Portable Acceleration of CMS Computing Workflows with Coprocessors as a Service

. 2024 ; 8 (1) : 17. [epub] 20240904

Status PubMed-not-MEDLINE Jazyk angličtina Země Švýcarsko Médium print-electronic

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/pmid39248308

Computing demands for large scientific experiments, such as the CMS experiment at the CERN LHC, will increase dramatically in the next decades. To complement the future performance increases of software running on central processing units (CPUs), explorations of coprocessor usage in data processing hold great potential and interest. Coprocessors are a class of computer processors that supplement CPUs, often improving the execution of certain functions due to architectural design choices. We explore the approach of Services for Optimized Network Inference on Coprocessors (SONIC) and study the deployment of this as-a-service approach in large-scale data processing. In the studies, we take a data processing workflow of the CMS experiment and run the main workflow on CPUs, while offloading several machine learning (ML) inference tasks onto either remote or local coprocessors, specifically graphics processing units (GPUs). With experiments performed at Google Cloud, the Purdue Tier-2 computing center, and combinations of the two, we demonstrate the acceleration of these ML algorithms individually on coprocessors and the corresponding throughput improvement for the entire workflow. This approach can be easily generalized to different types of coprocessors and deployed on local CPUs without decreasing the throughput performance. We emphasize that the SONIC approach enables high coprocessor usage and enables the portability to run workflows on different types of coprocessors.

Academy of Scientific Research and Technology of the Arab Republic of Egypt Egyptian Network of High Energy Physics Cairo Egypt

Adiyaman University Adiyaman Turkey

AGH University of Krakow Faculty of Computer Science Electronics and Telecommunications Krakow Poland

Authors affiliated with an institute or an international laboratory covered by a cooperation agreement with CERN Geneva Switzerland

Baylor University Waco TX USA

Beihang University Beijing China

Benemerita Universidad Autonoma de Puebla Puebla Mexico

Bergische University Wuppertal Wuppertal Germany

Bethel University St Paul MN USA

Bingol University Bingol Turkey

Birla Institute of Technology Mesra Mesra India

Bogazici University Istanbul Turkey

Boston University Boston MA USA

Bozok Universitetesi Rektörlügü Yozgat Turkey

Brandenburg University of Technology Cottbus Germany

British University in Egypt Cairo Egypt

Brown University Providence RI USA

Brunel University Uxbridge UK

California Institute of Technology Pasadena CA USA

Carnegie Mellon University Pittsburgh PA USA

Catholic University of America Washington DC USA

Center for High Energy Physics Fayoum University El Fayoum Egypt

Centro Brasileiro de Pesquisas Fisicas Rio de Janeiro Brazil

Centro de Investigacion y de Estudios Avanzados del IPN Mexico City Mexico

Centro de Investigaciones Energéticas Medioambientales y Tecnológicas Madrid Spain

Centro Siciliano di Fisica Nucleare e di Struttura Della Materia Catania Italy

CERN European Organization for Nuclear Research Geneva Switzerland

Charles University Prague Czech Republic

China Center of Advanced Science and Technology Beijing China

China Spallation Neutron Source Guangdong China

Chonnam National University Institute for Universe and Elementary Particles Kwangju Korea

College of Engineering and Technology American University of the Middle East Dasman Kuwait

Consejo Nacional de Ciencia y Tecnología Mexico City Mexico

Consiglio Nazionale delle Ricerche Istituto Officina dei Materiali Perugia Italy

Cornell University Ithaca NY USA

Çukurova University Physics Department Science and Art Faculty Adana Turkey

Department of Applied Physics Faculty of Science and Technology Universiti Kebangsaan Malaysia Bangi Malaysia

Department of Mathematics and Physics GWNU Gangneung Korea

Department of Physics Isfahan University of Technology Isfahan Iran

Department of Physics Kyung Hee University Seoul Korea

Department of Physics Tsinghua University Beijing China

Department of Physics University of Helsinki Helsinki Finland

Department of Physics University of Ruhuna Matara Sri Lanka

Department of Physics University of Science and Technology of Mazandaran Behshahr Iran

Department of Physics Yonsei University Seoul Korea

Deutsches Elektronen Synchrotron Hamburg Germany

Ecole Polytechnique Fédérale Lausanne Lausanne Switzerland

Erciyes University Kayseri Turkey

Erzincan Binali Yildirim University Erzincan Turkey

Escuela Politecnica Nacional Quito Ecuador

ETH Zurich Institute for Particle Physics and Astrophysics Zurich Switzerland

Faculty of Informatics University of Debrecen Debrecen Hungary

Faculty of Physics University of Belgrade Belgrade Serbia

Faculty of Science University of Split Split Croatia

Federal University of Rio Grande do Sul Porto Alegre Brazil

Fermi National Accelerator Laboratory Batavia IL USA

Florida Institute of Technology Melbourne FL USA

Florida State University Tallahassee FL USA

Forschungszentrum Jülich Juelich Germany

Georgian Technical University Tbilisi Georgia

Ghent University Ghent Belgium

Hacettepe University Ankara Turkey

Hanyang University Seoul Korea

Helsinki Institute of Physics Helsinki Finland

Helwan University Cairo Egypt

High Energy Physics Research Unit Department of Physics Faculty of Science Chulalongkorn University Bangkok Thailand

