{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T22:38:15Z","timestamp":1784241495685,"version":"3.55.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T00:00:00Z","timestamp":1735862400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T00:00:00Z","timestamp":1735862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["112-2221-E-033-024-MY3"],"award-info":[{"award-number":["112-2221-E-033-024-MY3"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-024-06849-5","type":"journal-article","created":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T09:57:15Z","timestamp":1735898235000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A fine-grained GPU sharing and job scheduling for deep learning jobs on the cloud"],"prefix":"10.1007","volume":"81","author":[{"given":"Wu-Chun","family":"Chung","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jyun-Sen","family":"Tong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi-Hao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,3]]},"reference":[{"issue":"5","key":"6849_CR1","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1145\/2890784","volume":"59","author":"B Burns","year":"2016","unstructured":"Burns B, Grant B, Oppenheimer D, Brewer E, Wilkes J (2016) Borg, omega, and Kubernetes. Commun ACM 59(5):50\u201357","journal-title":"Commun ACM"},{"key":"6849_CR2","unstructured":"NVIDIA device plugin for Kubernetes. https:\/\/github.com\/NVIDIA\/k8s-device-plugin. Accessed 19 August 2024"},{"key":"6849_CR3","doi-asserted-by":"crossref","unstructured":"Gu J, Song S, Li Y, Luo H (2018) GaiaGPU: Sharing GPUs in container clouds. In: 2018 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Ubiquitous Computing & Communications, Big Data & Cloud Computing, Social Computing & Networking, Sustainable Computing & Communications (ISPA\/IUCC\/BDCloud\/SocialCom\/SustainCom), IEEE, pp 469\u2013476.","DOI":"10.1109\/BDCloud.2018.00077"},{"key":"6849_CR4","doi-asserted-by":"crossref","unstructured":"Yeh TA, Chen HH, Chou J (2020) KubeShare: A framework to manage GPUs as first-class and shared resources in container cloud. In: Proceedings of the 29th international symposium on high-performance parallel and distributed computing, pp 173\u2013184.","DOI":"10.1145\/3369583.3392679"},{"key":"6849_CR5","unstructured":"Xiao W, Bhardwaj R, Ramjee R, Sivathanu M, Kwatra N, Han Z, Patel P, Peng X, Zhao H, Zhang Q et al (2018) Gandiva: Introspective cluster scheduling for deep learning. In: 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18), pp 595\u2013610."},{"key":"6849_CR6","doi-asserted-by":"crossref","unstructured":"Peng Y, Bao Y, Chen Y, Wu C, Guo C (2018) Optimus: an efficient dynamic resource scheduler for deep learning clusters. In: Proceedings of the Thirteenth EuroSys Conference, pp 1\u201314.","DOI":"10.1145\/3190508.3190517"},{"key":"6849_CR7","doi-asserted-by":"crossref","unstructured":"Han J, Rafique MM, Xu L, Butt AR, Lim SH, Vazhkudai SS (2020) Marble: A multi-GPU aware job scheduler for deep learning on HPC systems. In: 2020 20th IEEE\/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGRID), IEEE, pp 272\u2013281.","DOI":"10.1109\/CCGrid49817.2020.00-66"},{"key":"6849_CR8","doi-asserted-by":"crossref","unstructured":"Rattihalli G, Govindaraju M, Lu H, Tiwari D (2019) Exploring potential for non-disruptive vertical auto scaling and resource estimation in Kubernetes. In: 2019 IEEE 12th International Conference on Cloud Computing (CLOUD), IEEE, pp 33\u201340.","DOI":"10.1109\/CLOUD.2019.00018"},{"key":"6849_CR9","doi-asserted-by":"crossref","unstructured":"Chaudhary S, Ramjee R, Sivathanu M, Kwatra N, Viswanatha S (2020) Balancing efficiency and fairness in heterogeneous GPU clusters for deep learning. In: Proceedings of the Fifteenth European Conference on Computer Systems, pp 1\u201316.","DOI":"10.1145\/3342195.3387555"},{"key":"6849_CR10","unstructured":"Yu P, Chowdhury M (2019) Salus: Fine-grained GPU sharing primitives for deep learning applications. arXiv preprint arXiv:1902.04610."},{"key":"6849_CR11","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1016\/j.future.2021.06.021","volume":"125","author":"Z Li","year":"2021","unstructured":"Li Z, Chang V, Hu H, Fu M, Ge J, Piccialli F (2021) Optimizing makespan and resource utilization for multi-DNN training in GPU cluster. Future Gener Comput Syst 125:206\u2013220","journal-title":"Future Gener Comput Syst"},{"key":"6849_CR12","doi-asserted-by":"crossref","unstructured":"Lee CH, Li Z, Lu X, Chen T, Yang S, Wu C (2020) Multi-tenant machine learning platform based on Kubernetes. In: Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence, pp 5\u201312.","DOI":"10.1145\/3404555.3404565"},{"key":"6849_CR13","unstructured":"Yeung G, Borowiec D, Friday A, Harper R, Garraghan P (2020) Towards GPU utilization prediction for cloud deep learning. In: 12th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 20)."},{"key":"6849_CR14","unstructured":"Mahajan K, Balasubramanian A, Singhvi A, Venkataraman S, Akella A, Phanishayee A, Chawla S (2020) Themis: Fair and efficient GPU cluster scheduling. In: 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20), pp 289\u2013304."},{"key":"6849_CR15","unstructured":"Checkpoint\/Restore In Userspace. https:\/\/criu.org\/Main_Page. Accessed 19 August 2024."