{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T21:14:52Z","timestamp":1764018892882,"version":"3.37.3"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2020,1,9]],"date-time":"2020-01-09T00:00:00Z","timestamp":1578528000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,9]],"date-time":"2020-01-09T00:00:00Z","timestamp":1578528000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2015M3C4A7065646","2017R1A2B4005681"],"award-info":[{"award-number":["2015M3C4A7065646","2017R1A2B4005681"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1007\/s10586-019-03044-7","type":"journal-article","created":{"date-parts":[[2020,1,9]],"date-time":"2020-01-09T08:02:57Z","timestamp":1578556977000},"page":"2219-2234","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Job placement using reinforcement learning in GPU virtualization environment"],"prefix":"10.1007","volume":"23","author":[{"given":"Jisun","family":"Oh","sequence":"first","affiliation":[]},{"given":"Yoonhee","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,1,9]]},"reference":[{"key":"3044_CR1","unstructured":"Amazon ec2. https:\/\/aws.amazon.com\/ec2\/"},{"key":"3044_CR2","unstructured":"Nimbix. https:\/\/www.nimbix.net\/cloud-computing-nvidia\/"},{"key":"3044_CR3","unstructured":"Microsoft azure. https:\/\/docs.microsoft.com\/en-au\/azure\/virtual-machines\/windows\/sizes-gpu"},{"key":"3044_CR4","unstructured":"Alibaba. https:\/\/www.alibabacloud.com\/ko\/product\/gpu"},{"key":"3044_CR5","unstructured":"Kubernetes. https:\/\/kubernetes.io\/docs\/tasks\/manage-gpus\/scheduling-gpus\/"},{"key":"3044_CR6","unstructured":"Mesos. http:\/\/mesos.apache.org\/documentation\/latest\/gpu-support\/"},{"key":"3044_CR7","doi-asserted-by":"crossref","unstructured":"Liu, M., Li, T., Jia, N., Currid, A., Troy, V.: Understanding the virtualization\u201d tax\u201d of scale-out pass-through gpus in gaas clouds: An empirical study. In: 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA), pp. 259\u2013270. IEEE (2015)","DOI":"10.1109\/HPCA.2015.7056038"},{"key":"3044_CR8","doi-asserted-by":"crossref","unstructured":"Tang, X., Wang, H., Ma, X., El-Sayed, N., Zhai, J., Chen, W., Aboulnaga, A.: Spread-n-share: improving application performance and cluster throughput with resource-aware job placement. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, p.\u00a012. ACM (2019)","DOI":"10.1145\/3295500.3356152"},{"key":"3044_CR9","doi-asserted-by":"crossref","unstructured":"Duato, J., Pena, A.J., Silla, F., Mayo, R., Quintana-Ort\u00ed, E.S.: rCUDA: Reducing the number of gpu-based accelerators in high performance clusters. In: 2010 International Conference on High Performance Computing & Simulation, pp.\u00a0224\u2013231. IEEE (2010)","DOI":"10.1109\/HPCS.2010.5547126"},{"key":"3044_CR10","doi-asserted-by":"crossref","unstructured":"Ilager, S., Wankar, R., Kune, R., Buyya, R.: Gpu paas computation model in aneka cloud computing environments. Smart Data: State-of-the-Art Perspectives in Computing and Applications, p.\u00a019 (2019)","DOI":"10.1201\/9780429507670-2"},{"key":"3044_CR11","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1016\/j.future.2017.05.042","volume":"79","author":"AN Toosi","year":"2018","unstructured":"Toosi, A.N., Sinnott, R.O., Buyya, R.: Resource provisioning for data-intensive applications with deadline constraints on hybrid clouds using aneka. Future Gener. Comput. Syst. 79, 765\u2013775 (2018)","journal-title":"Future Gener. Comput. Syst."},{"key":"3044_CR12","unstructured":"Mps. https:\/\/docs.nvidia.com\/deploy\/mps\/index.html"},{"key":"3044_CR13","doi-asserted-by":"crossref","unstructured":"Chang, C.-C., Yang, S.-R., Yeh, E.-H., Lin, P., Jeng, J.