Horia Hulubei National Institute of Physics and Nuclear Engineering Bucharest Romania

HUN REN Wigner Research Centre for Physics Budapest Hungary

IIT Bhubaneswar Bhubaneswar India

Ilia State University Tbilisi Georgia

Imperial College London UK

Indian Institute of Science Bangalore India

Indian Institute of Science Education and Research Pune India

Indian Institute of Technology Madras Madras India

INFN Laboratori Nazionali di Frascati Frascati Italy

INFN Sezione di Bari Università di Bari Politecnico di Bari Bari Italy

INFN Sezione di Bologna Università di Bologna Bologna Italy

INFN Sezione di Catania Università di Catania Catania Italy

INFN Sezione di Firenze Università di Firenze Firenze Italy

INFN Sezione di Genova Università di Genova Genova Italy

INFN Sezione di Milano Bicocca Università di Milano Bicocca Milano Italy

INFN Sezione di Napoli Università di Napoli 'Federico II' Napoli Italy; Università della Basilicata Potenza Italy; Scuola Superiore Meridionale Napoli Italy

INFN Sezione di Padova Università di Padova Padova Italy; Università di Trento Trento Italy

INFN Sezione di Pavia Università di Pavia Pavia Italy

INFN Sezione di Perugia Università di Perugia Perugia Italy

INFN Sezione di Pisa Università di Pisa Scuola Normale Superiore di Pisa Pisa Italy; Università di Siena Siena Italy

INFN Sezione di Roma Sapienza Università di Roma Roma Italy

INFN Sezione di Torino Università di Torino Torino Italy; Università del Piemonte Orientale Novara Italy

INFN Sezione di Trieste Università di Trieste Trieste Italy

Institut de Physique des 2 Infinis de Lyon Villeurbanne France

Institut für Hochenergiephysik Vienna Austria

Institute for Nuclear Research and Nuclear Energy Bulgarian Academy of Sciences Sofia Bulgaria

Institute for Research in Fundamental Sciences Tehran Iran

Institute for Scintillation Materials of National Academy of Science of Ukraine Kharkiv Ukraine

Institute of Basic and Applied Sciences Faculty of Engineering Arab Academy for Science Technology and Maritime Transport Alexandria Egypt

Institute of Experimental Physics Faculty of Physics University of Warsaw Warsaw Poland

Institute of High Energy Physics Beijing China

Institute of Modern Physics and Key Laboratory of Nuclear Physics and Ion beam Application Fudan University Shanghai China

Institute of Nuclear and Particle Physics NCSR Demokritos Aghia Paraskevi Greece

Institute of Nuclear Physics of the Uzbekistan Academy of Sciences Tashkent Uzbekistan

Institute of Nuclear Research ATOMKI Debrecen Hungary

Institute of Physics Bhubaneswar India

Institute of Physics University of Debrecen Debrecen Hungary

institute or an international laboratory covered by a cooperation agreement with CERN Geneva Switzerland

Institute Rudjer Boskovic Zagreb Croatia

Instituto De Alta Investigación Universidad de Tarapacá Casilla 7 D Arica Chile

Instituto de Física de Cantabria CSIC Universidad de Cantabria Santander Spain

IPPP Durham University Durham UK

IRFU CEA Université Paris Saclay Gif sur Yvette France

Isfahan University of Technology Isfahan Iran

Istanbul Technical University Istanbul Turkey

Istanbul University Cerrahpasa Faculty of Engineering Istanbul Turkey

Istanbul University Istanbul Turkey

Italian National Agency for New Technologies Energy and Sustainable Economic Development Bologna Italy

Izmir Bakircay University Izmir Turkey

Johns Hopkins University Baltimore MD USA

Kafkas University Kars Turkey

Kansas State University Manhattan KS USA

Karamanoğlu Mehmetbey University Karaman Turkey

Karlsruher Institut fuer Technologie Karlsruhe Germany

Karoly Robert Campus MATE Institute of Technology Gyongyos Hungary

Konya Technical University Konya Turkey

Korea University Seoul Korea

Kyungpook National University Daegu Korea

Laboratoire d'Annecy le Vieux de Physique des Particules IN2P3 CNRS Annecy le Vieux France

Laboratoire Leprince Ringuet CNRS IN2P3 Ecole Polytechnique Institut Polytechnique de Paris Palaiseau France

Laboratório de Instrumentação e Física Experimental de Partículas Lisboa Portugal

Lappeenranta Lahti University of Technology Lappeenranta Finland

Lawrence Livermore National Laboratory Livermore CA USA

Marmara University Istanbul Turkey

Massachusetts Institute of Technology Cambridge MA USA

Middle East Technical University Physics Department Ankara Turkey

Milli Savunma University Istanbul Turkey

Monash University Faculty of Science Clayton Australia

MTA ELTE Lendület CMS Particle and Nuclear Physics Group Eötvös Loránd University Budapest Hungary

Nanjing Normal University Nanjing China

National and Kapodistrian University of Athens Athens Greece

National Central University Chung Li Taiwan

National Centre for Nuclear Research Swierk Poland

National Centre for Particle Physics Universiti Malaya Kuala Lumpur Malaysia

National Centre for Physics Quaid 1 Azam University Islamabad Pakistan

National Institute of Chemical Physics and Biophysics Tallinn Estonia

National Institute of Science Education and Research An OCC of Homi Bhabha National Institute Bhubaneswar Odisha India

