getElementById('2101.05108v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">18 pages, 18 figures, 4 tables</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Mach. Learn.: Sci. Technol. 2 045015 (2021) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2012.01563">arXiv:2012.01563</a> <span> [<a href="https://arxiv.org/pdf/2012.01563">pdf</a>, <a href="https://arxiv.org/format/2012.01563">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Instrumentation and Detectors">physics.ins-det</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Physics">physics.comp-ph</span> </div> </div> <p class="title is-5 mathjax"> Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Heintz%2C+A">Aneesh Heintz</a>, <a href="/search/cs?searchtype=author&query=Razavimaleki%2C+V">Vesal Razavimaleki</a>, <a href="/search/cs?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/cs?searchtype=author&query=DeZoort%2C+G">Gage DeZoort</a>, <a href="/search/cs?searchtype=author&query=Ojalvo%2C+I">Isobel Ojalvo</a>, <a href="/search/cs?searchtype=author&query=Thais%2C+S">Savannah Thais</a>, <a href="/search/cs?searchtype=author&query=Atkinson%2C+M">Markus Atkinson</a>, <a href="/search/cs?searchtype=author&query=Neubauer%2C+M">Mark Neubauer</a>, <a href="/search/cs?searchtype=author&query=Gray%2C+L">Lindsey Gray</a>, <a href="/search/cs?searchtype=author&query=Jindariani%2C+S">Sergo Jindariani</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/cs?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/cs?searchtype=author&query=Rankin%2C+D">Dylan Rankin</a>, <a href="/search/cs?searchtype=author&query=Aarrestad%2C+T">Thea Aarrestad</a>, <a href="/search/cs?searchtype=author&query=Loncar%2C+V">Vladimir Loncar</a>, <a href="/search/cs?searchtype=author&query=Pierini%2C+M">Maurizio Pierini</a>, <a href="/search/cs?searchtype=author&query=Summers%2C+S">Sioni Summers</a>, <a href="/search/cs?searchtype=author&query=Ngadiuba%2C+J">Jennifer Ngadiuba</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Mia Liu</a>, <a href="/search/cs?searchtype=author&query=Kreinar%2C+E">Edward Kreinar</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Z">Zhenbin Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2012.01563v1-abstract-short" style="display: inline;"> We develop and study FPGA implementations of algorithms for charged particle tracking based on graph neural networks. The two complementary FPGA designs are based on OpenCL, a framework for writing programs that execute across heterogeneous platforms, and hls4ml, a high-level-synthesis-based compiler for neural network to firmware conversion. We evaluate and compare the resource usage, latency, an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.01563v1-abstract-full').style.display = 'inline'; document.getElementById('2012.01563v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2012.01563v1-abstract-full" style="display: none;"> We develop and study FPGA implementations of algorithms for charged particle tracking based on graph neural networks. The two complementary FPGA designs are based on OpenCL, a framework for writing programs that execute across heterogeneous platforms, and hls4ml, a high-level-synthesis-based compiler for neural network to firmware conversion. We evaluate and compare the resource usage, latency, and tracking performance of our implementations based on a benchmark dataset. We find a considerable speedup over CPU-based execution is possible, potentially enabling such algorithms to be used effectively in future computing workflows and the FPGA-based Level-1 trigger at the CERN Large Hadron Collider. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.01563v1-abstract-full').style.display = 'none'; document.getElementById('2012.01563v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 4 figures, To appear in Third Workshop on Machine Learning and the Physical Sciences (NeurIPS 2020)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> FERMILAB-CONF-20-622-CMS-SCD </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2008.03601">arXiv:2008.03601</a> <span> [<a href="https://arxiv.org/pdf/2008.03601">pdf</a>, <a href="https://arxiv.org/format/2008.03601">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Instrumentation and Detectors">physics.ins-det</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.3389/fdata.2020.598927">10.3389/fdata.2020.598927 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Iiyama%2C+Y">Yutaro Iiyama</a>, <a href="/search/cs?searchtype=author&query=Cerminara%2C+G">Gianluca Cerminara</a>, <a href="/search/cs?searchtype=author&query=Gupta%2C+A">Abhijay Gupta</a>, <a href="/search/cs?searchtype=author&query=Kieseler%2C+J">Jan Kieseler</a>, <a href="/search/cs?searchtype=author&query=Loncar%2C+V">Vladimir Loncar</a>, <a href="/search/cs?searchtype=author&query=Pierini%2C+M">Maurizio Pierini</a>, <a href="/search/cs?searchtype=author&query=Qasim%2C+S+R">Shah Rukh Qasim</a>, <a href="/search/cs?searchtype=author&query=Rieger%2C+M">Marcel Rieger</a>, <a href="/search/cs?searchtype=author&query=Summers%2C+S">Sioni Summers</a>, <a href="/search/cs?searchtype=author&query=Van+Onsem%2C+G">Gerrit Van Onsem</a>, <a href="/search/cs?searchtype=author&query=Wozniak%2C+K">Kinga Wozniak</a>, <a href="/search/cs?searchtype=author&query=Ngadiuba%2C+J">Jennifer Ngadiuba</a>, <a href="/search/cs?searchtype=author&query=Di+Guglielmo%2C+G">Giuseppe Di Guglielmo</a>, <a href="/search/cs?