{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T16:08:16Z","timestamp":1762272496520,"version":"3.37.3"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,1,2]],"date-time":"2020-01-02T00:00:00Z","timestamp":1577923200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,2]],"date-time":"2020-01-02T00:00:00Z","timestamp":1577923200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100010904","name":"Major International Joint Research Programme","doi-asserted-by":"publisher","award":["61720106007"],"award-info":[{"award-number":["61720106007"]}],"id":[{"id":"10.13039\/501100010904","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2020,12]]},"DOI":"10.1007\/s10586-019-03037-6","type":"journal-article","created":{"date-parts":[[2020,1,2]],"date-time":"2020-01-02T19:04:30Z","timestamp":1577991870000},"page":"2689-2702","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Interference-aware parallelization for deep learning workload in GPU cluster"],"prefix":"10.1007","volume":"23","author":[{"given":"Xin","family":"Geng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9131-3517","authenticated-orcid":false,"given":"Haitao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huadong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,1,2]]},"reference":[{"key":"3037_CR1","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 1097\u20131105 (2012)"},{"key":"3037_CR2","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"3037_CR3","doi-asserted-by":"crossref","unstructured":"He, K.M., Zhang, X.Y., Ren, S.Q., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"6","key":"3037_CR4","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.R., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82\u201397 (2012)","journal-title":"IEEE Signal Process. Mag."},{"key":"3037_CR5","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A., Hinton, G.: Speech recognition with deep recurrent neural networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6645\u20136649 (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"3037_CR6","unstructured":"Hannun, A., Case, C., Casper, J., Catanzaro, B., Diamos, G., et\u00a0al.: Deep speech: scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014)"},{"key":"3037_CR7","unstructured":"Boag, S., Dube, P., Herta, B., Hummer, W., Ishakian, V., et al.: Scalable multi-framework multi-tenant lifecycle management of deep learning training jobs. In: Workshop on ML Systems, NIPS (2017)"},{"key":"3037_CR8","unstructured":"Jeon, M., Venkataraman, S., Qian, J.J., Phanishayee, A., Xiao, W.C., et\u00a0al.: Multi-tenant GPU clusters for deep learning workloads: analysis and implications. Technical report, MSR-TR-2018 (2018)"},{"key":"3037_CR9","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1109\/MCC.2014.51","volume":"3","author":"D Bernstein","year":"2014","unstructured":"Bernstein, D.: Containers and cloud: from LXC to Docker to Kubernetes. IEEE Cloud Comput. 3, 81\u201384 (2014)","journal-title":"IEEE Cloud Comput."},{"key":"3037_CR10","doi-asserted-by":"crossref","unstructured":"Vavilapalli, V.K., Murthy, A.C., Douglas, C., Agarwal, S., Konar, M., et\u00a0al.: Apache Hadoop Yarn: yet another resource negotiator. In: Proceedings of the 4th ACM Symposium on Cloud Computing (SOCC) (2013)","DOI":"10.1145\/2523616.2523633"},{"key":"3037_CR11","doi-asserted-by":"crossref","unstructured":"Amaral, M., Polo, J., Carrera, D., Seelam, S., Steinder, M.: Topology-aware GPU scheduling for learning workloads in cloud environments. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC) (2017)","DOI":"10.1145\/3126908.3126933"},{"key":"3037_CR12","unstructured":"Xiao, W.C., Bhardwaj, R., Ramjee, R., Sivathanu, M., Kwatra, N., et\u00a0al.: Gandiva: introspective cluster scheduling for deep learning. In: 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI), pp. 595\u2013610 (2018)"},{"issue":"1","key":"3037_CR13","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","volume":"38","author":"R Girshick","year":"2016","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 142\u2013158 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3037_CR14","unstructured":"Ng, J.Y.H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., et\u00a0al.: Beyond short snippets: deep networks for video classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4694\u20134702 (2015)"},{"key":"3037_CR15","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., \u010cernock\u1ef3, J., Khudanpur, S.: Recurrent neural network based language model. In: Eleventh Annual Conference of the International Speech Communication Association (2010)","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"3037_CR16","unstructured":"Jia, X., Song, S., Wei, H., Wang, Y., Chu, X.: Highly scalable deep learning training system with mixed-precision: training imagenet in four minutes (2018)"},{"key":"3037_CR17","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/MC.2009.263","volume":"8","author":"T Koren","year":"2009","unstructured":"Koren, T., Bell, R., Volinsky, C.: Matrix factorization techniques for recommender systems. Computer 8, 30\u201337 (2009)","journal-title":"Computer"},{"key":"3037_CR18","doi-asserted-by":"crossref","unstructured":"Li, S., Kawale, J., Fu, Y.: Deep collaborative filtering via marginalized denoising auto-encoder. In: ACM International Conference on Information and Knowledge Management (CIKM), pp. 811\u2013820 (2015)","DOI":"10.1145\/2806416.2806527"},{"key":"3037_CR19","doi-asserted-by":"crossref","unstructured":"He, X.N., Liao, L.Z., Zhang, H.W., Nie, L.Q., Hu, X., et\u00a0al.: Neural collaborative filtering. In: International Conference on World Wide Web, pp. 173\u2013182 (2017)","DOI":"10.1145\/3038912.3052569"},{"key":"3037_CR20","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/978-3-642-35289-8_25","volume-title":"Neural Networks: Tricks of the Trade","author":"L Bottou","year":"2012","unstructured":"Bottou, L.: Stochastic gradient descent tricks. Neural Networks: Tricks of the Trade, pp. 421\u2013436. Springer, Berlin (2012)"},{"key":"3037_CR21","unstructured":"Erhan, D., Manzagol, P.A., Bengio, Y., Bengio, S., Vincent, P.: The difficulty of training deep architectures and the effect of unsupervised pre-training. In: Artificial Intelligence and Statistics, pp. 153\u2013160 (2009)"},{"issue":"2","key":"3037_CR22","first-page":"625","volume":"11","author":"D Erhan","year":"2010","unstructured":"Erhan, D., Bengio, Y., Courville, A., Manzagol, P.A., Vincent, P., et al.: Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res. 11(2), 625\u2013660 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"3037_CR23","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: International Conference on Learning Representations (ICLR) (2015)"},{"issue":"7","key":"3037_CR24","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(7), 2121\u20132159 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"3037_CR25","unstructured":"Hinton, G., Srivastava, N., Swersky, K.: Neural networks for machine learning lecture 6a overview of mini-batch gradient descent (2012)"},{"key":"3037_CR26","unstructured":"Kennedy, J., Eberhart, R.: Particle swarm optimization. In: IEEE International Conference on Neural Networks, pp. 1942\u20131948 (1995)"},{"key":"3037_CR27","unstructured":"Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent neural network regularization. In: International Conference on Learning Representations (ICLR) (2015)"},{"issue":"8","key":"3037_CR28","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"issue":"11","key":"3037_CR29","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.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"3037_CR30","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., et\u00a0al.: Imagenet: A large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"6","key":"3037_CR31","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","volume":"29","author":"L Deng","year":"2012","unstructured":"Deng, L.: The MNIST database of handwritten digit images for machine learning research. IEEE Signal Process. Mag. 29(6), 141\u2013142 (2012)","journal-title":"IEEE Signal Process. Mag."},{"issue":"2","key":"3037_CR32","first-page":"313","volume":"19","author":"M Marcus","year":"1993","unstructured":"Marcus, M., Santorini, B., Marcinkiewicz, M.A.: Building a large annotated corpus of english: the penn treebank. Comput. Linguist. 19(2), 313\u2013330 (1993)","journal-title":"Comput. Linguist."},{"key":"3037_CR33","unstructured":"Common voice dataset. https:\/\/voice.mozilla.org\/"},{"key":"3037_CR34","doi-asserted-by":"crossref","unstructured":"Mishra, N., Lafferty, J.D., Hoffmann, H.: ESP: A machine learning approach to predicting application interference. In: IEEE International Conference on Autonomic Computing (ICAC), pp. 125\u2013134 (2017)","DOI":"10.1109\/ICAC.2017.29"},{"key":"3037_CR35","unstructured":"Dean, J., Corrado, G., Monga, R., Chen, K., Devin, M., et\u00a0al.: Large scale distributed deep networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 1223\u20131231 (2012)"},{"key":"3037_CR36","doi-asserted-by":"crossref","unstructured":"Teerapittayanon, S., McDanel, B., Kung, H.: Distributed deep neural networks over the cloud, the edge and end devices. In: IEEE International Conference on Distributed Computing Systems (ICDCS), pp. 328\u2013339 (2017)","DOI":"10.1109\/ICDCS.2017.226"},{"key":"3037_CR37","doi-asserted-by":"crossref","unstructured":"Cui, H.G., Zhang, H., Ganger, G.R., Gibbons, P.B., Xing, E.P.: GeePS: Scalable deep learning on distributed GPUs with a GPU-specialized parameter server. In: Proceedings of the Eleventh European Conference on Computer Systems (2016)","DOI":"10.1145\/2901318.2901323"},{"key":"3037_CR38","doi-asserted-by":"crossref","unstructured":"Gupta, S., Zhang, W., Wang, F.: Model accuracy and runtime tradeoff in distributed deep learning: a systematic study. In: IEEE International Conference on Data Mining (ICDM), pp. 171\u2013180 (2016)","DOI":"10.1109\/ICDM.2016.0028"},{"key":"3037_CR39","doi-asserted-by":"crossref","unstructured":"Qiao, W., Li, Y., Wu, Z.H.: Dltap: A network-efficient scheduling method for distributed deep learning workload in containerized cluster environment. In: ITM Web of Conferences, vol. 12 (2017)","DOI":"10.1051\/itmconf\/20171203030"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-03037-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-019-03037-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-03037-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T01:06:56Z","timestamp":1609463216000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-019-03037-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,2]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["3037"],"URL":"https:\/\/doi.org\/10.1007\/s10586-019-03037-6","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"type":"print","value":"1386-7857"},{"type":"electronic","value":"1573-7543"}],"subject":[],"published":{"date-parts":[[2020,1,2]]},"assertion":[{"value":"27 June 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 October 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 December 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}