National Science Centre Kharkiv Institute of Physics and Technology Kharkiv Ukraine

National Taiwan University Taipei Taiwan

National Technical University of Athens Athens Greece

Near East University Research Center of Experimental Health Science Mersin Turkey

Northeastern University Boston MA USA

Northwestern University Evanston IL USA

Now at Ain Shams University Cairo Egypt

Now at an institute or an international laboratory covered by a cooperation agreement with CERN Geneva Switzerland

Now at Henan Normal University Xinxiang China

Now at stanbul Okan University Istanbul Turkey

Now at The University of Iowa Iowa USA

Now at Universitatea Babes Bolyai Facultatea de Fizica Cluj Napoca Romania

Now at Zewail City of Science and Technology Zewail Egypt

other institute or international laboratory covered by a cooperation agreement with CERN Geneva Switzerland

Panjab University Chandigarh India

Paul Scherrer Institut Villigen Switzerland

Physics Department Faculty of Science Assiut University Assiut Egypt

Princeton University Princeton NJ USA

Punjab Agricultural University Ludhiana India

Purdue University Northwest Hammond IN USA

Purdue University West Lafayette IN USA

Rice University Houston TX USA

Riga Technical University Riga Latvia

Rutgers The State University of New Jersey Piscataway NJ USA

Rutherford Appleton Laboratory Didcot UK

RWTH Aachen University 1 Physikalisches Institut Aachen Germany

RWTH Aachen University 3 Physikalisches Institut A Aachen Germany

RWTH Aachen University 3 Physikalisches Institut B Aachen Germany

Saegis Campus Nugegoda Sri Lanka

Saha Institute of Nuclear Physics HBNI Kolkata India

School of Physics and Astronomy University of Southampton Southampton UK

Scuola Superiore Meridionale Università di Napoli 'Federico II' Napoli Italy

Sejong University Seoul Korea

Seoul National University Seoul Korea

Sharif University of Technology Tehran Iran

Sinop University Sinop Turkey

State Key Laboratory of Nuclear Physics and Technology Peking University Beijing China

State University of New York at Buffalo Buffalo NY USA

Stefan Meyer Institute for Subatomic Physics Vienna Austria

Sun Yat sen University Guangzhou China

Sungkyunkwan University Suwon Korea

Tata Institute of Fundamental Research A Mumbai India

Tata Institute of Fundamental Research B Mumbai India

Texas A and M University at Qatar Doha Qatar

Texas A and M University College Station TX USA

Texas Tech University Lubbock TX USA

The Ohio State University Columbus OH USA

The Rockefeller University New York NY USA

The University of Alabama Tuscaloosa AL USA

The University of Iowa Iowa USA

The University of Kansas Lawrence KS USA

The University of the State of Amazonas Manaus Brazil

Trincomalee Campus Eastern University Nilaveli Sri Lanka

TU Wien Vienna Austria

UFMS Nova Andradina Brazil

United States Naval Academy Annapolis MD USA

Universidad Autónoma de Madrid Madrid Spain

Universidad de Antioquia Medellin Colombia

Universidad de Los Andes Bogota Colombia

Universidad de Oviedo Instituto Universitario de Ciencias y Tecnologías Espaciales de Asturias Oviedo Spain

Universidad de Sonora Hermosillo Mexico

Universidad Iberoamericana Mexico City Mexico

Universidad San Francisco de Quito Quito Ecuador

Universidade do Estado do Rio de Janeiro Rio de Janeiro Brazil

Universidade Estadual de Campinas Campinas Brazil

Universidade Estadual Paulista Universidade Federal do ABC São Paulo Brazil

Università degli Studi Guglielmo Marconi Roma Italy

Università di Torino Torino Italy

Universität Zürich Zurich Switzerland

Université Catholique de Louvain Louvain la Neuve Belgium

Université de Haute Alsace Mulhouse France

Université de Strasbourg CNRS IPHC UMR 7178 Strasbourg France

Université Libre de Bruxelles Bruxelles Belgium

Universiteit Antwerpen Antwerpen Belgium

University College Dublin Dublin Ireland

University of Bristol Bristol UK

University of California Davis CA USA

University of California Los Angeles CA USA

University of California Riverside CA USA

University of California San Diego La Jolla CA USA

University of California Santa Barbara Department of Physics Santa Barbara CA USA

University of Canterbury Christchurch New Zealand

University of Chinese Academy of Sciences Beijing China

University of Colombo Colombo Sri Lanka

University of Colorado Boulder Boulder CO USA

University of Cyprus Nicosia Cyprus

University of Delhi Delhi India

University of Florida Gainesville FL USA

University of Hamburg Hamburg Germany

University of Hyderabad Hyderabad India

University of Illinois Chicago Chicago USA

University of Ioánnina Ioánnina Greece

University of Latvia Riga Latvia

University of Maryland College Park MD USA

University of Minnesota Minneapolis MN USA

University of Mississippi Oxford MS USA

University of Montenegro Podgorica Montenegro

University of Nebraska Lincoln Lincoln NE USA

University of Notre Dame Notre Dame IN USA

University of Puerto Rico Mayaguez PR USA

University of Rochester Rochester NY USA

University of Science and Technology of China Hefei China

University of Seoul Seoul Korea

University of Sofia Sofia Bulgaria

University of Split Faculty of Electrical Engineering Mechanical Engineering and Naval Architecture Split Croatia

