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 1–10 of 10 results for author: <span class="mathjax">Hauck, 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/physics" aria-role="search"> Searching in archive <strong>physics</strong>. <a href="/search/?searchtype=author&query=Hauck%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="Hauck, 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=Hauck%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="Hauck, 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/2406.12875">arXiv:2406.12875</a> <span> [<a href="https://arxiv.org/pdf/2406.12875">pdf</a>, <a href="https://arxiv.org/format/2406.12875">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="High Energy Physics - Experiment">hep-ex</span> </div> </div> <p class="title is-5 mathjax"> Machine learning evaluation in the Global Event Processor FPGA for the ATLAS trigger upgrade </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/physics?searchtype=author&query=Jiang%2C+Z">Zhixing Jiang</a>, <a href="/search/physics?searchtype=author&query=Hauck%2C+S">Scott Hauck</a>, <a href="/search/physics?searchtype=author&query=Yin%2C+D">Dennis Yin</a>, <a href="/search/physics?searchtype=author&query=Zuo%2C+B">Bowen Zuo</a>, <a href="/search/physics?searchtype=author&query=Carlson%2C+B">Ben Carlson</a>, <a href="/search/physics?searchtype=author&query=Hsu%2C+S">Shih-Chieh Hsu</a>, <a href="/search/physics?searchtype=author&query=Deiana%2C+A">Allison Deiana</a>, <a href="/search/physics?searchtype=author&query=Narayan%2C+R">Rohin Narayan</a>, <a href="/search/physics?searchtype=author&query=Parajuli%2C+S">Santosh Parajuli</a>, <a href="/search/physics?searchtype=author&query=Eastlack%2C+J">Jeff Eastlack</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="2406.12875v1-abstract-short" style="display: inline;"> The Global Event Processor (GEP) FPGA is an area-constrained, performance-critical element of the Large Hadron Collider's (LHC) ATLAS experiment. It needs to very quickly determine which small fraction of detected events should be retained for further processing, and which other events will be discarded. This system involves a large number of individual processing tasks, brought together within th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.12875v1-abstract-full').style.display = 'inline'; document.getElementById('2406.12875v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.12875v1-abstract-full" style="display: none;"> The Global Event Processor (GEP) FPGA is an area-constrained, performance-critical element of the Large Hadron Collider's (LHC) ATLAS experiment. It needs to very quickly determine which small fraction of detected events should be retained for further processing, and which other events will be discarded. This system involves a large number of individual processing tasks, brought together within the overall Algorithm Processing Platform (APP), to make filtering decisions at an overall latency of no more than 8ms. Currently, such filtering tasks are hand-coded implementations of standard deterministic signal processing tasks. In this paper we present methods to automatically create machine learning based algorithms for use within the APP framework, and demonstrate several successful such deployments. We leverage existing machine learning to FPGA flows such as hls4ml and fwX to significantly reduce the complexity of algorithm design. These have resulted in implementations of various machine learning algorithms with latencies of 1.2us and less than 5% resource utilization on an Xilinx XCVU9P FPGA. Finally, we implement these algorithms into the GEP system and present their actual performance. Our work shows the potential of using machine learning in the GEP for high-energy physics applications. This can significantly improve the performance of the trigger system and enable the ATLAS experiment to collect more data and make more discoveries. The architecture and approach presented in this paper can also be applied to other applications that require real-time processing of large volumes of data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.12875v1-abstract-full').style.display = 'none'; document.getElementById('2406.12875v1-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> 7 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </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">14 pages, 4 figures, 6 tables. Accepted by JINST on April 3, 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.00559">arXiv:2207.00559</a> <span> [<a href="https://arxiv.org/pdf/2207.00559">pdf</a>, <a href="https://arxiv.org/format/2207.00559">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="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> <p class="title is-5 mathjax"> Ultra-low latency recurrent neural network inference on FPGAs for physics applications with hls4ml </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/physics?searchtype=author&query=Khoda%2C+E+E">Elham E Khoda</a>, <a href="/search/physics?searchtype=author&query=Rankin%2C+D">Dylan Rankin</a>, <a href="/search/physics?searchtype=author&query=de+Lima%2C+R+T">Rafael Teixeira de Lima</a>, <a href="/search/physics?