{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:28:06Z","timestamp":1784644086706,"version":"3.55.0"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFB2904600"],"award-info":[{"award-number":["2023YFB2904600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62394324"],"award-info":[{"award-number":["62394324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102066"],"award-info":[{"award-number":["62102066"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Elite Scientists Sponsorship Program","award":["2022QNRC001"],"award-info":[{"award-number":["2022QNRC001"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["ZYGX2022J003"],"award-info":[{"award-number":["ZYGX2022J003"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cloud Comput."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tcc.2025.3548604","type":"journal-article","created":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T13:44:58Z","timestamp":1741268698000},"page":"590-604","source":"Crossref","is-referenced-by-count":13,"title":["Deadline-Aware Online Job Scheduling for Distributed Training in Heterogeneous Clusters"],"prefix":"10.1109","volume":"13","author":[{"given":"Yuchen","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1028-8178","authenticated-orcid":false,"given":"Long","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2448-8915","authenticated-orcid":false,"given":"Gang","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5219-1780","authenticated-orcid":false,"given":"Hongfang","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2083-9105","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.10.001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3285029"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2023.3308161"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2023.3336540"},{"key":"ref6","article-title":"Tesla P100 performance","year":"2024"},{"key":"ref7","article-title":"Tesla V100 performance","year":"2024"},{"key":"ref8","article-title":"A100 tensor core GPU","year":"2024"},{"key":"ref9","article-title":"H100 tensor core GPU","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486978"},{"key":"ref11","first-page":"185","article-title":"Can\u2019t be late: Optimizing spot instance savings under deadlines","volume-title":"Proc. USENIX Conf. Networked Syst. Des. Implementation","author":"Wu","year":"2024"},{"key":"ref12","article-title":"NVIDIA tesla V100vs nvidia H100 (PCIE)","year":"2024"},{"key":"ref13","first-page":"481","article-title":"Heterogeneity-aware cluster scheduling policies for deep learning workloads","volume-title":"Proc. USENIX Conf. Operating Syst. Des. Implementation","author":"Narayanan","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486422"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref16","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","volume-title":"Proc. USENIX Conf. Operating Syst. Des. Implementation","author":"Xiao","year":"2018"},{"key":"ref17","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","volume-title":"Proc. USENIX Conf. Networked Syst. Des. Implementation","author":"Gu","year":"2019"},{"key":"ref18","first-page":"1","article-title":"Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning","volume-title":"Proc. USENIX Conf. Operating Syst. Des. Implementation","author":"Qiao","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3052895"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796785"},{"key":"ref21","first-page":"721","article-title":"Elastic resource sharing for distributed deep learning","volume-title":"Proc. USENIX Conf. Networked Syst. Des. Implementation","author":"Hwang","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587445"},{"key":"ref23","first-page":"289","article-title":"Themis: Fair and efficient GPU cluster scheduling","volume-title":"Proc. USENIX Conf. Networked Syst. Des. Implementation","author":"Mahajan","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3136245"},{"key":"ref26","first-page":"703","article-title":"Shockwave: Fair and efficient cluster scheduling for dynamic adaptation in machine learning","volume-title":"Proc. USENIX Conf. Networked Syst. Des. Implementation","author":"Zheng","year":"2023"},{"key":"ref27","first-page":"1403","article-title":"Cassini: Network-aware job scheduling in machine learning clusters","volume-title":"Proc. USENIX Conf. Networked Syst. Des. Implementation","author":"Rajasekaran","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3371794"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575721"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613175"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS57955.2024.00066"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640375"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref35","first-page":"1","article-title":"Large scale distributed deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dean","year":"2012"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref37","first-page":"1","article-title":"PipeFream: Generalized pipeline parallelism for DNN training","volume-title":"Proc. 27th ACM Symp. Operating Syst. Princ.","author":"Narayanan","year":"2019"},{"key":"ref38","first-page":"1","article-title":"Beyond data and model parallelism for deep neural networks","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Jia","year":"2019"},{"key":"ref39","article-title":"Torchelastic","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3573037"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1002\/0471787779"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/sj.jors.2600425"},{"key":"ref43","article-title":"ElasticFlow: A framework for elastic resource management in distributed systems","author":"Group","year":"2023"},{"key":"ref44","article-title":"NVIDIA A100vs V100 benchmarks","year":"2021"},{"key":"ref45","article-title":"NVIDIA tesla V100vs NVIDIA RTX 3090 benchmarks","year":"2024"},{"key":"ref46","article-title":"Nvidia a100 GPU deep learning benchmarks and architectural overview","year":"2023"},{"key":"ref47","article-title":"Elasticflow traces","year":"2022"},{"key":"ref48","first-page":"631","article-title":"Litz: Elastic framework for high-performance distributed machine learning","volume-title":"Proc. USENIX Conf. Usenix Annu. Tech. Conf.","author":"Qiao","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2931558"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3064966"},{"key":"ref52","first-page":"533","article-title":"Antman: Dynamic scaling on GPU clusters for deep learning","volume-title":"Proc. USENIX Conf. Operating Syst. Des. Implementation","author":"Xiao","year":"2020"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2022.3143153"}],"container-title":["IEEE Transactions on Cloud Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6245519\/11027456\/10916521.pdf?arnumber=10916521","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:46:01Z","timestamp":1755546361000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10916521\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":53,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcc.2025.3548604","relation":{},"ISSN":["2168-7161","2372-0018"],"issn-type":[{"value":"2168-7161","type":"electronic"},{"value":"2372-0018","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}