University of Tennessee Knoxville TN USA

University of Virginia Charlottesville VA USA

University of Visva Bharati Santiniketan India

University of Wisconsin Madison WI USA

Vanderbilt University Nashville TN USA

Vilnius University Vilnius Lithuania

VINCA Institute of Nuclear Sciences University of Belgrade Belgrade Serbia

Vrije Universiteit Brussel Brussel Belgium

Warsaw University of Technology Warsaw Poland

Wayne State University Detroit MI USA

Yerevan Physics Institute Yerevan Armenia

Yerevan State University Yerevan Armenia

Yildiz Technical University Istanbul Turkey

Zhejiang University Hangzhou Zhejiang China

Zobrazit více v PubMed

Evans L, Bryant P (2008) LHC machine. JINST 3:S08001. 10.1088/1748-0221/3/08/S0800110.1088/1748-0221/3/08/S08001 DOI

ATLAS Collaboration (2008) The ATLAS experiment at the CERN Large Hadron Collider. JINST 3:S08003. 10.1088/1748-0221/3/08/S0800310.1088/1748-0221/3/08/S08003 DOI

CMS Collaboration (2008) The CMS experiment at the CERN LHC. JINST 3:S08004. 10.1088/1748-0221/3/08/S0800410.1088/1748-0221/3/08/S08004 DOI

ATLAS Collaboration (2012) Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC. Phys Lett B 716:1. 10.1016/j.physletb.2012.08.02010.1016/j.physletb.2012.08.020 DOI

CMS Collaboration (2012) Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC. Phys Lett B 716:30. 10.1016/j.physletb.2012.08.02110.1016/j.physletb.2012.08.021 DOI

Collaboration CMS, CMS Collaboration (2013) Observation of a new boson with mass near 125 GeV in pp collisions at [Image: see text] and 8 TeV. JHEP 06:081. 10.1007/JHEP06(2013)08110.1007/JHEP06(2013)081 DOI

Collaboration CMS, CMS Collaboration (2019) Search for supersymmetry in proton-proton collisions at 13 TeV in final states with jets and missing transverse momentum. JHEP 10:244. 10.1007/JHEP10(2019)24410.1007/JHEP10(2019)244 DOI

CMS Collaboration (2021) Combined searches for the production of supersymmetric top quark partners in proton-proton collisions at [Image: see text]. Eur Phys J C 81:970. 10.1140/epjc/s10052-021-09721-5 PubMed PMC

Collaboration CMS (2022) Search for higgsinos decaying to two Higgs bosons and missing transverse momentum in proton-proton collisions at [Image: see text]. JHEP 05:014. 10.1007/JHEP05(2022)01410.1007/JHEP05(2022)014 DOI

CMS Collaboration (2021) Search for supersymmetry in final states with two oppositely charged same-flavor leptons and missing transverse momentum in proton-proton collisions at [Image: see text]. JHEP 04:123. 10.1007/JHEP04(2021)12310.1007/JHEP04(2021)123 DOI

ATLAS Collaboration (2019) Search for squarks and gluinos in final states with hadronically decaying [Image: see text]-leptons, jets, and missing transverse momentum using pp collisions at [Image: see text] with the ATLAS detector. Phys Rev D 99:012009. 10.1103/PhysRevD.99.01200910.1103/PhysRevD.99.012009 DOI

Collaboration ATLAS (2020) Search for top squarks in events with a Higgs or Z boson using 139 [Image: see text] of pp collision data at [Image: see text] with the ATLAS detector. Eur Phys J C 80:1080. 10.1140/epjc/s10052-020-08469-810.1140/epjc/s10052-020-08469-8 DOI

ATLAS Collaboration (2021) Search for charginos and neutralinos in final states with two boosted hadronically decaying bosons and missing transverse momentum in pp collisions at [Image: see text] with the ATLAS detector. Phys Rev D 104:112010. 10.1103/PhysRevD.104.11201010.1103/PhysRevD.104.112010 DOI

ATLAS Collaboration (2023) Search for direct pair production of sleptons and charginos decaying to two leptons and neutralinos with mass splittings near the W-boson mass in [Image: see text] pp collisions with the ATLAS detector. JHEP 06:031. 10.1007/JHEP06(2023)03110.1007/JHEP06(2023)031 DOI

ATLAS Collaboration (2021) Search for new phenomena in events with an energetic jet and missing transverse momentum in pp collisions at [Image: see text] with the ATLAS detector. Phys Rev D 103:112006. 10.1103/PhysRevD.103.11200610.1103/PhysRevD.103.112006 DOI

CMS Collaboration (2021) Search for new particles in events with energetic jets and large missing transverse momentum in proton-proton collisions at [Image: see text]. JHEP 11:153. 10.1007/jhep11(2021)15310.1007/jhep11(2021)153 DOI

ATLAS Collaboration (2020) Search for new resonances in mass distributions of jet pairs using 139 [Image: see text] of pp collisions at [Image: see text] with the ATLAS detector. JHEP 03:145. 10.1007/jhep03(2020)14510.1007/jhep03(2020)145 DOI

ATLAS Collaboration (2019) Search for high-mass dilepton resonances using 139 [Image: see text] of pp collision data collected at [Image: see text] with the ATLAS detector. Phys Lett B 796:68. 10.1016/j.physletb.2019.07.01610.1016/j.physletb.2019.07.016 DOI

