{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:33:28Z","timestamp":1773246808272,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0160201"],"award-info":[{"award-number":["2022ZD0160201"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"RIE2020 Industry Alignment Fund - Industry Collaboration Projects"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tc.2024.3371794","type":"journal-article","created":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T18:53:20Z","timestamp":1709232800000},"page":"1500-1515","source":"Crossref","is-referenced-by-count":9,"title":["UniSched: A Unified Scheduler for Deep Learning Training Jobs With Different User Demands"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7048-1722","authenticated-orcid":false,"given":"Wei","family":"Gao","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4568-0244","authenticated-orcid":false,"given":"Zhisheng","family":"Ye","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8456-0491","authenticated-orcid":false,"given":"Peng","family":"Sun","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab & SenseTime, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-6650","authenticated-orcid":false,"given":"Tianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2751-5114","authenticated-orcid":false,"given":"Yonggang","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Des. Implementation (OSDI)","author":"Xiao","year":"2018"},{"key":"ref2","first-page":"947","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Jeon","year":"2019"},{"key":"ref3","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","volume-title":"Proc. 16th USENIX Symp. Netw. Syst. Des. Implementation (NSDI)","author":"Gu","year":"2019"},{"key":"ref4","first-page":"515","article-title":"HiveD: Sharing a GPU cluster for deep learning with guarantees","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation (OSDI)","author":"Zhao","year":"2020"},{"key":"ref5","first-page":"533","article-title":"AntMan: Dynamic scaling on GPU clusters for deep learning","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation (OSDI)","author":"Xiao","year":"2020"},{"key":"ref6","first-page":"1","article-title":"Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning","volume-title":"Proc. 15th USENIX Symp. Operating Syst. Des. Implementation (OSDI)","author":"Qiao","year":"2021"},{"key":"ref7","first-page":"289","article-title":"THEMIS: Fair and efficient GPU cluster scheduling","volume-title":"Proc. 17th USENIX Symp. Netw. Syst. Des. Implementation (NSDI)","author":"Mahajan","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387547"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3136245"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2670979.2670981"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2489646"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901355"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2931558"},{"key":"ref15","first-page":"265","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","volume-title":"Proc. 12th USENIX Conf. Operating Syst. Des. Implementation","author":"Abadi","year":"2016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3357223.3362719"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486978"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3242200"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref20","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref21","first-page":"3460","article-title":"Speeding up automatic hyperparameter optimization of deep neural networks by extrapolation of learning curves","volume-title":"Proc. 24th Int. Joint Conf. Artif. Intell. (IJCAI)","author":"Domhan","year":"2015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190515"},{"key":"ref23","first-page":"1","article-title":"Characterization and prediction of deep learning workloads in large-scale GPU datacenters","volume-title":"Proc. Int. Conf. High Perform. Comput., Netw., Storage Anal.","author":"Hu","year":"2021"},{"key":"ref24","article-title":"Kubernetes Contributors","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456245"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/globecom38437.2019.9014110"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2020.102590"},{"key":"ref28","article-title":"Tune: A research platform for distributed model selection and training","author":"Liaw","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"ref30","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"},{"key":"ref32","article-title":"Aryl: An elastic cluster scheduler for deep learning","author":"Li","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2928289"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3127490"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2898442.2898444"},{"key":"ref36","article-title":"Gurobi optimization","year":"2022"},{"key":"ref37","article-title":"Generalized mixed integer optimization in go","year":"2022"},{"key":"ref38","first-page":"481","article-title":"Heterogeneity-aware cluster scheduling policies for deep learning workloads","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation (OSDI)","author":"Narayanan","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3386367.3432588"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3136245"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/10527219\/10454114.pdf?arnumber=10454114","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T04:57:47Z","timestamp":1715317067000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10454114\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":40,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tc.2024.3371794","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}