{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T02:55:01Z","timestamp":1775184901232,"version":"3.50.1"},"reference-count":15,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,10,2]],"date-time":"2021-10-02T00:00:00Z","timestamp":1633132800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,10,2]],"date-time":"2021-10-02T00:00:00Z","timestamp":1633132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002347","name":"bundesministerium fr bildung und forschung","doi-asserted-by":"publisher","award":["05H19ODCA9"],"award-info":[{"award-number":["05H19ODCA9"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"bundesministerium fr bildung und forschung","doi-asserted-by":"publisher","award":["05H19ODCA9"],"award-info":[{"award-number":["05H19ODCA9"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"name":"aix-marseille universit\u00e9 - a*midex","award":["AMX-18-INT-006"],"award-info":[{"award-number":["AMX-18-INT-006"]}]},{"DOI":"10.13039\/501100002957","name":"Technische Universit\u00e4t Dresden","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100002957","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comput Softw Big Sci"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The ATLAS experiment at the Large Hadron Collider (LHC) is operated at CERN and measures proton\u2013proton collisions at multi-TeV energies with a repetition frequency of 40 MHz. Within the phase-II upgrade of the LHC, the readout electronics of the liquid-argon (LAr) calorimeters of ATLAS are being prepared for high luminosity operation expecting a pileup of up to 200 simultaneous proton\u2013proton interactions. Moreover, the calorimeter signals of up to 25 subsequent collisions are overlapping, which increases the difficulty of energy reconstruction by the calorimeter detector. Real-time processing of digitized pulses sampled at 40 MHz is performed using field-programmable gate arrays (FPGAs). To cope with the signal pileup, new machine learning approaches are explored: convolutional and recurrent neural networks outperform the optimal signal filter currently used, both in assignment of the reconstructed energy to the correct proton bunch crossing and in energy resolution. The improvements concern in particular energies derived from overlapping pulses. Since the implementation of the neural networks targets an FPGA, the number of parameters and the mathematical operations need to be well controlled. The trained neural network structures are converted into FPGA firmware using automated implementations in hardware description language and high-level synthesis tools. Very good agreement between neural network implementations in FPGA and software based calculations is observed. The prototype implementations on an Intel Stratix-10 FPGA reach maximum operation frequencies of 344\u2013640 MHz. Applying time-division multiplexing allows the processing of 390\u2013576 calorimeter channels by one FPGA for the most resource-efficient networks. Moreover, the latency achieved is about 200 ns. These performance parameters show that a neural-network based energy reconstruction can be considered for the processing of the ATLAS LAr calorimeter signals during the high-luminosity phase of the LHC.<\/jats:p>","DOI":"10.1007\/s41781-021-00066-y","type":"journal-article","created":{"date-parts":[[2021,10,4]],"date-time":"2021-10-04T15:21:29Z","timestamp":1633360889000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Artificial Neural Networks on FPGAs for Real-Time Energy Reconstruction of the ATLAS LAr Calorimeters"],"prefix":"10.1007","volume":"5","author":[{"given":"Georges","family":"Aad","sequence":"first","affiliation":[]},{"given":"Anne-Sophie","family":"Berthold","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Calvet","sequence":"additional","affiliation":[]},{"given":"Nemer","family":"Chiedde","sequence":"additional","affiliation":[]},{"given":"Etienne Marie","family":"Fortin","sequence":"additional","affiliation":[]},{"given":"Nick","family":"Fritzsche","sequence":"additional","affiliation":[]},{"given":"Rainer","family":"Hentges","sequence":"additional","affiliation":[]},{"given":"Lauri Antti Olavi","family":"Laatu","sequence":"additional","affiliation":[]},{"given":"Emmanuel","family":"Monnier","sequence":"additional","affiliation":[]},{"given":"Arno","family":"Straessner","sequence":"additional","affiliation":[]},{"given":"Johann Christoph","family":"Voigt","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,10,2]]},"reference":[{"key":"66_CR1","doi-asserted-by":"publisher","first-page":"S08003","DOI":"10.1088\/1748-0221\/3\/08\/S08003","volume":"3","author":"Collaboration ATLAS","year":"2008","unstructured":"ATLAS\u00a0 