Collaboration CMS (2018) Search for narrow and broad DIJET resonances in proton-proton collisions at [Image: see text] and constraints on dark matter mediators and other new particles. JHEP 08:130. 10.1007/jhep08(2018)13010.1007/jhep08(2018)130 DOI

Collaboration CMS (2020) Search for high mass dijet resonances with a new background prediction method in proton-proton collisions at [Image: see text]. JHEP 05:033. 10.1007/jhep05(2020)03310.1007/jhep05(2020)033 DOI

CMS Collaboration (2021) Search for resonant and nonresonant new phenomena in high-mass dilepton final states at [Image: see text]. JHEP 07:208. 10.1007/jhep07(2021)20810.1007/jhep07(2021)208 DOI

Aberle O et al (2020) High-Luminosity Large Hadron Collider (HL-LHC): Technical design report, CERN Yellow Rep Monogr 10.23731/CYRM-2020-0010

Bruning O, Rossi L (2015) The High Luminosity Large Hadron Collider: the new machine for illuminating the mysteries of universe. World Sci. 10.1142/958110.1142/9581 DOI

CMS Collaboration (2020) The Phase-2 upgrade of the CMS level-1 trigger, CMS Technical Design Report CERN-LHCC-2020-004, CMS-TDR-021. https://cds.cern.ch/record/2714892

ATLAS Collaboration (2017) Technical design report for the Phase-II upgrade of the ATLAS TDAQ system, ATLAS Technical Design Report CERN-LHCC-2017-020, ATLAS-TDR-029. 10.17181/CERN.2LBB.4IAL

Ryd A, Skinnari L (2020) Tracking triggers for the HL-LHC. Ann Rev Nucl Part Sci 70:171. 10.1146/annurev-nucl-020420-093547. arXiv:2010.1355710.1146/annurev-nucl-020420-093547 DOI

Collaboration A, ATLAS Collaboration (2020) Operation of the ATLAS trigger system in Run 2. JINST 15:P10004. 10.1088/1748-0221/15/10/P1000410.1088/1748-0221/15/10/P10004 DOI

CMS Collaboration (2017) The CMS trigger system. JINST 12:01020. 10.1088/1748-0221/12/01/P0102010.1088/1748-0221/12/01/P01020 DOI

CMS Collaboration (2021) The Phase-2 upgrade of the CMS data acquisition and high level trigger, CMS Technical Design Report CERN-LHCC-2021-007, CMS-TDR-022, 2021. https://cds.cern.ch/record/2759072

CMS Offline Software and Computing Group (2022) CMS Phase-2 computing model: Update document, CMS Note CMS-NOTE-2022-008.https://cds.cern.ch/record/2815292

ATLAS Collaboration (2022) ATLAS software and computing HL-LHC roadmap, LHCC Public Document CERN-LHCC-2022-005, LHCC-G-182. http://cds.cern.ch/record/2802918

Dennard RH et al (1974) Design of ion-implanted MOSFET’s with very small physical dimensions. IEEE J Solid-State Circuits 9:256. 10.1109/JSSC.1974.105051110.1109/JSSC.1974.1050511 DOI

Graphcore Intelligence processing unit. https://www.graphcore.ai/products/ipu. Accessed 08 Nov 2023

Jia Z, Tillman B, Maggioni M, Scarpazza DP (2019) Dissecting the Graphcore IPU architecture via microbenchmarking, arXiv:1912.03413

Guest D, Cranmer K, Whiteson D (2018) Deep learning and its application to LHC physics. Ann Rev Nucl Part Sci 68:161. 10.1146/annurev-nucl-101917-021019. arXiv:1806.1148410.1146/annurev-nucl-101917-021019 DOI

Albertsson K et al (2018) Machine learning in high energy physics community white paper. J Phys Conf Ser 1085:022008. 10.1088/1742-6596/1085/2/022008. arXiv:1807.0287610.1088/1742-6596/1085/2/022008 DOI

Bourilkov D (2020) Machine and deep learning applications in particle physics. Int J Mod Phys A 34:1930019. 10.1142/S0217751X19300199. arXiv:1912.0824510.1142/S0217751X19300199 DOI

Larkoski AJ, Moult I, Nachman B (2020) Jet substructure at the Large Hadron Collider: a review of recent advances in theory and machine learning. Phys Rept 841:1. 10.1016/j.physrep.2019.11.001. arXiv:1709.0446410.1016/j.physrep.2019.11.001 DOI

Matthew F, Benjamin N (2021) A living review of machine learning for particle physics, arXiv:2102.02770

Harris P, et al (2022) Physics community needs, tools, and resources for machine learning. In: Proceedings 2021 US Community Study on the Future of Particle Physics. arXiv:2203.16255

Savard C, et al (2023) Optimizing high throughput inference on graph neural networks at shared computing facilities with the NVIDIA Triton Inference Server, 12. arXiv:2312.06838

Farrell S, et al (2018) Novel deep learning methods for track reconstruction, In: 4th International Workshop Connecting The Dots 2018. arXiv:1810.06111

Amrouche S, et al (2019) The Tracking Machine Learning challenge: accuracy phase, ch 9, p 231. Springer Cham, 4, 10.1007/978-3-030-29135-8_9

