{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T13:33:11Z","timestamp":1770816791564,"version":"3.50.1"},"reference-count":33,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T00:00:00Z","timestamp":1701216000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T00:00:00Z","timestamp":1701216000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004007","name":"Instituto Nazionale di Fisica Nucleare","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004007","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2023,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Experimental particle physics demands a sophisticated trigger and acquisition system capable to efficiently retain the collisions of interest for further investigation. Heterogeneous computing with the employment of FPGA cards may emerge as a trending technology for the triggering strategy of the upcoming high-luminosity program of the Large Hadron Collider at CERN In this context, we present two machine-learning algorithms for selecting events where neutral long-lived particles decay within the detector volume studying their accuracy and inference time when accelerated on commercially available Xilinx FPGA accelerator cards. The inference time is also confronted with a CPU- and GPU-based hardware setup. The proposed new algorithms are proven efficient for the considered benchmark physics scenario and their accuracy is found to not degrade when accelerated on the FPGA cards. The results indicate that all tested architectures fit within the latency requirements of a second-level trigger farm and that exploiting accelerator technologies for real-time processing of particle-physics collisions is a promising research field that deserves additional investigations, in particular with machine-learning models with a large number of trainable parameters.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad087a","type":"journal-article","created":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T22:45:16Z","timestamp":1698792316000},"page":"045040","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Fast neural network inference on FPGAs for triggering on long-lived particles at colliders"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2368-4559","authenticated-orcid":true,"given":"Andrea","family":"Coccaro","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9870-2021","authenticated-orcid":false,"given":"Francesco","family":"Armando Di Bello","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9192-3537","authenticated-orcid":true,"given":"Stefano","family":"Giagu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9155-9453","authenticated-orcid":false,"given":"Lucrezia","family":"Rambelli","sequence":"additional","affiliation":[]},{"given":"Nicola","family":"Stocchetti","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2023,11,29]]},"reference":[{"key":"mlstad087abib1","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/3\/08\/S08003","article-title":"The ATLAS Experiment at the CERN Large Hadron Collider","volume":"3","author":"ATLAS Collaboration","year":"2008","journal-title":"J. Instrum."},{"key":"mlstad087abib2","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/3\/08\/S08004","article-title":"The CMS experiment at the CERN LHC","volume":"3","author":"CMS Collaboration","year":"2008","journal-title":"J. Instrum."},{"key":"mlstad087abib3","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/3\/08\/S08001","article-title":"LHC machine","volume":"3","author":"Evans","year":"2008","journal-title":"J. Instrum."},{"key":"mlstad087abib4","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/15\/10\/P10004","article-title":"Operation of the ATLAS trigger system in Run 2","volume":"15","author":"ATLAS Collaboration","year":"2020","journal-title":"J. Instrum."},{"key":"mlstad087abib5","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/12\/01\/P01020","article-title":"The CMS trigger system","volume":"12","author":"CMS Collaboration","year":"2017","journal-title":"J. Instrum."},{"key":"mlstad087abib6","article-title":"High-Luminosity Large Hadron Collider (HL-LHC):","author":"Aberle","year":"2020"},{"key":"mlstad087abib7","author":"ATLAS Collaboration","year":"2022"},{"key":"mlstad087abib8","author":"CMS Collaboration","year":"2022"},{"key":"mlstad087abib9","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/s41781-019-0027-2","article-title":"FPGA-accelerated machine learning inference as a service for particle physics computing","volume":"3","author":"Duarte","year":"2019","journal-title":"Comput. Softw. Big Sci."},{"key":"mlstad087abib10","doi-asserted-by":"crossref","DOI":"10.1109\/H2RC51942.2020.00010","article-title":"FPGAs-as-a-service toolkit (FaaST)","author":"Rankin","year":"2020"},{"key":"mlstad087abib11","article-title":"Xilinx ML suite","author":"Xilinx","year":"2018"},{"key":"mlstad087abib12","article-title":"Xilinx Vitis-AI suite","year":"2023"},{"key":"mlstad087abib13","article-title":"Intel distribution of OpenVINO toolkit","author":"Intel","year":"2018"},{"key":"mlstad087abib14","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/aba042","article-title":"Compressing deep neural networks on FPGAs to binary and ternary precision with HLS4ML","volume":"2","author":"Loncar","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad087abib15","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac0ea1","article-title":"Fast convolutional neural networks on FPGAs with hls4ml","volume":"2","author":"Aarrestad","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad087abib16","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1140\/epjc\/s10052-021-09770-w","article-title":"Model compression and simplification pipelines for fast deep neural network inference in FPGAs in HEP","volume":"81","author":"Francescato","year":"2021","journal-title":"Eur. Phys. J. C"},{"key":"mlstad087abib17","author":"LLPinMS","year":"2023"},{"key":"mlstad087abib18","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6471\/ab4574","article-title":"Searching for long-lived particles beyond the standard model at the large hadron collider","volume":"47","author":"Alimena","year":"2020","journal-title":"J. Phys. G: Nucl. Part. Phys."