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/cs?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/cs?searchtype=author&query=Rankin%2C+D">Dylan Rankin</a>, <a href="/search/cs?searchtype=author&query=Jindariani%2C+S">Sergo Jindariani</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Mia Liu</a>, <a href="/search/cs?searchtype=author&query=Pedro%2C+K">Kevin Pedro</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/cs?searchtype=author&query=Kreinar%2C+E">Edward Kreinar</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Z">Zhenbin Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2008.03601v2-abstract-short" style="display: inline;"> Graph neural networks have been shown to achieve excellent performance for several crucial tasks in particle physics, such as charged particle tracking, jet tagging, and clustering. An important domain for the application of these networks is the FGPA-based first layer of real-time data filtering at the CERN Large Hadron Collider, which has strict latency and resource constraints. We discuss how t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.03601v2-abstract-full').style.display = 'inline'; document.getElementById('2008.03601v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2008.03601v2-abstract-full" style="display: none;"> Graph neural networks have been shown to achieve excellent performance for several crucial tasks in particle physics, such as charged particle tracking, jet tagging, and clustering. An important domain for the application of these networks is the FGPA-based first layer of real-time data filtering at the CERN Large Hadron Collider, which has strict latency and resource constraints. We discuss how to design distance-weighted graph networks that can be executed with a latency of less than 1$渭\mathrm{s}$ on an FPGA. To do so, we consider a representative task associated to particle reconstruction and identification in a next-generation calorimeter operating at a particle collider. We use a graph network architecture developed for such purposes, and apply additional simplifications to match the computing constraints of Level-1 trigger systems, including weight quantization. Using the $\mathtt{hls4ml}$ library, we convert the compressed models into firmware to be implemented on an FPGA. Performance of the synthesized models is presented both in terms of inference accuracy and resource usage. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.03601v2-abstract-full').style.display = 'none'; document.getElementById('2008.03601v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 February, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 August, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 pages, 4 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> FERMILAB-PUB-20-405-E-SCD </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Frontiers in Big Data 3 (2021) 44 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2003.06308">arXiv:2003.06308</a> <span> [<a href="https://arxiv.org/pdf/2003.06308">pdf</a>, <a href="https://arxiv.org/format/2003.06308">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1088/2632-2153/aba042">10.1088/2632-2153/aba042 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Compressing deep neural networks on FPGAs to binary and ternary precision with HLS4ML </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Di+Guglielmo%2C+G">Giuseppe Di Guglielmo</a>, <a href="/search/cs?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/cs?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/cs?searchtype=author&query=Hoang%2C+D">Duc Hoang</a>, <a href="/search/cs?searchtype=author&query=Jindariani%2C+S">Sergo Jindariani</a>, <a href="/search/cs?searchtype=author&query=Kreinar%2C+E">Edward Kreinar</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Mia Liu</a>, <a href="/search/cs?searchtype=author&query=Loncar%2C+V">Vladimir Loncar</a>, <a href="/search/cs?searchtype=author&query=Ngadiuba%2C+J">Jennifer Ngadiuba</a>, <a href="/search/cs?searchtype=author&query=Pedro%2C+K">Kevin Pedro</a>, <a href="/search/cs?searchtype=author&query=Pierini%2C+M">Maurizio Pierini</a>, <a href="/search/cs?searchtype=author&query=Rankin%2C+D">Dylan Rankin</a>, <a