Ju X et al (2021) Performance of a geometric deep learning pipeline for HL-LHC particle tracking. Eur Phys J C 81:876. 10.1140/epjc/s10052-021-09675-8. arXiv:2103.0699510.1140/epjc/s10052-021-09675-8 DOI

DeZoort G et al (2021) Charged particle tracking via edge-classifying interaction networks. Comput Softw Big Sci 5:26. 10.1007/s41781-021-00073-z. arXiv:2103.1670110.1007/s41781-021-00073-z DOI

Qasim SR, Kieseler J, Iiyama Y, Pierini M (2019) Learning representations of irregular particle-detector geometry with distance-weighted graph networks. Eur Phys J C 79:608. 10.1140/epjc/s10052-019-7113-9. arXiv:1902.0798710.1140/epjc/s10052-019-7113-9 DOI

Kieseler J (2020) Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph and image data. Eur Phys J C 80:886. 10.1140/epjc/s10052-020-08461-2. arXiv:2002.0360510.1140/epjc/s10052-020-08461-2 DOI

CMS Collaboration (2023) GNN-based end-to-end reconstruction in the CMS Phase 2 high-granularity calorimeter. J Phys Conf Ser. 2438:012090. 10.1088/1742-6596/2438/1/01209010.1088/1742-6596/2438/1/012090 DOI

Pata J et al (2021) MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks. Eur Phys J C 81:381. 10.1140/epjc/s10052-021-09158-w. arXiv:2101.0857810.1140/epjc/s10052-021-09158-w DOI

CMS Collaboration (2023) Machine learning for particle flow reconstruction at CMS. J Phys Conf Ser 2438:012100. 10.1088/1742-6596/2438/1/01210010.1088/1742-6596/2438/1/012100 DOI

Mokhtar F, et al (2023) Progress towards an improved particle flow algorithm at CMS with machine learning. In: Proceedings 21st International Workshop on Advanced Computing and Analysis Techniques in Physics Research: AI meets Reality

Di Bello FA et al (2023) Reconstructing particles in jets using set transformer and hypergraph prediction networks. Eur Phys J C 83:596. 10.1140/epjc/s10052-023-11677-7. arXiv:2212.0132810.1140/epjc/s10052-023-11677-7 DOI

Pata J et al (2023) Improved particle-flow event reconstruction with scalable neural networks for current and future particle detectors. arXiv:2309.06782

Moreno EA et al (2020) JEDI-net: a jet identification algorithm based on interaction networks. Eur Phys J C 80:58. 10.1140/epjc/s10052-020-7608-4. arXiv:1908.0531810.1140/epjc/s10052-020-7608-4 DOI

Qu H, Gouskos L (2020) ParticleNet: jet tagging via particle clouds. Phys Rev D 101:056019. 10.1103/PhysRevD.101.056019. arXiv:1902.0857010.1103/PhysRevD.101.056019 DOI

Moreno EA et al (2020) Interaction networks for the identification of boosted [Image: see text] decays. Phys Rev D 102:012010. 10.1103/PhysRevD.102.012010. arXiv:1909.1228510.1103/PhysRevD.102.012010 DOI

Bols E et al (2020) Jet flavour classification using DeepJet. JINST 15:P12012. 10.1088/1748-0221/15/12/P12012. arXiv:2008.1051910.1088/1748-0221/15/12/P12012 DOI

CMS Collaboration (2020) Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques. JINST 15:P06005. 10.1088/1748-0221/15/06/P0600510.1088/1748-0221/15/06/P06005 DOI

Qu H, Li C, Qian S (2022) Particle transformer for jet tagging. In: Proceedings 39th International Conference on Machine Learning, Chaudhuri K et al. eds. vol. 162, p 18281

CMS Collaboration (2023) Muon identification using multivariate techniques in the CMS experiment in proton-proton collisions at [Image: see text]. arXiv:2310.03844

Duarte J et al (2019) FPGA-accelerated machine learning inference as a service for particle physics computing. Comput Softw Big Sci 3:13. 10.1007/s41781-019-0027-2. arXiv:1904.0898610.1007/s41781-019-0027-2 DOI

Rankin D et al (2020) FPGAs-as-a-service toolkit (FaaST), In: Proceedings 2020 IEEE/ACM International Workshop on Heterogeneous High-performance Reconfigurable Computing (H2RC). IEEE, 10.1109/h2rc51942.2020.00010

Krupa J et al (2021) GPU coprocessors as a service for deep learning inference in high energy physics. Mach Learn Sci Tech 2:035005. 10.1088/2632-2153/abec21. arXiv:2007.1035910.1088/2632-2153/abec21 DOI

Wang M et al (2021) GPU-accelerated machine learning inference as a service for computing in neutrino experiments. Front Big Data 3:604083. 10.3389/fdata.2020.604083. arXiv:2009.04509 10.3389/fdata.2020.604083 PubMed DOI PMC

Cai T et al (2023) Accelerating machine learning inference with GPUs in ProtoDUNE data processing. Comput Softw Big Sci 7:11. 10.1007/s41781-023-00101-0. arXiv:2301.04633 10.1007/s41781-023-00101-0 PubMed DOI PMC

Gunny A et al (2022) Hardware-accelerated inference for real-time gravitational-wave astronomy. Nature Astron 6:529. 10.1038/s41550-022-01651-w. arXiv:2108.1243010.1038/s41550-022-01651-w DOI

