{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T09:53:44Z","timestamp":1770458024385,"version":"3.49.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023,1,1]]},"DOI":"10.1109\/tcc.2021.3119205","type":"journal-article","created":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T20:18:04Z","timestamp":1633983484000},"page":"854-867","source":"Crossref","is-referenced-by-count":9,"title":["Gemini: Enabling Multi-Tenant GPU Sharing Based on Kernel Burst Estimation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4171-7991","authenticated-orcid":false,"given":"Hung-Hsin","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4229-3959","authenticated-orcid":false,"given":"En-Te","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5557-0033","authenticated-orcid":false,"given":"Yu-Min","family":"Chou","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7851-1140","authenticated-orcid":false,"given":"Jerry","family":"Chou","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"}]}],"member":"263","reference":[{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2462902.2462915"},{"key":"ref3","first-page":"499","article-title":"PipeSwitch: Fast pipelined context switching for deep learning applications","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation","author":"Bai"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018748"},{"key":"ref6","article-title":"The GitHub repository of gemini","author":"Chen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS.2010.5547126"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15277-1_37"},{"key":"ref9","article-title":"Kubernetes cluster management"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2016.94"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/BDCloud.2018.00077"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2017.17"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2011.13"},{"key":"ref14","article-title":"TimeGraph: GPU scheduling for real-time multi-tasking environments","volume-title":"Proc. USENIX Conf. USENIX Annu. Tech. Conf.","author":"Kato"},{"key":"ref15","first-page":"401","article-title":"Gdev: First-class GPU resource management in the operating system","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Kato"},{"key":"ref16","first-page":"161","article-title":"Zico: Efficient GPU memory sharing for concurrent DNN training","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Lim"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref18","article-title":"maskrcnn-benchmark: Fast, modular reference implementation of instance segmentation and object detection algorithms in PyTorch","author":"Massa","year":"2018"},{"key":"ref19","first-page":"291","article-title":"Enabling OS research by inferring interactions in the black-box GPU stack","volume-title":"Proc. USENIX Conf. Annu. Tech. Conf.","author":"Menychtas"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541963"},{"key":"ref21","article-title":"NVIDIAs next generation CUDA compute architecture: Kepler GK110","year":"2012","journal-title":"GPU Technol. Conf."},{"key":"ref22","article-title":"Sharing a GPU between MPI processes: Multi-process service (MPS) overview","year":"2013"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451160"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694346"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2632216"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1996130.1996160"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2043556.2043579"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.47"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2465829.2465830"},{"key":"ref30","first-page":"109","article-title":"GPUvm: Why not virtualizing GPUs at the hypervisor?,","volume-title":"Proc. USENIX Conf. USENIX Annu. Tech. Conf.","author":"Suzuki"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037742"},{"key":"ref32","article-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref33","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"},{"key":"ref34","article-title":"Salus: Fine-grained GPU sharing primitives for deep learning applications","volume-title":"Proc. 3rd MLSys Conf.","author":"Yu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.288"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2018.00077"}],"container-title":["IEEE Transactions on Cloud Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6245519\/10061174\/09566822.pdf?arnumber=9566822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:41:55Z","timestamp":1705016515000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9566822\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,1]]},"references-count":35,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcc.2021.3119205","relation":{},"ISSN":["2168-7161","2372-0018"],"issn-type":[{"value":"2168-7161","type":"electronic"},{"value":"2372-0018","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,1]]}}}