href="/search/cs?searchtype=author&query=Sagear%2C+S">Sheila Sagear</a>, <a href="/search/cs?searchtype=author&query=Summers%2C+S">Sioni Summers</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Z">Zhenbin Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2003.06308v2-abstract-short" style="display: inline;"> We present the implementation of binary and ternary neural networks in the hls4ml library, designed to automatically convert deep neural network models to digital circuits with FPGA firmware. Starting from benchmark models trained with floating point precision, we investigate different strategies to reduce the network's resource consumption by reducing the numerical precision of the network parame… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2003.06308v2-abstract-full').style.display = 'inline'; document.getElementById('2003.06308v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2003.06308v2-abstract-full" style="display: none;"> We present the implementation of binary and ternary neural networks in the hls4ml library, designed to automatically convert deep neural network models to digital circuits with FPGA firmware. Starting from benchmark models trained with floating point precision, we investigate different strategies to reduce the network's resource consumption by reducing the numerical precision of the network parameters to binary or ternary. We discuss the trade-off between model accuracy and resource consumption. In addition, we show how to balance between latency and accuracy by retaining full precision on a selected subset of network components. As an example, we consider two multiclass classification tasks: handwritten digit recognition with the MNIST data set and jet identification with simulated proton-proton collisions at the CERN Large Hadron Collider. The binary and ternary implementation has similar performance to the higher precision implementation while using drastically fewer FPGA resources. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2003.06308v2-abstract-full').style.display = 'none'; document.getElementById('2003.06308v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 March, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Update to MLST journal version</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> FERMILAB-PUB-20-167-PPD-SCD </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Mach. Learn.: Sci. Technol. 2, 015001 (2020) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2002.02534">arXiv:2002.02534</a> <span> [<a href="https://arxiv.org/pdf/2002.02534">pdf</a>, <a href="https://arxiv.org/format/2002.02534">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Physics">physics.comp-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Instrumentation and Methods for Astrophysics">astro-ph.IM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1088/1748-0221/15/05/p05026">10.1088/1748-0221/15/05/p05026 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Fast inference of Boosted Decision Trees in FPGAs for particle physics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Summers%2C+S">Sioni Summers</a>, <a href="/search/cs?searchtype=author&query=Di+Guglielmo%2C+G">Giuseppe Di Guglielmo</a>, <a href="/search/cs?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/cs?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/cs?searchtype=author&query=Hoang%2C+D">Duc Hoang</a>, <a href="/search/cs?searchtype=author&query=Jindariani%2C+S">Sergo Jindariani</a>, <a href="/search/cs?searchtype=author&query=Kreinar%2C+E">Edward Kreinar</a>, <a href="/search/cs?searchtype=author&query=Loncar%2C+V">Vladimir Loncar</a>, <a href="/search/cs?searchtype=author&query=Ngadiuba%2C+J">Jennifer Ngadiuba</a>, <a href="/search/cs?searchtype=author&query=Pierini%2C+M">Maurizio Pierini</a>, <a href="/search/cs?searchtype=author&query=Rankin%2C+D">Dylan Rankin</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Z">Zhenbin Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2002.02534v2-abstract-short" style="display: inline;"> We describe the implementation of Boosted Decision Trees in the hls4ml library, which allows the translation of a trained model into FPGA firmware through an automated conversion process. Thanks to its fully on-chip implementation, hls4ml performs inference of Boosted Decision Tree models with extremely low latency. With a typical latency less than 100 ns, this solution is suitable for FPGA-based… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.02534v2-abstract-full').style.display = 'inline'; document.getElementById('2002.02534v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2002.02534v2-abstract-full" style="display: none;"> We describe the implementation of Boosted Decision Trees in the hls4ml library, which allows the translation of a trained model into FPGA firmware through an automated conversion process. Thanks