ALICE Collaboration (2019) Real-time data processing in the ALICE high level trigger at the LHC. Comput Phys Commun 242:25. 10.1016/j.cpc.2019.04.01110.1016/j.cpc.2019.04.011 DOI

Aaij R et al (2020) Allen: a high level trigger on GPUs for LHCb. Comput Softw Big Sci 4:7. 10.1007/s41781-020-00039-7. arXiv:1912.09161 10.1007/s41781-020-00039-7 PubMed DOI PMC

LHCb Collaboration (2023) The LHCb upgrade I. arXiv:2305.10515

Bocci A et al (2020) Heterogeneous reconstruction of tracks and primary vertices with the CMS pixel tracker. Front Big Data 3:601728. 10.3389/fdata.2020.601728. arXiv:2008.13461 10.3389/fdata.2020.601728 PubMed DOI PMC

Collaboration CMS (2023) CMS high level trigger performance comparison on CPUs and GPUs. J Phys Conf Ser 2438:012016. 10.1088/1742-6596/2438/1/01201610.1088/1742-6596/2438/1/012016 DOI

Vom Bruch D (2020) Real-time data processing with GPUs in high energy physics. JINST 15:C06010. 10.1088/1748-0221/15/06/C06010. arXiv:2003.1149110.1088/1748-0221/15/06/C06010 DOI

Collaboration CMS (2015) Mini-AOD: A new analysis data format for CMS. J Phys Conf Ser 664:7. 10.1088/1742-6596/664/7/07205210.1088/1742-6596/664/7/072052 DOI

CMS Collaboration (2006) CMS physics: Technical design report volume 1: Detector performance and software. CMS Technical Design Report CERN-LHCC-2006-001, CMS-TDR-8-1. https://cds.cern.ch/record/922757

CMS Collaboration CMSSW on Github. http://cms-sw.github.io/ Accessed 08 Nov 2023

CMS Collaboration (2020) Performance of the CMS Level-1 trigger in proton-proton collisions at [Image: see text]. JINST 15:P10017. 10.1088/1748-0221/15/10/P1001710.1088/1748-0221/15/10/P10017 DOI

CMS Collaboration (2021) Electron and photon reconstruction and identification with the CMS experiment at the CERN LHC. JINST 16:P05014. 10.1088/1748-0221/16/05/P0501410.1088/1748-0221/16/05/P05014 DOI

Collaboration CMS, CMS Collaboration (2014) Description and performance of track and primary-vertex reconstruction with the CMS tracker. JINST 9:P10009. 10.1088/1748-0221/9/10/P1000910.1088/1748-0221/9/10/P10009 DOI

CMS Collaboration (2017) Particle-flow reconstruction and global event description with the CMS detector. JINST 12:P10003. 10.1088/1748-0221/12/10/P1000310.1088/1748-0221/12/10/P10003 DOI

oneTBB, oneAPI Threading Building Blocks. https://github.com/oneapi-src/oneTBB. Accessed 08 Nov 2023

Bocci A et al (2020) Bringing heterogeneity to the CMS software framework. Eur Phys J Web Conf 245:05009. 10.1051/epjconf/202024505009. arXiv:2004.0433410.1051/epjconf/202024505009 DOI

CMS Collaboration (2019) A further reduction in CMS event data for analysis: the NANOAOD format. Eur Phys J Web Conf 214:06021. 10.1051/epjconf/20192140602110.1051/epjconf/201921406021 DOI

Collaboration CMS (2020) Extraction and validation of a new set of CMS pythia 8 tunes from underlying-event measurements. Eur Phys J C 80:4. 10.1140/epjc/s10052-019-7499-4 10.1140/epjc/s10052-019-7499-4 PubMed DOI PMC

Collaboration CMS, CMS Collaboration (2020) Pileup mitigation at CMS in 13 TeV data. JINST 15:P09018. 10.1088/1748-0221/15/09/P0901810.1088/1748-0221/15/09/P09018 DOI

Collaboration CMS (2020) NANOAOD: a new compact event data format in CMS. Eur Phys J Web Conf. 245:06002. 10.1051/epjconf/20202450600210.1051/epjconf/202024506002 DOI

NVIDIA. NVIDIA Triton Inference Server. https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html. Accessed 08 Nov 2023

gRPC, gRPC – a high performance, open source universal RPC framework. https://grpc.io/. Accessed 08 Nov 2023

Kubernetes Kubernetes documentation. https://kubernetes.io/docs/home/. Accessed 08 Nov 2023

K. Pedro et al SonicCore. https://github.com/cms-sw/cmssw/tree/master/HeterogeneousCore/SonicCore. Accessed 08 Nov 2023

K. Pedro et al. SonicTriton. https://github.com/cms-sw/cmssw/tree/master/HeterogeneousCore/SonicTriton. Accessed 08 Nov 2023

Pedro K SonicCMS. https://github.com/fastmachinelearning/SonicCMS. Accessed 08 Nov 2023

Caulfield AM, et al (2016) A cloud-scale acceleration architecture. In: Proc.eedings 2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO), p 1. 10.1109/MICRO.2016.7783710

