{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T05:23:00Z","timestamp":1782278580185,"version":"3.54.5"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cloud Comput."],"published-print":{"date-parts":[[2023,7,1]]},"DOI":"10.1109\/tcc.2023.3264242","type":"journal-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T17:35:52Z","timestamp":1680543352000},"page":"3153-3167","source":"Crossref","is-referenced-by-count":8,"title":["Dynamic GPU Scheduling With Multi-Resource Awareness and Live Migration Support"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8940-8042","authenticated-orcid":false,"given":"Xiaoyang","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3743-8511","authenticated-orcid":false,"given":"Yongkun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6842-5899","authenticated-orcid":false,"given":"Fan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9586-0561","authenticated-orcid":false,"given":"Yinlong","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7466-0384","authenticated-orcid":false,"given":"John C. S.","family":"Lui","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Theano: Deep learning on GPUs with python","volume":"3","author":"bergstra","year":"2011","journal-title":"Proc NIPS BigLearning Workshop"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.47"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00035"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2465829.2465830"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/PDCAT.2009.78"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS49563.2019.00014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2011.112"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2786763.2694346"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.131"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid54584.2022.00079"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2924433"},{"key":"ref10","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc 12th USENIX Conf Operating Syst Des Implementation"},{"key":"ref32","first-page":"665","article-title":"MDev-NVMe: A NVMe storage virtualization solution with mediated Pass-Through","author":"peng","year":"2018","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref2","year":"2023","journal-title":"CUDA Samples"},{"key":"ref1","year":"2017","journal-title":"Cloud computing is still dangerously underutilized"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1618525.1618534"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.73"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2013.102"},{"key":"ref38","first-page":"121","article-title":"A full GPU virtualization solution with mediated Pass-Through","author":"tian","year":"2014","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00077"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5753\/wperformance.2017.3360"},{"key":"ref24","article-title":"A quantitative measure of fairness and discrimination for resource allocation in shared systems","author":"jain","year":"1984"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378466"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15291-7_23"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3079202"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-03779-4"},{"key":"ref25","article-title":"KVMGT: A full GPU virtualization solution","author":"song","year":"2014","journal-title":"KVM Forum"},{"key":"ref47","article-title":"Full virtualization for GPUs reconsidered","author":"yu","year":"2017","journal-title":"Proc Annu Workshop Duplicating Deconstructing Debunking"},{"key":"ref20","article-title":"Fine-grained resource sharing for concurrent GPGPU kernels","author":"gregg","year":"2012","journal-title":"Proc 4th USENIX Conf Hot Topics Parallelism"},{"key":"ref42","article-title":"AntMan: Dynamic scaling on GPU clusters for deep learning","author":"xiao","year":"2020","journal-title":"Proc USENIX Conf Operating Syst Des Implementation"},{"key":"ref41","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","author":"xiao","year":"2018","journal-title":"Proc 13th USENIX Conf Operating Syst Des Implementation"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00209"},{"key":"ref44","article-title":"Towards GPU utilization prediction for cloud deep learning","author":"yeung","year":"2020","journal-title":"Proc 12th USENIX Conf Hot Topics Cloud Comput"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3138825"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3365657"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063398"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2019.2955119"},{"key":"ref29","first-page":"579","article-title":"Looking beyond GPUs for DNN scheduling on Multi-Tenant clusters","author":"mohan","year":"2022","journal-title":"Proc USENIX Conf Operating Syst Des Implementation"},{"key":"ref8","year":"2016","journal-title":"Unified memory on pascal"},{"key":"ref7","year":"2023","journal-title":"Tensorflow Benchmarks"},{"key":"ref9","year":"2016","journal-title":"VGG 16"},{"key":"ref4","year":"2023","journal-title":"nvdia-smi"},{"key":"ref3","year":"2023","journal-title":"Cuda Toolkit"},{"key":"ref6","year":"2023","journal-title":"Nvprof"},{"key":"ref5","year":"2023","journal-title":"NVIDIA GRID"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC.2012.116"}],"container-title":["IEEE Transactions on Cloud Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6245519\/10241247\/10091187.pdf?arnumber=10091187","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T17:11:30Z","timestamp":1717693890000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10091187\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,1]]},"references-count":47,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcc.2023.3264242","relation":{},"ISSN":["2168-7161","2372-0018"],"issn-type":[{"value":"2168-7161","type":"electronic"},{"value":"2372-0018","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,1]]}}}