to its fully on-chip implementation, hls4ml performs inference of Boosted Decision Tree models with extremely low latency. With a typical latency less than 100 ns, this solution is suitable for FPGA-based real-time processing, such as in the Level-1 Trigger system of a collider experiment. These developments open up prospects for physicists to deploy BDTs in FPGAs for identifying the origin of jets, better reconstructing the energies of muons, and enabling better selection of rare signal processes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.02534v2-abstract-full').style.display = 'none'; document.getElementById('2002.02534v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> JINST 15 P05026 (2020) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1804.06913">arXiv:1804.06913</a> <span> [<a href="https://arxiv.org/pdf/1804.06913">pdf</a>, <a href="https://arxiv.org/format/1804.06913">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Instrumentation and Detectors">physics.ins-det</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="High Energy Physics - Experiment">hep-ex</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1088/1748-0221/13/07/P07027">10.1088/1748-0221/13/07/P07027 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Fast inference of deep neural networks in FPGAs for particle physics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/cs?searchtype=author&query=Han%2C+S">Song Han</a>, <a href="/search/cs?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/cs?searchtype=author&query=Jindariani%2C+S">Sergo Jindariani</a>, <a href="/search/cs?searchtype=author&query=Kreinar%2C+E">Edward Kreinar</a>, <a href="/search/cs?searchtype=author&query=Kreis%2C+B">Benjamin Kreis</a>, <a href="/search/cs?searchtype=author&query=Ngadiuba%2C+J">Jennifer Ngadiuba</a>, <a href="/search/cs?searchtype=author&query=Pierini%2C+M">Maurizio Pierini</a>, <a href="/search/cs?searchtype=author&query=Rivera%2C+R">Ryan Rivera</a>, <a href="/search/cs?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+Z">Zhenbin Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1804.06913v3-abstract-short" style="display: inline;"> Recent results at the Large Hadron Collider (LHC) have pointed to enhanced physics capabilities through the improvement of the real-time event processing techniques. Machine learning methods are ubiquitous and have proven to be very powerful in LHC physics, and particle physics as a whole. However, exploration of the use of such techniques in low-latency, low-power FPGA hardware has only just begu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1804.06913v3-abstract-full').style.display = 'inline'; document.getElementById('1804.06913v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1804.06913v3-abstract-full" style="display: none;"> Recent results at the Large Hadron Collider (LHC) have pointed to enhanced physics capabilities through the improvement of the real-time event processing techniques. Machine learning methods are ubiquitous and have proven to be very powerful in LHC physics, and particle physics as a whole. However, exploration of the use of such techniques in low-latency, low-power FPGA hardware has only just begun. FPGA-based trigger and data acquisition (DAQ) systems have extremely low, sub-microsecond latency requirements that are unique to particle physics. We present a case study for neural network inference in FPGAs focusing on a classifier for jet substructure which would enable, among many other physics scenarios, searches for new dark sector particles and novel measurements of the Higgs boson. While we focus on a specific example, the lessons are far-reaching. We develop a package based on High-Level Synthesis (HLS) called hls4ml to build machine learning models in FPGAs. The use of HLS increases accessibility across a broad user community and allows for a drastic decrease in firmware development time. We map out FPGA resource usage and latency versus neural network hyperparameters to identify the problems in particle physics that would benefit from performing neural network inference with FPGAs. For our example jet substructure model, we fit well within the available resources of modern FPGAs with a latency on the scale of 100 ns. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1804.06913v3-abstract-full').style.display = 'none'; document.getElementById('1804.06913v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 June, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 April, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">22 pages, 17 figures, 2 tables, JINST revision</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> FERMILAB-PUB-18-089-E </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> JINST 13 P07027 (2018) </p> </li> </ol> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository