{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T19:22:21Z","timestamp":1774120941126,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Union's Horizon 2020 Framework Programme for Research and Innovation, EuroHPC JU ADMIRE","award":["956748 (EU), 16HPC006K (BMBF)"],"award-info":[{"award-number":["956748 (EU), 16HPC006K (BMBF)"]}]},{"name":"State of Hesse (HMWK) Chapter 1502, Funding 19 NHR4CES, German Federal Ministry of Education and Research (BMBF)","award":["NHR2021HE"],"award-info":[{"award-number":["NHR2021HE"]}]},{"name":"European Union's Horizon 2020 Framework Programme for Research and Innovation, EBRAINS research infrastructure Human Brain Project SGA3","award":["945539"],"award-info":[{"award-number":["945539"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,29]]},"DOI":"10.1145\/3545008.3545046","type":"proceedings-article","created":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T01:04:08Z","timestamp":1673744648000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["ElastiSim: A Batch-System Simulator for Malleable Workloads"],"prefix":"10.1145","author":[{"given":"Taylan","family":"\u00d6zden","sequence":"first","affiliation":[{"name":"Department of Computer Science, Technical University of Darmstadt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim","family":"Beringer","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Technical University of Darmstadt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arya","family":"Mazaheri","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Technical University of Darmstadt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hamid Mohammadi","family":"Fard","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Technical University of Darmstadt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix","family":"Wolf","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Technical University of Darmstadt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,1,13]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Maciej Besta Marcel Schneider Salvatore\u00a0Di Girolamo Ankit Singla and Torsten Hoefler. 2021. Towards Million-Server Network Simulations on Just a Laptop. arXiv:2105.12663"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2012.31"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Rajkumar Buyya and Manzur Murshed. 2002. Gridsim: A toolkit for the modeling and simulation of distributed resource management and scheduling for grid computing. Concurrency and computation: practice and experience 14 13-15(2002) 1175\u20131220.","DOI":"10.1002\/cpe.710"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503277"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2027066.2027068"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/UKSIM.2008.28"},{"key":"e_1_3_2_1_7_1","unstructured":"Marcia\u00a0C. Cera Yiannis Georgiou Olivier Richard Nicolas Maillard and Philippe Olivier\u00a0Alexandre Navaux. 2009. Supporting MPI Malleable Applications upon the OAR Resource Manager. In Colloque d\u2019Informatique: Br\u00e9sil \/ INRIA Coop\u00e9rations Avanc\u00e9es et D\u00e9fis(COLIBRI)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC50609.2020.00036"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2966884.2966917"},{"key":"e_1_3_2_1_10_1","volume-title":"Compr\u00e9s\u00a0Ure\u00f1a and Michael Gerndt","author":"A.","year":"2019","unstructured":"Isa\u00edas\u00a0A. Compr\u00e9s\u00a0Ure\u00f1a and Michael Gerndt. 2019. Towards Elastic Resource Management. In Proc. of the 11th International Workshop on Parallel Tools for High Performance Computing(PTHPC), Christoph Niethammer, Michael\u00a0M. Resch, Wolfgang\u00a0E. Nagel, Holger Brunst, and Hartmut Mix (Eds.). Springer, 105\u2013127."},{"key":"e_1_3_2_1_11_1","volume-title":"Proc. of the Workshop on Emerging Supercomputing Technologies(WEST, Vol.\u00a02011)","author":"Cope Jason","year":"2011","unstructured":"Jason Cope, Ning Liu, Sam Lang, Phil Carns, Chris Carothers, and Robert Ross. 2011. Codes: Enabling co-design of multilayer exascale storage architectures. In Proc. of the Workshop on Emerging Supercomputing Technologies(WEST, Vol.\u00a02011). ACM."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337909"},{"key":"e_1_3_2_1_13_1","unstructured":"DDN. 2022. IME\u00aeFLASH-NATIVE DATA CACHE | DDN. https:\/\/www.ddn.com\/products\/ime-flash-native-data-cache\/."},{"key":"e_1_3_2_1_14_1","volume-title":"Energy-aware scheduling of malleable HPC applications using a Particle Swarm optimised greedy algorithm. Sustainable Computing: Informatics and Systems 28","author":"Dupont Briag","year":"2020","unstructured":"Briag Dupont, Nesryne Mejri, and Georges Da Costa. 2020. Energy-aware scheduling of malleable HPC applications using a Particle Swarm optimised greedy algorithm. Sustainable Computing: Informatics and Systems 28 (2020)."},{"key":"e_1_3_2_1_15_1","volume-title":"Proc. 20th Workshop on Job Scheduling Strategies for Parallel Processing(JSSPP).","author":"Dutot Pierre-Fran\u00e7ois","year":"2016","unstructured":"Pierre-Fran\u00e7ois Dutot, Michael Mercier, Millian Poquet, and Olivier Richard. 2016. Batsim: a Realistic Language-Independent Resources and Jobs Management Systems Simulator. In Proc. 20th Workshop on Job Scheduling Strategies for Parallel Processing(JSSPP)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1272980.1272986"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2003.1231190"},{"key":"e_1_3_2_1_18_1","volume-title":"Feitelson and Larry Rudolph","author":"G.","year":"1996","unstructured":"Dror\u00a0G. Feitelson and Larry Rudolph. 1996. Towards Convergence in Job Schedulers for Parallel Supercomputers. In Proc. of the 2nd Workshop on Job Scheduling Strategies for Parallel Processing(JSSPP). Springer, 1\u201326."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.06.013"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/1345263.1345279"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-019-02905-5"},{"key":"e_1_3_2_1_22_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. arXiv:1512.03385"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2907294.2907316"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD.2004.27"},{"key":"e_1_3_2_1_25_1","unstructured":"Forrest\u00a0N. Iandola Song Han Matthew\u00a0W. Moskewicz Khalid Ashraf William\u00a0J. Dally and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5MB model size. arXiv:1602.07360"},{"key":"e_1_3_2_1_26_1","unstructured":"iMatix. 2022. ZeroMQ\u2014An open-source universal messaging library. https:\/\/zeromq.org\/."},{"key":"e_1_3_2_1_27_1","unstructured":"INRIA CNRS ENS Rennes and UH M\u0101noa. 2022. They use SimGrid. https:\/\/simgrid.org\/usages.html."},{"key":"e_1_3_2_1_28_1","volume-title":"Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads. In 2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Jeon Myeongjae","year":"2019","unstructured":"Myeongjae Jeon, Shivaram Venkataraman, Amar Phanishayee, Junjie Qian, Wencong Xiao, and Fan Yang. 2019. Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads. In 2019 USENIX Annual Technical Conference (USENIX ATC 19). USENIX Association, Renton, WA, 947\u2013960. https:\/\/www.usenix.org\/conference\/atc19\/presentation\/jeon"},{"key":"e_1_3_2_1_29_1","unstructured":"Zihan Jiang Wanling Gao Fei Tang Xingwang Xiong Lei Wang Chuanxin Lan Chunjie Luo Hongxiao Li and Jianfeng Zhan. 2021. HPC AI500: Representative Repeatable and Simple HPC AI Benchmarking. arXiv:2102.12848"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS.2018.8641556"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDSW.2010.5668066"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/3021426.3021446"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00046"},{"key":"e_1_3_2_1_34_1","volume-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky Alex","unstructured":"Alex Krizhevsky. 2012. Learning Multiple Layers of Features from Tiny Images. University of Toronto(2012)."},{"key":"e_1_3_2_1_35_1","unstructured":"Alex Krizhevsky. 2014. One weird trick for parallelizing convolutional neural networks. arXiv:1404.5997"},{"key":"e_1_3_2_1_36_1","unstructured":"Benjamin\u00a0R. Landsteiner Dave Henseler Douglas Petesch and Nicholas\u00a0J. Wright. 2016. Architecture and Design of Cray DataWarp. https:\/\/cug.org\/proceedings\/cug2016_proceedings\/includes\/files\/pap105s2-file1.pdf."},{"key":"e_1_3_2_1_37_1","volume-title":"Landsteiner and David Paul","author":"R.","year":"2018","unstructured":"Benjamin\u00a0R. Landsteiner and David Paul. 2018. DataWarp Transparent Cache: Implementation, Challenges, and Early Experience. https:\/\/cug.org\/proceedings\/cug2018_proceedings\/includes\/files\/pap119s2-file1.pdf."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2012.6232369"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40047-6_16"},{"key":"e_1_3_2_1_40_1","volume-title":"MPI: A Message-Passing Interface Standard Version 4.0. https:\/\/www.mpi-forum.org\/docs\/mpi-4.0\/mpi40-report.pdf","author":"Interface Forum Message Passing","year":"2021","unstructured":"Message Passing Interface Forum. 2021. MPI: A Message-Passing Interface Standard Version 4.0. https:\/\/www.mpi-forum.org\/docs\/mpi-4.0\/mpi40-report.pdf"},{"key":"e_1_3_2_1_41_1","unstructured":"Arash Partow. 2022. C++ Mathematical Expression Library. https:\/\/www.partow.net\/programming\/exprtk\/index.html."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.34"},{"key":"e_1_3_2_1_43_1","volume-title":"Proc. of the 12th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing(CCGrid). IEEE, 668\u2013675","author":"Quinson Martin","year":"2011","unstructured":"Martin Quinson, Cristian Rosa, and Christophe Thiery. 2011. Parallel Simulation of Peer-to-Peer Systems. In Proc. of the 12th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing(CCGrid). IEEE, 668\u2013675."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Ilija Radosavovic Raj\u00a0Prateek Kosaraju Ross Girshick Kaiming He and Piotr Doll\u00e1r. 2020. Designing Network Design Spaces. arXiv:2003.13678","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-77398-8_9"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_47_1","unstructured":"Alexander Sergeev and Mike\u00a0Del Balso. 2018. Horovod: fast and easy distributed deep learning in TensorFlow. arXiv:1802.05799"},{"key":"e_1_3_2_1_48_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/1297797.1297821"},{"key":"e_1_3_2_1_50_1","unstructured":"Massimo\u00a0Benini Stephen\u00a0Trofinoff. 2015. Using and Modifying the BSC Slurm Workload Simulator. https:\/\/slurm.schedmd.com\/SLUG15\/BSC_Slurm_Workload_Simulator_Enhancements.pdf."},{"key":"e_1_3_2_1_51_1","unstructured":"ThinkParQ and Fraunhofer ITWM. 2022. BeeOND: BeeGFS On Demand. https:\/\/doc.beegfs.io\/latest\/advanced_topics\/beeond.html"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00049"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517448"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.5555\/2388996.2389007"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/10968987_3"}],"event":{"name":"ICPP '22: 51st International Conference on Parallel Processing","location":"Bordeaux France","acronym":"ICPP '22"},"container-title":["Proceedings of the 51st International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3545008.3545046","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3545008.3545046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:44Z","timestamp":1750186964000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3545008.3545046"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,29]]},"references-count":55,"alternative-id":["10.1145\/3545008.3545046","10.1145\/3545008"],"URL":"https:\/\/doi.org\/10.1145\/3545008.3545046","relation":{},"subject":[],"published":{"date-parts":[[2022,8,29]]},"assertion":[{"value":"2023-01-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}