-Y.: A kubernetes-based monitoring platform for dynamic cloud resource provisioning. In: GLOBECOM 2017-2017 IEEE Global Communications Conference, pp. 1\u20136. IEEE (2017)","DOI":"10.1109\/GLOCOM.2017.8254046"},{"key":"3044_CR14","doi-asserted-by":"crossref","unstructured":"Gu, J., Song, S., Li, Y., Luo, H., 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), pp. 469\u2013476. IEEE (2018)","DOI":"10.1109\/BDCloud.2018.00077"},{"key":"3044_CR15","doi-asserted-by":"crossref","unstructured":"Song, S., Deng, L., Gong, J., Luo, H.: Gaia scheduler: A kubernetes-based scheduler framework. 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), pp.\u00a0252\u2013259. IEEE (2018)","DOI":"10.1109\/BDCloud.2018.00048"},{"issue":"12","key":"3044_CR16","doi-asserted-by":"publisher","first-page":"3472","DOI":"10.1109\/TPDS.2017.2717908","volume":"28","author":"C-H Hong","year":"2017","unstructured":"Hong, C.-H., Spence, I., Nikolopoulos, D.S.: Fairgv: fair and fast gpu virtualization. IEEE Trans. Parallel Distrib. Syst. 28(12), 3472\u20133485 (2017)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"3044_CR17","doi-asserted-by":"crossref","unstructured":"Tanasic, I., Gelado, I., Cabezas, J., Ramirez, A., Navarro, N., Valero, M.: Enabling preemptive multiprogramming on gpus. In 2014 ACM\/IEEE 41st International Symposium on Computer Architecture (ISCA), pp. 193\u2013204. IEEE (2014)","DOI":"10.1109\/ISCA.2014.6853208"},{"key":"3044_CR18","doi-asserted-by":"crossref","unstructured":"Ukidave, Y., Kalra, C., Kaeli, D., Mistry, P., Schaa, D.: Runtime support for adaptive spatial partitioning and inter-kernel communication on gpus. In: 2014 IEEE 26th International Symposium on Computer Architecture and High Performance Computing, pp. 168\u2013175. IEEE (2014)","DOI":"10.1109\/SBAC-PAD.2014.43"},{"key":"3044_CR19","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, G., Howie Huang, H., Wang, Z., Zheng, W.: Performance analysis of gpu-based convolutional neural networks. In: 2016 45th International Conference on Parallel Processing (ICPP), pp. 67\u201376. IEEE (2016)","DOI":"10.1109\/ICPP.2016.15"},{"key":"3044_CR20","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et\u00a0al.: Tensorflow: A system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), pp. 265\u2013283 (2016)"},{"key":"3044_CR21","unstructured":"Lammps. https:\/\/lammps.sandia.gov\/"},{"key":"3044_CR22","unstructured":"Qmcpack. https:\/\/qmcpack.org\/"},{"key":"3044_CR23","doi-asserted-by":"crossref","unstructured":"Phull, R., Li, C.-H., Rao, K., Cadambi, H., Chakradhar, S.: Interference-driven resource management for gpu-based heterogeneous clusters. In: Proceedings of the 21st international symposium on High-Performance Parallel and Distributed Computing, pp. 109\u2013120. ACM (2012)","DOI":"10.1145\/2287076.2287091"},{"key":"3044_CR24","unstructured":"Nvidia gpu cloud. https:\/\/ngc.nvidia.com\/"},{"key":"3044_CR25","unstructured":"Dutreilh, X., Kirgizov, S., Melekhova, O., Malenfant, J., Rivierre, N., Truck, I.: Using reinforcement learning for autonomic resource allocation in clouds: towards a fully automated workflow. In: ICAS 2011, The Seventh International Conference on Autonomic and Autonomous Systems, pp. 67\u201374 (2011)"},{"issue":"12","key":"3044_CR26","doi-asserted-by":"publisher","first-page":"1656","DOI":"10.1002\/cpe.2864","volume":"25","author":"E Barrett","year":"2013","unstructured":"Barrett, E., Howley, E., Duggan, J.: Applying reinforcement learning towards automating resource allocation and application scalability in the cloud. Concurr. Comput. Pract. Exp. 25(12), 1656\u20131674 (2013)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"3044_CR27","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"3044_CR28","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602, (2013)"},{"key":"3044_CR29","unstructured":"deeprm. https:\/\/github.com\/hongzimao\/deeprm"},{"key":"3044_CR30","unstructured":"Gromacs. http:\/\/www.gromacs.org\/"},{"key":"3044_CR31","unstructured":"Hoomd. http:\/\/glotzerlab.engin.umich.edu\/hoomd-blue\/"},{"key":"3044_CR32","unstructured":"Alibaba