{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T16:56:06Z","timestamp":1776617766158,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Science and Technology Development Fund of Macau","award":["0024\/2022\/A1"],"award-info":[{"award-number":["0024\/2022\/A1"]}]},{"name":"Science and Technology Development Fund of Macau","award":["0071\/2023\/ITP2"],"award-info":[{"award-number":["0071\/2023\/ITP2"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1145\/3652892.3654792","type":"proceedings-article","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:36:13Z","timestamp":1732736173000},"page":"36-48","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Optimal Resource Efficiency with Fairness in Heterogeneous GPU Clusters"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3590-4400","authenticated-orcid":false,"given":"Zizhao","family":"Mo","sequence":"first","affiliation":[{"name":"University of Macau, Macau, Macao"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6657-1154","authenticated-orcid":false,"given":"Huanle","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Macau, Macau, Macao"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1179-7855","authenticated-orcid":false,"given":"Wing Cheong","family":"Lau","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}]}],"member":"320","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_2_1","volume-title":"Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. Attention is all you need. In Advances in neural information processing systems, 2017."},{"key":"e_1_3_2_1_3_1","volume-title":"Fast yolo: A fast you only look once system for real-time embedded object detection in video. arXiv preprint arXiv:1709.05943","author":"Shafiee Mohammad Javad","year":"2017","unstructured":"Mohammad Javad Shafiee, Brendan Chywl, Francis Li, and Alexander Wong. Fast yolo: A fast you only look once system for real-time embedded object detection in video. arXiv preprint arXiv:1709.05943, 2017."},{"key":"e_1_3_2_1_4_1","volume-title":"https:\/\/cloud.google.com\/gpu","author":"Google","year":"2022","unstructured":"Google cloud platform. https:\/\/cloud.google.com\/gpu, 2022-10-20."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of NSDI","author":"Gu Juncheng","year":"2019","unstructured":"Juncheng Gu, Mosharaf Chowdhury, Kang G Shin, Yibo Zhu, Myeongjae Jeon, Junjie Qian, Hongqiang Liu, and Chuanxiong Guo. Tiresias: A GPU cluster manager for distributed deep learning. In Proceedings of NSDI, 2019."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of Eurosys","author":"Peng Yanghua","year":"2018","unstructured":"Yanghua Peng, Yixin Bao, Yangrui Chen, Chuan Wu, and Chuanxiong Guo. Optimus: An efficient dynamic resource scheduler for deep learning clusters. In Proceedings of Eurosys, 2018."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387547"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of OSDI","author":"Narayanan Deepak","year":"2020","unstructured":"Deepak Narayanan, Keshav Santhanam, Fiodar Kazhamiaka, Amar Phanishayee, and Matei Zaharia. Heterogeneity-aware cluster scheduling policies for deep learning workloads. In Proceedings of OSDI, 2020."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of NSDI","author":"Mahajan Kshiteej","year":"2020","unstructured":"Kshiteej Mahajan, Arjun Balasubramanian, Arjun Singhvi, Shivaram Venkataraman, Aditya Akella, Amar Phanishayee, and Shuchi Chawla. Themis: Fair and efficient GPU cluster scheduling. In Proceedings of NSDI, 2020."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/75246.75248"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/321738.321743"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/2808941"},{"key":"e_1_3_2_1_14_1","first-page":"345","volume-title":"Proceedings of the twenty-fifth annual ACM symposium on Theory of computing","author":"Proportionate","year":"1993","unstructured":"Proportionate progress: A notion of fairness in resource allocation. In Proceedings of the twenty-fifth annual ACM symposium on Theory of computing, pages 345--354, 1993."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/645605.663243"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1109\/REAL.2003.1253262","volume-title":"RTSS 2003. 24th IEEE Real-Time Systems Symposium, 2003","author":"Zhu Dakai","year":"2003","unstructured":"Dakai Zhu, Daniel Moss\u00e9, and Rami Melhem. Multiple-resource periodic scheduling problem: how much fairness is necessary? In RTSS 2003. 24th IEEE Real-Time Systems Symposium, 2003, pages 142--151. IEEE, 2003."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/964723.383074"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/SFFCS.1999.814631"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of NSDI","author":"Ghodsi Ali","year":"2011","unstructured":"Ali Ghodsi, Matei Zaharia, Benjamin Hindman, Andy Konwinski, Scott Shenker, and Ion Stoica. Dominant resource fairness: Fair allocation of multiple resource types. In Proceedings of NSDI, 2011."