{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T00:20:53Z","timestamp":1758846053225,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,5]]},"DOI":"10.1145\/3676151.3719359","type":"proceedings-article","created":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T00:57:09Z","timestamp":1746233829000},"page":"181-191","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Introducing GPU Persistent Graphs for Time-sensitive Workflows"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0027-3765","authenticated-orcid":false,"given":"Cyril","family":"Cetre","sequence":"first","affiliation":[{"name":"Thales Research &amp; Techonology, Palaiseau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3767-6552","authenticated-orcid":false,"given":"Florian","family":"Ferreira","sequence":"additional","affiliation":[{"name":"LESIA, Observatoire de Paris, Universit\u00e9 PSL, CNRS, Universit\u00e9 Sorbonne, Universit\u00e9 Paris Cit\u00e9, Meudon, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2507-5772","authenticated-orcid":false,"given":"R\u00e9mi","family":"Barrere","sequence":"additional","affiliation":[{"name":"Thales Research &amp; Technology, Palaiseau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2080-7189","authenticated-orcid":false,"given":"Damien","family":"Gratadour","sequence":"additional","affiliation":[{"name":"LESIA, Observatoire de Paris, Universit\u00e9 PSL, CNRS, Universit\u00e9 Sorbonne, Universit\u00e9 Paris Cit\u00e9, Meudon, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,5,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2017.00017"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS58335.2023.00012"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.2313196"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5160984"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","unstructured":"Nicola Capodieci and Paolo Burgio. 2015. Efficient Implementation of Genetic Algorithms on GP-GPU with Scheduled Persistent CUDA Threads. In 2015 Seventh International Symposium on Parallel Architectures Algorithms and Programming (PAAP). 6--12. https:\/\/doi.org\/10.1109\/PAAP.2015.13","DOI":"10.1109\/PAAP.2015.13"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2018.00021"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTCSA50079.2020.9203722"},{"key":"e_1_3_2_1_8_1","volume-title":"11th European Congress Embedded Real Time System ( ERTS2022 )","author":"Cetre Cyril","year":"2022","unstructured":"Cyril Cetre, Florian Ferreira, Arnaud Sevin, R\u00e9mi Barrere, and Damien Gratadour. 2022. Real-time high performance computing using a Jetson Xavier AGX. In 11th European Congress Embedded Real Time System ( ERTS2022 ). Toulouse, France. https:\/\/hal.science\/hal-03693764"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Yann Cl\u00e9net Tristan Buey Eric Gendron Zoltan Hubert Fabrice Vidal Mathieu Cohen Fr\u00e9d\u00e9ric Chapron Arnaud Sevin Pierre F\u00e9dou Ga\u00eble Barbary Pierre Baudoz Bruno Borgo Saber Ben Nejma Vincent Chambouleyron Vincent D\u00e9o Olivier Dupuis S\u00e9bastien Durand Florian Ferreira Julien Gaudemard Damien Gratadour Elsa Huby Jean-Michel Huet Bertrand Le Ruyet Napol\u00e9on Nguyen-Tuong Cl\u00e9ment Perrot Simone Thijs Youssef Youn\u00e8s G\u00e9rard Rousset Philippe Feautrier G\u00e9rard Zins Emiliano Diolaiti Paolo Ciliegi Simone Esposito Lorenzo Busoni Josef Schubert Michael Hartl Veronika H\u00f6rmann and Richard Davies. 2018. The MICADO first-light imager for the ELT: towards the preliminary design review of the MICADO-MAORY SCAO. In Adaptive Optics Systems VI Laird M. Close Laura Schreiber and Dirk Schmidt (Eds.) Vol. 10703. International Society for Optics and Photonics SPIE 1070313. https:\/\/doi.org\/10.1117\/12.2311481","DOI":"10.1117\/12.2311481"},{"key":"e_1_3_2_1_10_1","volume-title":"Adaptive Optics for Extremely Large Telescopes conference, 6th edition","author":"Cl\u00e9net Yann","year":"2019","unstructured":"Yann Cl\u00e9net, Tristan Buey, Eric Gendron, Zoltan Hubert, Fabrice Vidal, Mathieu Cohen, Fr\u00e9d\u00e9ric Chapron, Arnaud Sevin, Pierre F\u00e9dou, Ga\u00eble Barbary, Bruno Borgo, Jean-Michel Huet, Alexandre Blin, Olivier Dupuis, Julien Gaudemard, Saber Ben Nejma, Damien Gratadour, Vincent Deo, Florian Moura Ferreira, Simone Thijs, Vincent Lapeyr\u00e8re, Jordan Raffard, Fanny Chemla, Bertrand Le Ruyet, Arielle Bertrou-Cantou, Milan Rozel, Youssef Younes, G\u00e9rard Rousset, G\u00e9rard Zins, Emiliano Diolaiti, Paolo Ciliegi, Vincent Garrel, Sebastian Rabien, Josef Schubert, Michael Hartl, Veronika H\u00f6rmann, and Richard J Davies. 2019. MICADO-MAORY SCAO Preliminary design, development plan & calibration strategies. In Adaptive Optics for Extremely Large Telescopes conference, 6th edition. Qu\u00e9bec, Canada. https:\/\/hal.science\/hal-03078430"},{"key":"e_1_3_2_1_11_1","volume-title":"28th International Conference on Concurrency Theory (CONCUR 2017) (Leibniz International Proceedings in Informatics (LIPIcs)","volume":"13","author":"Donaldson Alastair F.","year":"2017","unstructured":"Alastair F. Donaldson, Jeroen Ketema, Tyler Sorensen, and John Wickerson. 