},{"key":"6849_CR16","unstructured":"NVIDIA Management Library (NVML). https:\/\/developer.nvidia.com\/management-library-nvml. Accessed 19 August 2024."},{"key":"6849_CR17","unstructured":"CUDA. https:\/\/developer.nvidia.com\/cuda-zone. Accessed 19 August 2024."},{"key":"6849_CR18","unstructured":"Jeon M, Venkataraman S, Phanishayee A, Qian J, Xiao W, Yang F (2019) Analysis of large-scale multi-tenant GPU clusters for DNN training workloads. In: 2019 USENIX Annual Technical Conference (USENIX ATC 19), pp 947\u2013960."},{"issue":"11","key":"6849_CR19","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"issue":"3","key":"6849_CR20","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1145\/359436.359453","volume":"20","author":"C Bays","year":"1977","unstructured":"Bays C (1977) A comparison of next-fit, first-fit, and best-fit. Commun ACM 20(3):191\u2013192","journal-title":"Commun ACM"},{"key":"6849_CR21","doi-asserted-by":"crossref","unstructured":"Yoo AB, Jette MA, Grondona M (2003) Slurm: Simple Linux utility for resource management. In: Workshop Job Scheduling Strategies Parallel Process, Springer, pp 44-60","DOI":"10.1007\/10968987_3"},{"key":"6849_CR22","doi-asserted-by":"crossref","unstructured":"Feng H, Misra V, Rubenstein D (2007) PBS: A unified priority-based scheduler. In: Proc 2007 ACM SIGMETRICS Int Conf Meas Model Comput Syst, pp 203\u2013214.","DOI":"10.1145\/1254882.1254906"},{"key":"6849_CR23","doi-asserted-by":"crossref","unstructured":"Lifka DA (1995) The ANL\/IBM SP scheduling system. In: Workshop Job Scheduling Strategies Parallel Process, Springer, pp 295\u2013303.","DOI":"10.1007\/3-540-60153-8_35"},{"issue":"6","key":"6849_CR24","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1109\/71.932708","volume":"12","author":"AW Mu\u2019alem","year":"2001","unstructured":"Mu\u2019alem AW, Feitelson DG (2001) Utilization, predictability, workloads, and user runtime estimates in scheduling the IBM SP2 with backfilling. IEEE Trans Parallel Distrib Syst 12(6):529\u2013543","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"6","key":"6849_CR25","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1109\/TPDS.2007.70606","volume":"18","author":"D Tsafrir","year":"2007","unstructured":"Tsafrir D, Etsion Y, Feitelson DG (2007) Backfilling using system-generated predictions rather than user runtime estimates. IEEE Trans Parallel Distrib Syst 18(6):789\u2013803","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"6849_CR26","unstructured":"Silberman N (2017) TF-Slim: A lightweight library for defining, training and evaluating complex models in TensorFlow. Georgia Inst Tech, Atlanta, CA, USA, Rep 2017."},{"key":"6849_CR27","unstructured":"Krizhevsky A, Hinton G et al (2009) Learning multiple layers of features from tiny images. Toronto, ON, Canada"},{"key":"6849_CR28","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proc IEEE Conf Comput Vis Pattern Recognit, pp 1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"6849_CR29","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"6849_CR30","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"key":"6849_CR31","unstructured":"Deitel HM (1990) An introduction to operating systems. Addison-Wesley, Reading"},{"issue":"1","key":"6849_CR32","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1007\/s11227-022-04682-2","volume":"79","author":"W Shen","year":"2023","unstructured":"Shen W, Liu Z, Tan Y, Luo Z, Lei Z (2023) KubeGPU: efficient sharing and isolation mechanisms for GPU resource management in container cloud. J Supercomput 79(1):591\u2013625","journal-title":"J Supercomput"},{"key":"6849_CR33","doi-asserted-by":"crossref","unstructured":"Chung WC, Tong JS (2023) A fine-grained scheduling based on GPU sharing for deep learning jobs on the cloud. In: 2023 International Conference on Consumer Electronics-Taiwan (ICCE-Taiwan), IEEE, pp 59\u201360","DOI":"10.1109\/ICCE-Taiwan58799.2023.10226864"},{"issue":"1","key":"6849_CR34","doi-asserted-by":"publisher","first-page":"79","DOI":"10.3354\/cr030079","volume":"30","author":"CJ Willmott","year":"2005","unstructured":"Willmott CJ, Matsuura K (2005) Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim Res 30(1):79\u201382","journal-title":"Clim Res"},{"key":"6849_CR35","doi-asserted-by":"publisher","first-page":"17557","DOI":"10.1109\/ACCESS.2021.3053162","volume":"9","author":"M Agung","year":"2021","unstructured":"Agung M, Watanabe Y, Weber H, Egawa R, Takizawa H (2021) Preemptive parallel job scheduling for heterogeneous systems supporting urgent computing. IEEE Access 9:17557\u201317571","journal-title":"IEEE Access"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06849-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-06849-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06849-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T10:10:52Z","timestamp":1735899052000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-06849-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,3]]},"references-count":35,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,1]]}},"alternative-id":["6849"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-06849-5","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,3]]},"assertion":[{"value":"17 December 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"361"}}