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1629575.1629601"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of OSDI","author":"Grandl Robert","year":"2016","unstructured":"Robert Grandl, Mosharaf Chowdhury, Aditya Akella, and Ganesh Ananthanarayanan. Altruistic scheduling in multi-resource clusters. In Proceedings of OSDI, 2016."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of NSDI","author":"Chowdhury Mosharaf","year":"2016","unstructured":"Mosharaf Chowdhury, Zhenhua Liu, Ali Ghodsi, and Ion Stoica. {HUG}:{Multi-Resource} fairness for correlated and elastic demands. In Proceedings of NSDI, 2016."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7996727"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2362139"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.85"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1981.1095081"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.2737\/FPL-GTR-290"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476223"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of ATC","author":"Jeon Myeongjae","year":"2019","unstructured":"Myeongjae Jeon, Shivaram Venkataraman, Amar Phanishayee, Junjie Qian, Wencong Xiao, and Fan Yang. Analysis of large-scale multi-tenant GPU clusters for DNN training workloads. In Proceedings of ATC, 2019."},{"key":"e_1_3_2_1_30_1","volume-title":"The lovely but lonely vickrey auction. Combinatorial auctions","author":"Ausubel Lawrence M","year":"2006","unstructured":"Lawrence M Ausubel, Paul Milgrom, et al. The lovely but lonely vickrey auction. Combinatorial auctions, 2006."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of OSDI","author":"Xiao Wencong","year":"2020","unstructured":"Wencong Xiao, Shiru Ren, Yong Li, Yang Zhang, Pengyang Hou, Zhi Li, Yihui Feng, Wei Lin, and Yangqing Jia. Antman: Dynamic scaling on GPU clusters for deep learning. In Proceedings of OSDI, 2020."},{"key":"e_1_3_2_1_32_1","volume-title":"On extreme points of convex sets. Journal of mathematical analysis and applications","author":"Dubins Lester E.","year":"1962","unstructured":"Lester E. Dubins. On extreme points of convex sets. Journal of mathematical analysis and applications, 1962."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of OSDI)","author":"Mohan Jayashree","year":"2022","unstructured":"Jayashree Mohan, Amar Phanishayee, Janardhan Kulkarni, and Vijay Chidambaram. Looking beyond {GPUs} for {DNN} scheduling on {Multi-Tenant} clusters. In Proceedings of OSDI), 2022."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3305218.3305227"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/75246.75248"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.1992.263509"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of INFOCOM","author":"Zhang Hui","year":"1996","unstructured":"Hui Zhang and Jon CR Bennett. Wf2q: worst-case fair weighted fair queueing. In Proceedings of INFOCOM, 1996."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/248156.248171"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/217382.217453"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.21236\/ADA333257"},{"key":"e_1_3_2_1_41_1","volume-title":"Multiresource allocation: Fairness-efficiency tradeoffs in a unifying framework","author":"Joe-Wong Carlee","year":"2013","unstructured":"Carlee Joe-Wong, Soumya Sen, Tian Lan, and Mung Chiang. Multiresource allocation: Fairness-efficiency tradeoffs in a unifying framework. IEEE\/ACM Transactions on Networking, 2013."},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of NSDI","author":"Hwang Changho","year":"2021","unstructured":"Changho Hwang, Taehyun Kim, Sunghyun Kim, Jinwoo Shin, and Kyoung Soo Park. Elastic resource sharing for distributed deep learning. In Proceedings of NSDI, 2021."}],"event":{"name":"Middleware '24: 25th International Middleware Conference","location":"Hong Kong Hong Kong","acronym":"Middleware '24","sponsor":["IFIP","Usenix"]},"container-title":["Proceedings of the 25th International Middleware Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652892.3654792","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652892.3654792","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:53:57Z","timestamp":1750287237000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652892.3654792"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":42,"alternative-id":["10.1145\/3652892.3654792","10.1145\/3652892"],"URL":"https:\/\/doi.org\/10.1145\/3652892.3654792","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2024-12-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}