},{"key":"mlstad087abib19","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1016\/j.physletb.2007.06.055","article-title":"Echoes of a hidden valley at hadron colliders","volume":"B651","author":"Strassler","year":"2007","journal-title":"Phys. Lett."},{"key":"mlstad087abib20","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1016\/j.physletb.2008.02.008","article-title":"Discovering the Higgs through highly-displaced vertices","volume":"B661","author":"Strassler","year":"2008","journal-title":"Phys. Lett."},{"key":"mlstad087abib21","doi-asserted-by":"publisher","first-page":"JHEP05(2010)077","DOI":"10.1007\/JHEP05(2010)077","article-title":"Hidden higgs decaying to lepton jets","author":"Falkowski","year":"2010","journal-title":"J. High Energy Phys."},{"key":"mlstad087abib22","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.105.241801","article-title":"Discovering higgs decays to lepton jets at Hadron colliders","volume":"105","author":"Falkowski","year":"2010","journal-title":"Phys. Rev. Lett."},{"key":"mlstad087abib23","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/8\/07\/P07015","article-title":"Triggers for displaced decays of long-lived neutral particles in the ATLAS detector","volume":"8","author":"ATLAS Collaboration","year":"2013","journal-title":"J. Instrum."},{"key":"mlstad087abib24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.94.113003","article-title":"Data-driven model-independent searches for long-lived particles at the LHC","volume":"94","author":"Coccaro","year":"2016","journal-title":"Phys. Rev. D"},{"key":"mlstad087abib25","doi-asserted-by":"publisher","first-page":"JHEP11(2019)156","DOI":"10.1007\/JHEP11(2019)156","article-title":"Study of energy deposition patterns in hadron calorimeter for prompt and displaced jets using convolutional neural network","author":"Bhattacherjee","year":"2019","journal-title":"J. High Energy Phys."},{"key":"mlstad087abib26","doi-asserted-by":"publisher","first-page":"JHEP08(2020)141","DOI":"10.1007\/JHEP08(2020)141","article-title":"Triggering long-lived particles in HL-LHC and the challenges in the first stage of the trigger system","author":"Bhattacherjee","year":"2020","journal-title":"J. High Energy Phys."},{"key":"mlstad087abib27","article-title":"ATLAS muon detector commissioning","author":"Diehl","year":"2009"},{"key":"mlstad087abib28","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1140\/epjc\/s10052-023-11584-x","article-title":"Studies of the muon momentum calibration and performance of the ATLAS detector with pp collisions at s = 13 TeV","volume":"83","author":"ATLAS Collaboration","year":"2023","journal-title":"Eur. Phys. J. C"},{"key":"mlstad087abib29","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.121.241803","article-title":"Anomaly detection for resonant new physics with machine learning","volume":"121","author":"Collins","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"mlstad087abib30","article-title":"A survey of convolutional neural networks: analysis, applications, and prospects","author":"Li","year":"2020"},{"key":"mlstad087abib31","doi-asserted-by":"publisher","first-page":"JHEP07(2016)069","DOI":"10.1007\/JHEP07(2016)069","article-title":"Jet-images\u2014deep learning edn","author":"de Oliveira","year":"2016","journal-title":"J. High Energy Phys."},{"key":"mlstad087abib32","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-46475-6_43","article-title":"Perceptual losses for real-time style transfer and super-resolution","author":"Johnson","year":"2016"},{"key":"mlstad087abib33","article-title":"ONNX: Open Neural Network Exchange","author":"Bai","year":"2023"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad087a","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad087a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad087a","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad087a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad087a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad087a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad087a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad087a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T08:39:49Z","timestamp":1701247189000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad087a"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,29]]},"references-count":33,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,11,29]]},"published-print":{"date-parts":[[2023,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad087a","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,29]]},"assertion":[{"value":"Fast neural network inference on FPGAs for triggering on long-lived particles at colliders","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-07-13","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-10-31","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-11-29","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}