Kuznetsov V (2018) vkuznet/TFaaS: First public version, 10.5281/zenodo.1308049

Kuznetsov V, Giommi L, Bonacorsi D (2021) MLaaS4HEP: machine learning as a service for HEP. Comput Softw Big Sci 5:17. 10.1007/s41781-021-00061-3. arXiv:2007.1478110.1007/s41781-021-00061-3 DOI

KServe, KServe documentation website. https://kserve.github.io/website/. Accessed 08 Nov 2023

NVIDIA NVIDIA Triton Inference Server README (release 22.08). https://github.com/triton-inference-server/server/blob/r22.08/README.md#documentation Accessed 08 Nov 2023

Paszke A et al (2019) PyTorch: an imperative style, high-performance deep learning library, In: Advances in Neural Information Processing Systems 32, Wallach H et al., eds., p 8024. Curran Associates, Inc., http://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf. arXiv:1912.01703

NVIDIA NVIDIA TensorRT. https://developer.nvidia.com/tensorrt. Accessed 08 Nov 2023

ONNX Open Neural Network Exchange (ONNX). https://github.com/onnx/onnx. Accessed 08 Nov 2023

Abadi M et al (2016) TensorFlow: A system for large-scale machine learning, arXiv:1605.08695

Chen T, Guestrin C (2016) XGBoost: A scalable tree boosting system, In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery. 10.1145/2939672.2939785

NVIDIA NVIDIA Triton Inference Server Model Analyzer. https://github.com/triton-inference-server/model_analyzer. Accessed 08 Nov 2023

Buncic P et al (2010) CernVM - a virtual software appliance for LHC applications. J Phys Conf Ser 219:042003. 10.1088/1742-6596/219/4/04200310.1088/1742-6596/219/4/042003 DOI

Guida SD et al (2015) The CMS condition database system. J Phys Conf Ser 664:042024. 10.1088/1742-6596/664/4/04202410.1088/1742-6596/664/4/042024 DOI

Bauerdick L et al (2012) Using Xrootd to federate regional storage. J Phys Conf Ser 396:042009. 10.1088/1742-6596/396/4/04200910.1088/1742-6596/396/4/042009 DOI

CMS Collaboration (2019) Performance of missing transverse momentum reconstruction in proton-proton collisions at [Image: see text] using the CMS detector. JINST 14:P07004. 10.1088/1748-0221/14/07/P0700410.1088/1748-0221/14/07/P07004 DOI

CMSSW, ParticleNet producer in CMSSW. https://github.com/cms-sw/cmssw/blob/CMSSW_13_0_0/RecoBTag/ONNXRuntime/plugins/BoostedJetONNXJetTagsProducer.cc. Accessed: 08 Nov 2023

CMSSW ParticleNet SONIC producer in CMSSW. https://github.com/cms-sw/cmssw/blob/CMSSW_13_0_0/RecoBTag/ONNXRuntime/plugins/ParticleNetSonicJetTagsProducer.cc. Accessed 08 Nov 2023

Cacciari M, Salam GP, Soyez G (2008) The anti- [Image: see text] jet clustering algorithm. JHEP 04:063. 10.1088/1126-6708/2008/04/063. arXiv:0802.118910.1088/1126-6708/2008/04/063 DOI

Cacciari M, Salam GP, Soyez G (2012) FastJet user manual. Eur Phys J C 72:1896. 10.1140/epjc/s10052-012-1896-2. arXiv:1111.609710.1140/epjc/s10052-012-1896-2 DOI

CMS Collaboration (2023) Performance of the ParticleNet tagger on small and large-radius jets at high level trigger in Run 3. CMS Detector Performance Note CMS-DP-2023-021, https://cds.cern.ch/record/2857440

CMS Collaboration (2020) Identification of highly Lorentz-boosted heavy particles using graph neural networks and new mass decorrelation techniques, CMS Detector Performance Note CMS-DP-2020-002, https://cds.cern.ch/record/2707946

CMS Collaboration (2021) Mass regression of highly-boosted jets using graph neural networks, CMS Detector Performance Note CMS-DP-2021-017, https://cds.cern.ch/record/2777006

Feng Y (2020) A new deep-neural-network-based missing transverse momentum estimator, and its application to W recoil. PhD thesis, University of Maryland, College Park, 10.13016/e6ze-zycc

CMS Collaboration (2022) Identification of hadronic tau lepton decays using a deep neural network. JINST 17:P07023. 10.1088/1748-0221/17/07/P0702310.1088/1748-0221/17/07/P07023 DOI

NVIDIA Corporation (2020) NVIDIA T4 70W low profile PCIe GPU accelerator. NVIDIA Corporation, Santa Clara

Holzman B et al (2017) HEPCloud, a new paradigm for HEP facilities: CMS amazon web services investigation. Comput Softw Big Sci 1:1. 10.1007/s41781-017-0001-9. arXiv:1710.0010010.1007/s41781-017-0001-9 DOI

Corporation Intel (2023) Intel 64 and IA-32 architectures software developer’s manual. Intel Corporation, Santa Clara

SchedMD Slurm workload manager. https://slurm.schedmd.com/documentation.html. Accessed 08 Nov 2023

Inc Advanced Micro Devices (2020) AMD EPYC 7002 series processors power electronic health record solutions. Advanced Micro Devices Inc, Santa Clara

Najít záznam

Citační ukazatele

Nahrávání dat ...

Možnosti archivace

Nahrávání dat ...