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/physics?searchtype=author&query=Hauck%2C+S">Scott Hauck</a>, <a href="/search/physics?searchtype=author&query=Hsu%2C+S">Shih-Chieh Hsu</a>, <a href="/search/physics?searchtype=author&query=Kagan%2C+M">Michael Kagan</a>, <a href="/search/physics?searchtype=author&query=Loncar%2C+V">Vladimir Loncar</a>, <a href="/search/physics?searchtype=author&query=Paikara%2C+C">Chaitanya Paikara</a>, <a href="/search/physics?searchtype=author&query=Rao%2C+R">Richa Rao</a>, <a href="/search/physics?searchtype=author&query=Summers%2C+S">Sioni Summers</a>, <a href="/search/physics?searchtype=author&query=Vernieri%2C+C">Caterina Vernieri</a>, <a href="/search/physics?searchtype=author&query=Wang%2C+A">Aaron Wang</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="2207.00559v1-abstract-short" style="display: inline;"> Recurrent neural networks have been shown to be effective architectures for many tasks in high energy physics, and thus have been widely adopted. Their use in low-latency environments has, however, been limited as a result of the difficulties of implementing recurrent architectures on field-programmable gate arrays (FPGAs). In this paper we present an implementation of two types of recurrent neura… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.00559v1-abstract-full').style.display = 'inline'; document.getElementById('2207.00559v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.00559v1-abstract-full" style="display: none;"> Recurrent neural networks have been shown to be effective architectures for many tasks in high energy physics, and thus have been widely adopted. Their use in low-latency environments has, however, been limited as a result of the difficulties of implementing recurrent architectures on field-programmable gate arrays (FPGAs). In this paper we present an implementation of two types of recurrent neural network layers -- long short-term memory and gated recurrent unit -- within the hls4ml framework. We demonstrate that our implementation is capable of producing effective designs for both small and large models, and can be customized to meet specific design requirements for inference latencies and FPGA resources. We show the performance and synthesized designs for multiple neural networks, many of which are trained specifically for jet identification tasks at the CERN Large Hadron Collider. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.00559v1-abstract-full').style.display = 'none'; document.getElementById('2207.00559v1-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> 1 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2022. </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">12 pages, 6 figures, 5 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.16255">arXiv:2203.16255</a> <span> [<a href="https://arxiv.org/pdf/2203.16255">pdf</a>, <a href="https://arxiv.org/format/2203.16255">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="General Relativity and Quantum Cosmology">gr-qc</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> </div> </div> <p class="title is-5 mathjax"> Physics Community Needs, Tools, and Resources for Machine Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/physics?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/physics?searchtype=author&query=Katsavounidis%2C+E">Erik Katsavounidis</a>, <a href="/search/physics?searchtype=author&query=McCormack%2C+W+P">William Patrick McCormack</a>, <a href="/search/physics?searchtype=author&query=Rankin%2C+D">Dylan Rankin</a>, <a href="/search/physics?searchtype=author&query=Feng%2C+Y">Yongbin Feng</a>, <a href="/search/physics?searchtype=author&query=Gandrakota%2C+A">Abhijith Gandrakota</a>, <a href="/search/physics?searchtype=author&query=Herwig%2C+C">Christian Herwig</a>, <a href="/search/physics?searchtype=author&query=Holzman%2C+B">Burt Holzman</a>, <a href="/search/physics?searchtype=author&query=Pedro%2C+K">Kevin Pedro</a>, <a href="/search/physics?