{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:46:45Z","timestamp":1773193605607,"version":"3.50.1"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202143"],"award-info":[{"award-number":["62202143"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004761","name":"Natural Science Foundation of Henan Province, China","doi-asserted-by":"crossref","award":["252300421230"],"award-info":[{"award-number":["252300421230"]}],"id":[{"id":"10.13039\/501100004761","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cloud Comput."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tcc.2026.3658199","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T20:30:15Z","timestamp":1769545815000},"page":"242-258","source":"Crossref","is-referenced-by-count":0,"title":["Fragmentation-Aware and Efficiency-Oriented Scheduling for GPU Sharing Workloads"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7301-1690","authenticated-orcid":false,"given":"Delai","family":"Deng","sequence":"first","affiliation":[{"name":"School of Computer and Information Engineering, Henan University, Kaifeng, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8538-6309","authenticated-orcid":false,"given":"Yuxiang","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer and Information Engineering, Henan University, Kaifeng, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0801-8443","authenticated-orcid":false,"given":"Yulei","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Electrical, Electronic and Mechanical Engineering, University of Bristol, Bristol, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8784-0364","authenticated-orcid":false,"given":"Huijie","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer and Information Engineering, Henan University, Kaifeng, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3025916"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00036"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3094295"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3158270"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587445"},{"key":"ref7","first-page":"945","article-title":"MLaaS in the wild: Workload analysis and scheduling in large-scale heterogeneous GPU clusters","volume-title":"Proc. 19th USENIX Symp. Networked Syst. Des. Implementation","author":"Weng","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3721427"},{"key":"ref9","first-page":"995","article-title":"Beware of fragmentation: Scheduling GPU-sharing workloads with fragmentation gradient descent","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Weng","year":"2023"},{"key":"ref10","first-page":"579","article-title":"Looking beyond GPUs for DNN scheduling on multi-tenant clusters","volume-title":"Proc. 16th USENIX Symp. Operating Syst. Des. Implementation","author":"Mohan","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626334"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3698038.3698515"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3242200"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486978"},{"key":"ref15","first-page":"481","article-title":"Heterogeneity-aware cluster scheduling policies for deep learning workloads","volume-title":"Proc. USENIX Symp. Operating Syst. Des. Implementation","author":"Narayanan","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387547"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/BDCloud.2018.00077"},{"key":"ref18","first-page":"539","article-title":"Microsecond-scale preemption for concurrent GPU-accelerated DNN inferences","volume-title":"Proc. 16th USENIX Symp. Operating Syst. Des. Implementation","author":"Han","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2011.112"},{"key":"ref20","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Des. Implementation","author":"Xiao","year":"2018"},{"key":"ref21","first-page":"173","article-title":"KubeShare: A framework to manage GPUs as first-class and shared resources in container cloud","volume-title":"Proc. 29th Int. Symp. High- Perform. Parallel Distrib. Comput.","author":"Chen","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330370"},{"key":"ref23","article-title":"NVIDIA multi-instance GPU: Seven independent instances in a single GPU","year":"2023"},{"key":"ref24","first-page":"845","article-title":"Protean:VM allocation service at scale","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation","author":"Hadary","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3293835"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref27","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","volume-title":"Proc. 16th USENIX Symp. Networked Syst. Des. Implementation","author":"Gu","year":"2019"},{"key":"ref28","first-page":"289","article-title":"Themis: Fair and efficient GPU cluster scheduling","volume-title":"Proc. 17th USENIX Symp. Networked Syst. Des. Implementation","author":"Mahajan","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3371794"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS57955.2024.00066"},{"key":"ref31","article-title":"Rubick: Exploiting job reconfigurability for deep learning cluster scheduling","volume-title":"Proc. Mach. Learn. Syst.","volume":"7","author":"Zhang","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544224"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"ref34","first-page":"515","article-title":"HiveD: Sharing a GPU cluster for deep learning with guarantees","volume-title":"Proc. USENIX Symp. Operating Syst. Des. Implementation","author":"Zhao","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2014.6968735"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640375"},{"key":"ref37","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref38","first-page":"533","article-title":"AntMan: Dynamic scaling on GPU clusters for deep learning","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation","author":"Xiao","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2025.3548604"}],"container-title":["IEEE Transactions on Cloud Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6245519\/11427054\/11365979.pdf?arnumber=11365979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T05:22:09Z","timestamp":1773120129000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11365979\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":39,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcc.2026.3658199","relation":{},"ISSN":["2168-7161","2372-0018"],"issn-type":[{"value":"2168-7161","type":"electronic"},{"value":"2372-0018","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}