fake gpu. https:\/\/github.com\/AliyunContainerService\/gpushare-scheduler-extender"},{"key":"3044_CR33","unstructured":"Nvidia docker container. https:\/\/github.com\/NVIDIA\/nvidia-docker"},{"key":"3044_CR34","doi-asserted-by":"crossref","unstructured":"Grandl, R., Ananthanarayanan, G., Kandula, S., Rao, S., Akella, A.: Multi-resource packing for cluster schedulers. In: ACM SIGCOMM Computer Communication Review, vol.\u00a044, pp. 455\u2013466. ACM (2014)","DOI":"10.1145\/2740070.2626334"},{"key":"3044_CR35","doi-asserted-by":"crossref","unstructured":"Diab, K.M., Mustafa Rafique, M., Hefeeda, M.: Dynamic sharing of gpus in cloud systems. In: 2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum, pp. 947\u2013954. IEEE (2013)","DOI":"10.1109\/IPDPSW.2013.102"},{"key":"3044_CR36","unstructured":"Lawall, Levin\u00a0S.: J. Building stable kernel trees with machine learning"},{"key":"3044_CR37","unstructured":"2019 usenix: Conference on operational machine learning. https:\/\/www.usenix.org\/conference\/opml19"},{"key":"3044_CR38","doi-asserted-by":"crossref","unstructured":"Rossi, F., Nardelli, M., Cardellini, V.: Horizontal and vertical scaling of container-based applications using reinforcement learning. In: 2019 IEEE 12th International Conference on Cloud Computing (CLOUD), pp. 329\u2013338. IEEE (2019)","DOI":"10.1109\/CLOUD.2019.00061"},{"key":"3044_CR39","doi-asserted-by":"crossref","unstructured":"Mao, H., Alizadeh, M., Menache, I., Kandula, S.: Resource management with deep reinforcement learning. In: Proceedings of the 15th ACM Workshop on Hot Topics in Networks, pp. 50\u201356. ACM (2016)","DOI":"10.1145\/3005745.3005750"},{"key":"3044_CR40","doi-asserted-by":"crossref","unstructured":"Bao, Y., Peng, Y., Wu, C.: Deep learning-based job placement in distributed machine learning clusters. In: IEEE INFOCOM 2019-IEEE Conference on Computer Communications, pp. 505\u2013513. IEEE (2019)","DOI":"10.1109\/INFOCOM.2019.8737460"},{"key":"3044_CR41","unstructured":"Xu, X., Zhang, N., Cui, M., He, M., Surana, R.: Characterization and prediction of performance interference on mediated passthrough gpus for interference-aware scheduler. In: 11th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 19), (2019)"},{"key":"3044_CR42","doi-asserted-by":"crossref","unstructured":"Ukidave, Y., Li, X., Kaeli, D.: Mystic: Predictive scheduling for gpu based cloud servers using machine learning. In: 2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 353\u2013362. IEEE (2016)","DOI":"10.1109\/IPDPS.2016.73"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-03044-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-019-03044-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-03044-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,8]],"date-time":"2021-01-08T01:56:30Z","timestamp":1610070990000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-019-03044-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,9]]},"references-count":42,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,9]]}},"alternative-id":["3044"],"URL":"https:\/\/doi.org\/10.1007\/s10586-019-03044-7","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"type":"print","value":"1386-7857"},{"type":"electronic","value":"1573-7543"}],"subject":[],"published":{"date-parts":[[2020,1,9]]},"assertion":[{"value":"25 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 December 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 December 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 January 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}