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/physics?searchtype=author&query=Yang%2C+T">Tingjun Yang</a>, <a href="/search/physics?searchtype=author&query=Ngadiuba%2C+J">Jennifer Ngadiuba</a>, <a href="/search/physics?searchtype=author&query=Coughlin%2C+M">Michael Coughlin</a>, <a href="/search/physics?searchtype=author&query=Hauck%2C+S">Scott Hauck</a>, <a href="/search/physics?searchtype=author&query=Hsu%2C+S">Shih-Chieh Hsu</a>, <a href="/search/physics?searchtype=author&query=Khoda%2C+E+E">Elham E Khoda</a>, <a href="/search/physics?searchtype=author&query=Chen%2C+D">Deming Chen</a>, <a href="/search/physics?searchtype=author&query=Neubauer%2C+M">Mark Neubauer</a>, <a href="/search/physics?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/physics?searchtype=author&query=Karagiorgi%2C+G">Georgia Karagiorgi</a>, <a href="/search/physics?searchtype=author&query=Liu%2C+M">Mia Liu</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="2203.16255v1-abstract-short" style="display: inline;"> Machine learning (ML) is becoming an increasingly important component of cutting-edge physics research, but its computational requirements present significant challenges. In this white paper, we discuss the needs of the physics community regarding ML across latency and throughput regimes, the tools and resources that offer the possibility of addressing these needs, and how these can be best utiliz… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.16255v1-abstract-full').style.display = 'inline'; document.getElementById('2203.16255v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.16255v1-abstract-full" style="display: none;"> Machine learning (ML) is becoming an increasingly important component of cutting-edge physics research, but its computational requirements present significant challenges. In this white paper, we discuss the needs of the physics community regarding ML across latency and throughput regimes, the tools and resources that offer the possibility of addressing these needs, and how these can be best utilized and accessed in the coming years. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.16255v1-abstract-full').style.display = 'none'; document.getElementById('2203.16255v1-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 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2022. </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">Contribution to Snowmass 2021, 33 pages, 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.02048">arXiv:2112.02048</a> <span> [<a href="https://arxiv.org/pdf/2112.02048">pdf</a>, <a href="https://arxiv.org/format/2112.02048">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="Hardware Architecture">cs.AR</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="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/10.3389/fdata.2022.828666">10.3389/fdata.2022.828666 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Graph Neural Networks for Charged Particle Tracking on FPGAs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/physics?searchtype=author&query=Elabd%2C+A">Abdelrahman Elabd</a>, <a href="/search/physics?searchtype=author&query=Razavimaleki%2C+V">Vesal Razavimaleki</a>, <a href="/search/physics?searchtype=author&query=Huang%2C+S">Shi-Yu Huang</a>, <a href="/search/physics?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/physics?searchtype=author&query=Atkinson%2C+M">Markus Atkinson</a>, <a href="/search/physics?searchtype=author&query=DeZoort%2C+G">Gage DeZoort</a>, <a href="/search/physics?searchtype=author&query=Elmer%2C+P">Peter Elmer</a>, <a href="/search/physics?searchtype=author&query=Hauck%2C+S">Scott Hauck</a>, <a href="/search/physics?searchtype=author&query=Hu%2C+J">Jin-Xuan Hu</a>, <a href="/search/physics?searchtype=author&query=Hsu%2C+S">Shih-Chieh Hsu</a>, <a href="/search/physics?searchtype=author&query=Lai%2C+B">Bo-Cheng Lai</a>, <a href="/search/physics?searchtype=author&query=Neubauer%2C+M">Mark Neubauer</a>, <a href="/search/physics?searchtype=author&query=Ojalvo%2C+I">Isobel Ojalvo</a>, <a href="/search/physics?searchtype=author&query=Thais%2C+S">Savannah Thais</a>, <a href="/search/physics?searchtype=author&query=Trahms%2C+M">Matthew Trahms</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="2112.02048v3-abstract-short" style="display: inline;"> The determination of charged particle trajectories in collisions at the CERN Large Hadron Collider (LHC) is an important but challenging problem, especially in the high interaction density conditions expected during the future high-luminosity phase of the LHC (HL-LHC). Graph neural networks (GNNs) are a type of geometric deep learning algorithm that has successfully been applied to this task by em… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.02048v3-abstract-full').style.display = 'inline'; document.getElementById('2112.02048v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.02048v3-abstract-full" style="display: none;"> The determination of charged particle trajectories in collisions at the CERN Large Hadron Collider (LHC) is an important but challenging problem, especially in the high interaction density conditions expected during the future high-luminosity phase of the LHC (HL-LHC). Graph neural networks (GNNs) are a type of geometric deep learning algorithm that has successfully been applied to this task by embedding tracker data as a graph -- nodes represent hits, while edges represent possible track segments -- and classifying the edges as true or fake track segments. However, their study in hardware- or software-based trigger applications has been limited due to their large computational cost. In this paper, we introduce an automated translation workflow, integrated into a broader tool called $\texttt{hls4ml}$, for converting GNNs into firmware for field-programmable gate arrays (FPGAs). We use this translation tool to implement GNNs for charged particle tracking, trained using the TrackML challenge dataset, on FPGAs with designs targeting different graph sizes, task complexites, and latency/throughput requirements. This work could enable the inclusion of charged particle tracking GNNs at the trigger level for HL-LHC experiments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.02048v3-abstract-full').style.display = 'none'; document.getElementById('2112.02048v3-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">28 pages, 17 figures, 1 table, published version</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Front. Big Data 5 (2022) 828666 </p> </li> <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/physics?searchtype=author&query=Deiana%2C+A+M">Allison McCarn Deiana</a>, <a href="/search/physics?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/physics?searchtype=author&query=Agar%2C+J">Joshua Agar</a>, <a href="/search/physics?searchtype=author&query=Blott%2C+M">Michaela Blott</a>, <a href="/search/physics?searchtype=author&query=Di+Guglielmo%2C+G">Giuseppe Di Guglielmo</a>, <a href="/search/physics?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/physics?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/physics?searchtype=author&query=Hauck%2C+S">Scott Hauck</a>, <a href="/search/physics?searchtype=author&query=Liu%2C+M">Mia Liu</a>, <a href="/search/physics?searchtype=author&query=Neubauer%2C+M+S">Mark S. Neubauer</a>, <a href="/search/physics?searchtype=author&query=Ngadiuba%2C+J">Jennifer Ngadiuba</a>, <a href="/search/physics?searchtype=author&query=Ogrenci-Memik%2C+S">Seda Ogrenci-Memik</a>, <a href="/search/physics?searchtype=author&query=Pierini%2C+M">Maurizio Pierini</a>, <a href="/search/physics?searchtype=author&query=Aarrestad%2C+T">Thea Aarrestad</a>, <a href="/search/physics?searchtype=author&query=Bahr%2C+S">Steffen Bahr</a>, <a href="/search/physics?searchtype=author&query=Becker%2C+J">Jurgen Becker</a>, <a href="/search/physics?searchtype=author&query=Berthold%2C+A">Anne-Sophie Berthold</a>, <a href="/search/physics?searchtype=author&query=Bonventre%2C+R+J">Richard J. Bonventre</a>, <a href="/search/physics?searchtype=author&query=Bravo%2C+T+E+M">Tomas E. Muller Bravo</a>, <a href="/search/physics?searchtype=author&query=Diefenthaler%2C+M">Markus Diefenthaler</a>, <a href="/search/physics?searchtype=author&query=Dong%2C+Z">Zhen Dong</a>, <a href="/search/physics?searchtype=author&query=Fritzsche%2C+N">Nick Fritzsche</a>, <a href="/search/physics?searchtype=author&query=Gholami%2C+A">Amir Gholami</a>, <a href="/search/physics?searchtype=author&query=Govorkova%2C+E">Ekaterina Govorkova</a>, <a href="/search/physics?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/physics?searchtype=author&query=Fahim%2C+F">Farah Fahim</a>, <a href="/search/physics?searchtype=author&query=Hawks%2C+B">Benjamin Hawks</a>, <a href="/search/physics?searchtype=author&query=Herwig%2C+C">Christian Herwig</a>, <a href="/search/physics?searchtype=author&query=Hirschauer%2C+J">James Hirschauer</a>, <a href="/search/physics?searchtype=author&query=Jindariani%2C+S">Sergo Jindariani</a>, <a href="/search/physics?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/physics?searchtype=author&query=Carloni%2C+L+P">Luca P. Carloni</a>, <a href="/search/physics?searchtype=author&query=Di+Guglielmo%2C+G">Giuseppe Di Guglielmo</a>, <a href="/search/physics?