2017. Forward Progress on GPU Concurrency (Invited Talk). In 28th International Conference on Concurrency Theory (CONCUR 2017) (Leibniz International Proceedings in Informatics (LIPIcs), Vol. 85), Roland Meyer and Uwe Nestmann (Eds.). Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik, Dagstuhl, Germany, 1:1--1:13. http:\/\/drops.dagstuhl.de\/opus\/volltexte\/2017\/7805"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"F. Ferreira A. Sevin J. Bernard O. Guyon A. Bertrou-Cantou J. Raffard F. Vidal E. Gendron and D. Gratadour. 2020. Hard real-time core software of the AO RTC COSMIC platform: architecture and performance. In Adaptive Optics Systems VII Laura Schreiber Dirk Schmidt and Elise Vernet (Eds.) Vol. 11448. International Society for Optics and Photonics SPIE 1144815. https:\/\/doi.org\/10.1117\/12.2561244","DOI":"10.1117\/12.2561244"},{"key":"e_1_3_2_1_13_1","unstructured":"Alan Gray. 2019. Getting Started with CUDA Graphs. https:\/\/developer.nvidia.com\/blog\/cuda-graphs\/."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339596"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-astro-081817-052000"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488699"},{"key":"e_1_3_2_1_17_1","unstructured":"Leela S. Karumbunathan. 2022. NVIDIA Jetson AGX Orin Series. NVIDIA. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/gtcf21\/jetson-orin\/nvidia-jetson-agx-orin-technical-brief.pdf"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ZINC52049.2021.9499270"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.450850"},{"key":"e_1_3_2_1_20_1","unstructured":"NVIDIA. 2014. Kepler TM GK110\/210 whitepaper. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/Data-Center\/tesla-product-literature\/NVIDIA-Kepler-GK110-GK210-Architecture-Whitepaper.pdf."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS48715.2020.000-5"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.4230\/LIPIcs.ECRTS.2020.10"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453417.3453432"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.2627827"},{"key":"e_1_3_2_1_25_1","unstructured":"Sally Stevenson Stephen Jones and Fred Oh. 2022. Enabling Dynamic Control Flow in CUDA Graphs with Device Graph Launch. https:\/\/developer.nvidia.com\/blog\/enabling-dynamic-control-flow-in-cuda-graphs-with-device-graph-launch\/."},{"key":"e_1_3_2_1_26_1","volume-title":"Improving Real-Time Performance with CUDA Persistent Threads (CuPer) on the Jetson TX2. Concurrent Real-Time White Paper","author":"Todd Allen","year":"2018","unstructured":"Allen Todd. 2018. Improving Real-Time Performance with CUDA Persistent Threads (CuPer) on the Jetson TX2. Concurrent Real-Time White Paper (2018). https:\/\/concurrent-rt.com\/wp-content\/uploads\/2020\/12\/Improving-Real-Time-Performance-With-CUDA-Persistent-Threads.pdf"},{"key":"e_1_3_2_1_27_1","unstructured":"Jiqun Tu. 2022. Constructing CUDA Graphs with Dynamic Parameters. https:\/\/developer.nvidia.com\/blog\/constructing-cuda-graphs-with-dynamic-parameters\/."},{"key":"e_1_3_2_1_28_1","unstructured":"Holly Wilper Knight Robert and Jason Cohen. 2020. Understanding the Visualization of Overhead and Latency in NVIDIA Nsight Systems. NVIDIA. https:\/\/developer.nvidia.com\/blog\/understanding-the-visualization-of-overhead-and-latency-in-nsight-systems\/"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.4230\/LIPIcs.ECRTS.2018.20"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00048"},{"key":"e_1_3_2_1_31_1","volume-title":"Understanding the Overheads of Launching CUDA Kernels","author":"Zhang Lingqi","year":"2019","unstructured":"Lingqi Zhang, Mohamed Wahib, and Satoshi Matsuoka. 2017. Understanding the Overheads of Launching CUDA Kernels. Tokyo Institute of Technology, Dept. of Mathematical and Computing Science, Tokyo, Japan. https:\/\/www.hpcs.cs.tsukuba.ac.jp\/icpp2019\/data\/posters\/Poster17-abst.pdf"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3235439"}],"event":{"name":"ICPE '25: 16th ACM\/SPEC International Conference on Performance Engineering","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","SIGMETRICS ACM Special Interest Group on Measurement and Evaluation"],"location":"Toronto ON Canada","acronym":"ICPE '25"},"container-title":["Proceedings of the 16th ACM\/SPEC International Conference on Performance Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676151.3719359","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676151.3719359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T16:23:11Z","timestamp":1758817391000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676151.3719359"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,5]]},"references-count":32,"alternative-id":["10.1145\/3676151.3719359","10.1145\/3676151"],"URL":"https:\/\/doi.org\/10.1145\/3676151.3719359","relation":{},"subject":[],"published":{"date-parts":[[2025,5,5]]},"assertion":[{"value":"2025-05-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}