{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T07:22:30Z","timestamp":1774596150829,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T00:00:00Z","timestamp":1715040000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CAREER-2048044"],"award-info":[{"award-number":["CAREER-2048044"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Department of Energy, Office of Science","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,7]]},"DOI":"10.1145\/3629526.3645035","type":"proceedings-article","created":{"date-parts":[[2024,5,6]],"date-time":"2024-05-06T20:44:32Z","timestamp":1715028272000},"page":"190-200","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["MalleTrain: Deep Neural Networks Training on Unfillable Supercomputer Nodes"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1374-7086","authenticated-orcid":false,"given":"Xiaolong","family":"Ma","sequence":"first","affiliation":[{"name":"University of Nevada, Reno, Reno, NV, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9840-7754","authenticated-orcid":false,"given":"Feng","family":"Yan","sequence":"additional","affiliation":[{"name":"University of Houston, Houston, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5176-003X","authenticated-orcid":false,"given":"Lei","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Nevada, Reno, Reno, NV, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2129-5269","authenticated-orcid":false,"given":"Ian","family":"Foster","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory & University of Chicago, Lemont, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6418-5767","authenticated-orcid":false,"given":"Michael E.","family":"Papka","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory & University of Illinois Chicago, Lemont, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6647-4423","authenticated-orcid":false,"given":"Zhengchun","family":"Liu","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0046-9883","authenticated-orcid":false,"given":"Rajkumar","family":"Kettimuthu","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory & University of Chicago, Lemont, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,7]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2023. https:\/\/aws.amazon.com\/ec2\/spot\/. Accessed: 2023--10--23."},{"key":"e_1_3_2_1_2_1","unstructured":"2023. https:\/\/cloud.google.com\/spot-vms. Accessed: 2023--10--23."},{"key":"e_1_3_2_1_3_1","unstructured":"2023. https:\/\/azure.microsoft.com\/en-us\/products\/virtual-machines\/spot\/. Accessed: 2023--10--23."},{"key":"e_1_3_2_1_4_1","unstructured":"2023. https:\/\/www.alcf.anl.gov\/polaris. Accessed: 2023--10--23."},{"key":"e_1_3_2_1_5_1","unstructured":"2023. https:\/\/www.top500.org\/lists\/top500\/2023\/11\/. Accessed: 2023--11--15."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.58"},{"key":"e_1_3_2_1_7_1","volume-title":"A scalable, commodity data center network architecture. ACM SIGCOMM computer communication review 38, 4","author":"Al-Fares Mohammad","year":"2008","unstructured":"Mohammad Al-Fares, Alexander Loukissas, and Amin Vahdat. 2008. A scalable, commodity data center network architecture. ACM SIGCOMM computer communication review 38, 4 (2008), 63--74."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER51413.2022.00050"},{"key":"e_1_3_2_1_9_1","volume-title":"Workshop on Job Scheduling Strategies for Parallel Processing. Springer, 1--24","author":"Allcock William","year":"2017","unstructured":"William Allcock, Paul Rich, Yuping Fan, and Zhiling Lan. 2017. Experience and practice of batch scheduling on Leadership Supercomputers at Argonne. In Workshop on Job Scheduling Strategies for Parallel Processing. Springer, 1--24."},{"key":"e_1_3_2_1_10_1","volume-title":"Distributed optimization with tunable learned priors for robust ptycho-tomography. arXiv preprint arXiv:2009.09498","author":"Aslan Selin","year":"2020","unstructured":"Selin Aslan, Zhengchun Liu, Viktor Nikitin, Tekin Bicer, Sven Leyffer, and Doga Gursoy. 2020. Distributed optimization with tunable learned priors for robust ptycho-tomography. arXiv preprint arXiv:2009.09498 (2020)."},{"key":"e_1_3_2_1_11_1","unstructured":"Sebastian Buchwald Manuel Mohr and Andreas Zwinkau. 2015. Malleable Invasive Applications. In Software Engineering (Workshops). 123--126."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2019.2919690"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-007-0032-9"},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Machine Learning. PMLR, 1437--1446","author":"Falkner Stefan","year":"2018","unstructured":"Stefan Falkner, Aaron Klein, and Frank Hutter. 2018. BOHB: Robust and efficient hyperparameter optimization at scale. In International Conference on Machine Learning. PMLR, 1437--1446."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/646377.689507"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1254882.1254906"},{"key":"e_1_3_2_1_17_1","volume-title":"large minibatch SGD: Training ImageNet in 1 hour. arXiv preprint arXiv:1706.02677","author":"Goyal Priya","year":"2017","unstructured":"Priya Goyal, Piotr Doll\u00e1r, Ross Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, and Kaiming He. 2017. Accurate, large minibatch SGD: Training ImageNet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)."},{"key":"e_1_3_2_1_18_1","unstructured":"Matthew D Jones Joseph P White Martins Innus Robert L DeLeon Nikolay Simakov Jeffrey T Palmer Steven M Gallo Thomas R Furlani Michael Showerman Robert Brunner et al. 2017. Workload analysis of Blue Waters. arXiv preprint arXiv:1703.00924 (2017)."