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/physics?searchtype=author&query=Krupa%2C+J">Jeffrey Krupa</a>, <a href="/search/physics?searchtype=author&query=Rankin%2C+D">Dylan Rankin</a>, <a href="/search/physics?searchtype=author&query=Valentin%2C+M+B">Manuel Blanco Valentin</a>, <a href="/search/physics?searchtype=author&query=Hester%2C+J">Josiah Hester</a>, <a href="/search/physics?searchtype=author&query=Luo%2C+Y">Yingyi Luo</a>, <a href="/search/physics?searchtype=author&query=Mamish%2C+J">John Mamish</a>, <a href="/search/physics?searchtype=author&query=Orgrenci-Memik%2C+S">Seda Orgrenci-Memik</a>, <a href="/search/physics?searchtype=author&query=Aarrestad%2C+T">Thea Aarrestad</a>, <a href="/search/physics?searchtype=author&query=Javed%2C+H">Hamza Javed</a>, <a href="/search/physics?searchtype=author&query=Loncar%2C+V">Vladimir Loncar</a>, <a href="/search/physics?searchtype=author&query=Pierini%2C+M">Maurizio Pierini</a>, <a href="/search/physics?searchtype=author&query=Pol%2C+A+A">Adrian Alan Pol</a>, <a href="/search/physics?searchtype=author&query=Summers%2C+S">Sioni Summers</a>, <a href="/search/physics?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/physics?searchtype=author&query=Hauck%2C+S">Scott Hauck</a>, <a href="/search/physics?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/2010.08556">arXiv:2010.08556</a> <span> [<a href="https://arxiv.org/pdf/2010.08556">pdf</a>, <a href="https://arxiv.org/format/2010.08556">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="Distributed, Parallel, and Cluster Computing">cs.DC</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="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/10.1109/H2RC51942.2020.00010">10.1109/H2RC51942.2020.00010 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> FPGAs-as-a-Service Toolkit (FaaST) </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/physics?searchtype=author&query=Rankin%2C+D+S">Dylan Sheldon Rankin</a>, <a href="/search/physics?searchtype=author&query=Krupa%2C+J">Jeffrey Krupa</a>, <a href="/search/physics?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/physics?searchtype=author&query=Flechas%2C+M+A">Maria Acosta Flechas</a>, <a href="/search/physics?searchtype=author&query=Holzman%2C+B">Burt Holzman</a>, <a href="/search/physics?searchtype=author&query=Klijnsma%2C+T">Thomas Klijnsma</a>, <a href="/search/physics?searchtype=author&query=Pedro%2C+K">Kevin Pedro</a>, <a href="/search/physics?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/physics?searchtype=author&query=Hauck%2C+S">Scott Hauck</a>, <a href="/search/physics?searchtype=author&query=Hsu%2C+S">Shih-Chieh Hsu</a>, <a href="/search/physics?searchtype=author&query=Trahms%2C+M">Matthew Trahms</a>, <a href="/search/physics?searchtype=author&query=Lin%2C+K">Kelvin Lin</a>, <a href="/search/physics?searchtype=author&query=Lou%2C+Y">Yu Lou</a>, <a href="/search/physics?searchtype=author&query=Ho%2C+T">Ta-Wei Ho</a>, <a href="/search/physics?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/physics?searchtype=author&query=Liu%2C+M">Mia Liu</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="2010.08556v1-abstract-short" style="display: inline;"> Computing needs for high energy physics are already intensive and are expected to increase drastically in the coming years. In this context, heterogeneous computing, specifically as-a-service computing, has the potential for significant gains over traditional computing models. Although previous studies and packages in the field of heterogeneous computing have focused on GPUs as accelerators, FPGAs… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.08556v1-abstract-full').style.display = 'inline'; document.getElementById('2010.08556v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2010.08556v1-abstract-full" style="display: none;"> Computing needs for high energy physics are already intensive and are expected to increase drastically in the coming years. In this context, heterogeneous computing, specifically as-a-service computing, has the potential for significant gains over traditional computing models. Although previous studies and packages in the field of heterogeneous computing have focused on GPUs as accelerators, FPGAs are an extremely promising option as well. A series of workflows are developed to establish the performance capabilities of FPGAs as a service. Multiple different devices and a range of algorithms for use in high energy physics are studied. For a small, dense network, the throughput can be improved by an order of magnitude with respect to GPUs as a service. For large convolutional networks, the throughput is found to be comparable to GPUs as a service. This work represents the first open-source FPGAs-as-a-service toolkit. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.08556v1-abstract-full').style.display = 'none'; document.getElementById('2010.08556v1-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> 16 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 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">10 pages, 7 figures, to appear in proceedings of the 2020 IEEE/ACM International Workshop on Heterogeneous High-performance Reconfigurable Computing</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> FERMILAB-CONF-20-426-SCD </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2020 IEEE/ACM International Workshop on Heterogeneous High-performance Reconfigurable Computing (H2RC), 2020, pp. 38-47 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2007.10359">arXiv:2007.10359</a> <span> [<a href="https://arxiv.org/pdf/2007.10359">pdf</a>, <a href="https://arxiv.org/format/2007.10359">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="Distributed, Parallel, and Cluster Computing">cs.DC</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="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/10.1088/2632-2153/abec21">10.1088/2632-2153/abec21 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> GPU coprocessors as a service for deep learning inference in high energy physics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/physics?searchtype=author&query=Krupa%2C+J">Jeffrey Krupa</a>, <a href="/search/physics?searchtype=author&query=Lin%2C+K">Kelvin Lin</a>, <a href="/search/physics?searchtype=author&query=Flechas%2C+M+A">Maria Acosta Flechas</a>, <a href="/search/physics?searchtype=author&query=Dinsmore%2C+J">Jack Dinsmore</a>, <a href="/search/physics?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/physics?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/physics?searchtype=author&query=Hauck%2C+S">Scott Hauck</a>, <a href="/search/physics?searchtype=author&query=Holzman%2C+B">Burt Holzman</a>, <a href="/search/physics?searchtype=author&query=Hsu%2C+S">Shih-Chieh Hsu</a>, <a href="/search/physics?searchtype=author&query=Klijnsma%2C+T">Thomas Klijnsma</a>, <a href="/search/physics?searchtype=author&query=Liu%2C+M">Mia Liu</a>, <a href="/search/physics?searchtype=author&query=Pedro%2C+K">Kevin Pedro</a>, <a href="/search/physics?searchtype=author&query=Rankin%2C+D">Dylan Rankin</a>, <a href="/search/physics?searchtype=author&query=Suaysom%2C+N">Natchanon Suaysom</a>, <a href="/search/physics?searchtype=author&query=Trahms%2C+M">Matt Trahms</a>, <a href="/search/physics?searchtype=author&query=Tran%2C+N">Nhan Tran</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="2007.10359v2-abstract-short" style="display: inline;"> In the next decade, the demands for computing in large scientific experiments are expected to grow tremendously. During the same time period, CPU performance increases will be limited. At the CERN Large Hadron Collider (LHC), these two issues will confront one another as the collider is upgraded for high luminosity running. Alternative processors such as graphics processing units (GPUs) can resolv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.10359v2-abstract-full').style.display = 'inline'; document.getElementById('2007.10359v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2007.10359v2-abstract-full" style="display: none;"> In the next decade, the demands for computing in large scientific experiments are expected to grow tremendously. During the same time period, CPU performance increases will be limited. At the CERN Large Hadron Collider (LHC), these two issues will confront one another as the collider is upgraded for high luminosity running. Alternative processors such as graphics processing units (GPUs) can resolve this confrontation provided that algorithms can be sufficiently accelerated. In many cases, algorithmic speedups are found to be largest through the adoption of deep learning algorithms. We present a comprehensive exploration of the use of GPU-based hardware acceleration for deep learning inference within the data reconstruction workflow of high energy physics. We present several realistic examples and discuss a strategy for the seamless integration of coprocessors so that the LHC can maintain, if not exceed, its current performance throughout its running. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.10359v2-abstract-full').style.display = 'none'; document.getElementById('2007.10359v2-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 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 July, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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">26 pages, 7 figures, 2 tables</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> FERMILAB-PUB-20-338-E-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 (2021) 035005 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1904.08986">arXiv:1904.08986</a> <span> [<a href="https://arxiv.org/pdf/1904.08986">pdf</a>, <a href="https://arxiv.org/format/1904.08986">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="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> <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/10.1007/s41781-019-0027-2">10.1007/s41781-019-0027-2 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> FPGA-accelerated machine learning inference as a service for particle physics computing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/physics?searchtype=author&query=Duarte%2C+J">Javier Duarte</a>, <a href="/search/physics?searchtype=author&query=Harris%2C+P">Philip Harris</a>, <a href="/search/physics?searchtype=author&query=Hauck%2C+S">Scott Hauck</a>, <a href="/search/physics?searchtype=author&query=Holzman%2C+B">Burt Holzman</a>, <a href="/search/physics?searchtype=author&query=Hsu%2C+S">Shih-Chieh Hsu</a>, <a href="/search/physics?searchtype=author&query=Jindariani%2C+S">Sergo Jindariani</a>, <a href="/search/physics?searchtype=author&query=Khan%2C+S">Suffian Khan</a>, <a href="/search/physics?searchtype=author&query=Kreis%2C+B">Benjamin Kreis</a>, <a href="/search/physics?searchtype=author&query=Lee%2C+B">Brian Lee</a>, <a href="/search/physics?searchtype=author&query=Liu%2C+M">Mia Liu</a>, <a href="/search/physics?searchtype=author&query=Lon%C4%8Dar%2C+V">Vladimir Lon膷ar</a>, <a href="/search/physics?searchtype=author&query=Ngadiuba%2C+J">Jennifer Ngadiuba</a>, <a href="/search/physics?searchtype=author&query=Pedro%2C+K">Kevin Pedro</a>, <a href="/search/physics?searchtype=author&query=Perez%2C+B">Brandon Perez</a>, <a href="/search/physics?searchtype=author&query=Pierini%2C+M">Maurizio Pierini</a>, <a href="/search/physics?searchtype=author&query=Rankin%2C+D">Dylan Rankin</a>, <a href="/search/physics?searchtype=author&query=Tran%2C+N">Nhan Tran</a>, <a href="/search/physics?searchtype=author&query=Trahms%2C+M">Matthew Trahms</a>, <a href="/search/physics?searchtype=author&query=Tsaris%2C+A">Aristeidis Tsaris</a>, <a href="/search/physics?searchtype=author&query=Versteeg%2C+C">Colin Versteeg</a>, <a href="/search/physics?searchtype=author&query=Way%2C+T+W">Ted W. Way</a>, <a href="/search/physics?searchtype=author&query=Werran%2C+D">Dustin Werran</a>, <a href="/search/physics?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="1904.08986v2-abstract-short" style="display: inline;"> New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of mach… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.08986v2-abstract-full').style.display = 'inline'; document.getElementById('1904.08986v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1904.08986v2-abstract-full" style="display: none;"> New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that potentially requires minimal modification to the current computing model. As examples, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC and apply a ResNet-50 model with transfer learning for neutrino event classification. Using Project Brainwave by Microsoft to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) milliseconds with our experimental physics software framework using Brainwave as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600--700 inferences per second using an image batch of one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.08986v2-abstract-full').style.display = 'none'; document.getElementById('1904.08986v2-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> 16 October, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 April, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2019. </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">16 pages, 14 figures, 2 tables</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> FERMILAB-PUB-19-170-CD-CMS-E-ND </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Comput Softw Big Sci (2019) 3: 13 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1803.00844">arXiv:1803.00844</a> <span> [<a href="https://arxiv.org/pdf/1803.00844">pdf</a>, <a