Collaboration (2008) The ATLAS experiment at the CERN large hadron collider. JINST 3:S08003. https:\/\/doi.org\/10.1088\/1748-0221\/3\/08\/S08003","journal-title":"JINST"},{"key":"66_CR2","doi-asserted-by":"publisher","first-page":"S08001","DOI":"10.1088\/1748-0221\/3\/08\/S08001","volume":"3","author":"L Evans","year":"2008","unstructured":"Evans L, Bryant Ph (2008) LHC machine. JINST 3:S08001. https:\/\/doi.org\/10.1088\/1748-0221\/3\/08\/S08001","journal-title":"JINST"},{"key":"66_CR3","unstructured":"ATLAS Collaboration (2017) Technical design report for the phase-II upgrade of the ATLAS TDAQ system, CERN-LHCC-2017-020, ATLAS-TDR-029. https:\/\/cds.cern.ch\/record\/2285584"},{"key":"66_CR4","unstructured":"ATLAS Collaboration (2017) Technical design report for the phase-II upgrade of the ATLAS LAr calorimeter, CERN-LHCC-2017-018, ATLAS-TDR-027. https:\/\/cds.cern.ch\/record\/2285582"},{"key":"66_CR5","unstructured":"Intel Corporation (2020) Intel stratix-10 device datasheet. Version 2020.12.24"},{"key":"66_CR6","doi-asserted-by":"publisher","first-page":"02006","DOI":"10.1051\/epjconf\/201921402006","volume":"214","author":"N Madysa","year":"2019","unstructured":"Madysa N (2019) AREUS: a software framework for ATLAS readout electronics upgrade simulation. EPJ Web Conf 214:02006. https:\/\/doi.org\/10.1051\/epjconf\/201921402006","journal-title":"EPJ Web Conf"},{"key":"66_CR7","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1016\/0168-9002(94)91332-3","volume":"338","author":"WE Cleland","year":"1994","unstructured":"Cleland WE, Stern EG (1994) Signal processing considerations for liquid ionization calorimeters in a high rate environment. NIM A 338:467\u2013497. https:\/\/doi.org\/10.1016\/0168-9002(94)91332-3","journal-title":"NIM A"},{"key":"66_CR8","unstructured":"https:\/\/keras.io\/. Accessed 18 Feb 2021"},{"key":"66_CR9","unstructured":"https:\/\/www.tensorflow.org\/. Accessed 18 Feb 2021"},{"issue":"4","key":"66_CR10","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun Y et al (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541\u2013551. https:\/\/doi.org\/10.1162\/neco.1989.1.4.541","journal-title":"Neural Comput"},{"key":"66_CR11","doi-asserted-by":"publisher","first-page":"132306","DOI":"10.1016\/j.physd.2019.132306","volume":"404","author":"A Sherstinky","year":"2020","unstructured":"Sherstinky A (2020) Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D 404:132306. https:\/\/doi.org\/10.1016\/j.physd.2019.132306","journal-title":"Physica D"},{"key":"66_CR12","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput. 9:1735\u20131780. https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput."},{"key":"66_CR13","unstructured":"Quartus, ModelSim and HLS tools (2021) https:\/\/www.intel.com. Accessed 18 Feb 2021"},{"key":"66_CR14","unstructured":"Questa Sim (2021) https:\/\/eda.sw.siemens.com\/. Accessed 20 Jun 2021"},{"key":"66_CR15","doi-asserted-by":"publisher","first-page":"P07027","DOI":"10.1088\/1748-0221\/13\/07\/P07027","volume":"13","author":"J Duarte","year":"2018","unstructured":"Duarte J et al (2018) Fast inference of deep neural networks in FPGAs for particle physics. JINST 13:P07027. https:\/\/doi.org\/10.1088\/1748-0221\/13\/07\/P07027","journal-title":"JINST"}],"container-title":["Computing and Software for Big Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41781-021-00066-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41781-021-00066-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41781-021-00066-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,26]],"date-time":"2021-12-26T11:05:39Z","timestamp":1640516739000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41781-021-00066-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,2]]},"references-count":15,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["66"],"URL":"https:\/\/doi.org\/10.1007\/s41781-021-00066-y","relation":{},"ISSN":["2510-2036","2510-2044"],"issn-type":[{"value":"2510-2036","type":"print"},{"value":"2510-2044","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,2]]},"assertion":[{"value":"5 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 September 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 October 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interests"}},{"value":"The VHDL implementation of the CNNs as well as the simulated data will become public through the general software and data publication measures of the ATLAS collaboration. The vanilla RNN implementation in HLS will be published within the hls4ml framework\u00a0[].","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Data availability"}}],"article-number":"19"}}