},{"key":"e_1_3_2_1_19_1","volume-title":"Predicting disruptive instabilities in controlled fusion plasmas through deep learning. Nature 568, 7753","author":"Kates-Harbeck Julian","year":"2019","unstructured":"Julian Kates-Harbeck, Alexey Svyatkovskiy, and William Tang. 2019. Predicting disruptive instabilities in controlled fusion plasmas through deep learning. Nature 568, 7753 (2019), 526--531."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1394608.1382129"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1115\/1.4062092"},{"key":"e_1_3_2_1_22_1","first-page":"230","article-title":"A system for massively parallel hyperparameter tuning","volume":"2","author":"Li Liam","year":"2020","unstructured":"Liam Li, Kevin Jamieson, Afshin Rostamizadeh, Ekaterina Gonina, Jonathan Ben- Tzur, Moritz Hardt, Benjamin Recht, and Ameet Talwalkar. 2020. A system for massively parallel hyperparameter tuning. Proceedings of Machine Learning and Systems 2 (2020), 230--246.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_23_1","volume-title":"DARTS: Differentiable architecture search. arXiv preprint arXiv:1806.09055","author":"Liu Hanxiao","year":"2018","unstructured":"Hanxiao Liu, Karen Simonyan, and Yiming Yang. 2018. DARTS: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/DLS49591.2019.00008"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid57682.2023.00036"},{"key":"e_1_3_2_1_26_1","volume-title":"BraggNN: Fast X-ray Bragg Peak Analysis Using Deep Learning. arXiv preprint arXiv:2008.08198","author":"Liu Zhengchun","year":"2020","unstructured":"Zhengchun Liu, Hemant Sharma, Jun-Sang Park, Peter Kenesei, Jonathan Almer, Rajkumar Kettimuthu, and Ian Foster. 2020. BraggNN: Fast X-ray Bragg Peak Analysis Using Deep Learning. arXiv preprint arXiv:2008.08198 (2020)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.932708"},{"key":"e_1_3_2_1_28_1","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga et al. 2019. PyTorch: An imperative style high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019)."},{"key":"e_1_3_2_1_29_1","volume-title":"Quantification and Implications. In 2020 SC20: International Conference for High Performance Computing, Networking, Storage and Analysis (SC). IEEE Computer Society, 1186--1202","author":"Patel Tirthak","year":"2020","unstructured":"Tirthak Patel, Zhengchun Liu, Rajkumar Kettimuthu, Paul Rich, William Allcock, and Devesh Tiwari. 2020. Job Characteristics on Large-Scale Systems: Long-Term Analysis, Quantification and Implications. In 2020 SC20: International Conference for High Performance Computing, Networking, Storage and Analysis (SC). IEEE Computer Society, 1186--1202."},{"key":"e_1_3_2_1_30_1","first-page":"1","article-title":"Pollux: Coadaptive Cluster Scheduling for Goodput-Optimized Deep Learning","volume":"21","author":"Qiao Aurick","year":"2021","unstructured":"Aurick Qiao, Sang Keun Choe, Suhas Jayaram Subramanya, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R Ganger, and Eric P Xing. 2021. Pollux: Coadaptive Cluster Scheduling for Goodput-Optimized Deep Learning.. In OSDI, Vol. 21. 1--18.","journal-title":"OSDI"},{"key":"e_1_3_2_1_31_1","volume-title":"Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning. arXiv preprint arXiv:2008.12260","author":"Qiao Aurick","year":"2020","unstructured":"Aurick Qiao, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R Ganger, and Eric P Xing. 2020. Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning. arXiv preprint arXiv:2008.12260 (2020)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"e_1_3_2_1_33_1","volume-title":"Horovod: Fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:1802.05799","author":"Sergeev Alexander","year":"2018","unstructured":"Alexander Sergeev and Mike Del Balso. 2018. Horovod: Fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:1802.05799 (2018)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626403001288"},{"key":"e_1_3_2_1_35_1","volume-title":"International Conference on Machine Learning. PMLR, 7105--7114","author":"Ying Chris","year":"2019","unstructured":"Chris Ying, Aaron Klein, Eric Christiansen, Esteban Real, Kevin Murphy, and Frank Hutter. 2019. NAS-Bench-101: Towards reproducible neural architecture search. In International Conference on Machine Learning. PMLR, 7105--7114."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/10968987_3"},{"key":"e_1_3_2_1_37_1","volume-title":"Workshop on Job Scheduling Strategies for Parallel Processing. Springer, 253--271","author":"You Haihang","year":"2012","unstructured":"Haihang You and Hao Zhang. 2012. Comprehensive workload analysis and modeling of a petascale supercomputer. In Workshop on Job Scheduling Strategies for Parallel Processing. Springer, 253--271."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"}],"event":{"name":"ICPE '24: 15th ACM\/SPEC International Conference on Performance Engineering","location":"London United Kingdom","acronym":"ICPE '24","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 15th ACM\/SPEC International Conference on Performance Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3629526.3645035","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3629526.3645035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T23:49:15Z","timestamp":1755906555000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3629526.3645035"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,7]]},"references-count":39,"alternative-id":["10.1145\/3629526.3645035","10.1145\/3629526"],"URL":"https:\/\/doi.org\/10.1145\/3629526.3645035","relation":{},"subject":[],"published":{"date-parts":[[2024,5,7]]},"assertion":[{"value":"2024-05-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}