href="https://arxiv.org/format/1803.00844">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="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/10.1088/1748-0221/13/05/T05008">10.1088/1748-0221/13/05/T05008 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Production and Integration of the ATLAS Insertable B-Layer </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/physics?searchtype=author&query=Abbott%2C+B">B. Abbott</a>, <a href="/search/physics?searchtype=author&query=Albert%2C+J">J. Albert</a>, <a href="/search/physics?searchtype=author&query=Alberti%2C+F">F. Alberti</a>, <a href="/search/physics?searchtype=author&query=Alex%2C+M">M. Alex</a>, <a href="/search/physics?searchtype=author&query=Alimonti%2C+G">G. Alimonti</a>, <a href="/search/physics?searchtype=author&query=Alkire%2C+S">S. Alkire</a>, <a href="/search/physics?searchtype=author&query=Allport%2C+P">P. Allport</a>, <a href="/search/physics?searchtype=author&query=Altenheiner%2C+S">S. Altenheiner</a>, <a href="/search/physics?searchtype=author&query=Ancu%2C+L">L. Ancu</a>, <a href="/search/physics?searchtype=author&query=Anderssen%2C+E">E. Anderssen</a>, <a href="/search/physics?searchtype=author&query=Andreani%2C+A">A. Andreani</a>, <a href="/search/physics?searchtype=author&query=Andreazza%2C+A">A. Andreazza</a>, <a href="/search/physics?searchtype=author&query=Axen%2C+B">B. Axen</a>, <a href="/search/physics?searchtype=author&query=Arguin%2C+J">J. Arguin</a>, <a href="/search/physics?searchtype=author&query=Backhaus%2C+M">M. Backhaus</a>, <a href="/search/physics?searchtype=author&query=Balbi%2C+G">G. Balbi</a>, <a href="/search/physics?searchtype=author&query=Ballansat%2C+J">J. Ballansat</a>, <a href="/search/physics?searchtype=author&query=Barbero%2C+M">M. Barbero</a>, <a href="/search/physics?searchtype=author&query=Barbier%2C+G">G. Barbier</a>, <a href="/search/physics?searchtype=author&query=Bassalat%2C+A">A. Bassalat</a>, <a href="/search/physics?searchtype=author&query=Bates%2C+R">R. Bates</a>, <a href="/search/physics?searchtype=author&query=Baudin%2C+P">P. Baudin</a>, <a href="/search/physics?searchtype=author&query=Battaglia%2C+M">M. Battaglia</a>, <a href="/search/physics?searchtype=author&query=Beau%2C+T">T. Beau</a>, <a href="/search/physics?searchtype=author&query=Beccherle%2C+R">R. Beccherle</a> , et al. (352 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="1803.00844v3-abstract-short" style="display: inline;"> During the shutdown of the CERN Large Hadron Collider in 2013-2014, an additional pixel layer was installed between the existing Pixel detector of the ATLAS experiment and a new, smaller radius beam pipe. The motivation for this new pixel layer, the Insertable B-Layer (IBL), was to maintain or improve the robustness and performance of the ATLAS tracking system, given the higher instantaneous and i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1803.00844v3-abstract-full').style.display = 'inline'; document.getElementById('1803.00844v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1803.00844v3-abstract-full" style="display: none;"> During the shutdown of the CERN Large Hadron Collider in 2013-2014, an additional pixel layer was installed between the existing Pixel detector of the ATLAS experiment and a new, smaller radius beam pipe. The motivation for this new pixel layer, the Insertable B-Layer (IBL), was to maintain or improve the robustness and performance of the ATLAS tracking system, given the higher instantaneous and integrated luminosities realised following the shutdown. Because of the extreme radiation and collision rate environment, several new radiation-tolerant sensor and electronic technologies were utilised for this layer. This paper reports on the IBL construction and integration prior to its operation in the ATLAS detector. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1803.00844v3-abstract-full').style.display = 'none'; document.getElementById('1803.00844v3-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> 6 June, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 March, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 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">90 pages in total. Author list: ATLAS IBL Collaboration, starting page 2. 69 figures, 20 tables. Published in Journal of Instrumentation. All figures available at: https://atlas.web.cern.ch/Atlas/GROUPS/PHYSICS/PLOTS/PIX-2018-001</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Journal of Instrumentation JINST 13 T05008 (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