{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T16:36:55Z","timestamp":1746549415168,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030602383"},{"type":"electronic","value":"9783030602390"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-60239-0_33","type":"book-chapter","created":{"date-parts":[[2020,9,29]],"date-time":"2020-09-29T09:03:14Z","timestamp":1601370194000},"page":"492-508","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Horus: An Interference-Aware Resource Manager for Deep Learning Systems"],"prefix":"10.1007","author":[{"given":"Gingfung","family":"Yeung","sequence":"first","affiliation":[]},{"given":"Damian","family":"Borowiec","sequence":"additional","affiliation":[]},{"given":"Renyu","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Adrian","family":"Friday","sequence":"additional","affiliation":[]},{"given":"Richard","family":"Harper","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Garraghan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"key":"33_CR1","unstructured":"Nvidia Deep Learning Performance Guide, \nhttps:\/\/docs.nvidia.com\/deeplearning\/sdk\/dl-performance-guide\/index.html"},{"key":"33_CR2","unstructured":"Pytorch, \nhttps:\/\/pytorch.org\/"},{"key":"33_CR3","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: ACM SC (2017)","DOI":"10.1145\/3126908.3126933"},{"key":"33_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3241049","volume":"17","author":"A Bhuiyan","year":"2018","unstructured":"Bhuiyan, A., Guo, Z., Saifullah, A., Guan, N., Xiong, H.: Energy-efficient real-time scheduling of DAG tasks. ACM TECS 17, 1\u201325 (2018)","journal-title":"ACM TECS"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Chaudhary, S., et al.: Balancing efficiency and fairness in heterogeneous GPU clusters for deep learning. In: ACM EuroSys 2020 (2020)","DOI":"10.1145\/3342195.3387555"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Q., Yang, H., et al.: Prophet: precise QoS prediction on non-preemptive accelerators to improve utilization in warehouse-scale computers. In: ACM SIGOPS Operating Systems Review (2017)","DOI":"10.1145\/3037697.3037700"},{"key":"33_CR7","unstructured":"Chen, Y., Li, J., Xiao, H., Jin, X., Yan, S., Feng, J.: Dual path networks. In: Advances in Neural Information Processing Systems, pp. 4467\u20134475 (2017)"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Delimitrou, C., Kozyrakis, C.: Paragon: QoS-aware scheduling for heterogeneous datacenters. In: ACM SIGPLAN Notices. ACM (2013)","DOI":"10.1145\/2451116.2451125"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Delimitrou, C., Kozyrakis, C.: Quasar: resource-efficient and QoS-aware cluster management. In: ACM ASPLOS (2014)","DOI":"10.1145\/2541940.2541941"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Gardner, M., Grus, J., Neumann, M., Tafjord, O., et al.: AllenNLP: a deep semantic natural language processing platform (2017)","DOI":"10.18653\/v1\/W18-2501"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM (1999)","DOI":"10.1049\/cp:19991218"},{"key":"33_CR12","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)"},{"key":"33_CR13","unstructured":"Gu, J., Chowdhury, M., Shin, K.G., Zhu, Y., et al.: Tiresias: a $$\\{$$GPU$$\\}$$ cluster manager for distributed deep learning. In: USENIX NSDI (2019)"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Han, D., Kim, J., Kim, J.: Deep pyramidal residual networks. In: IEEE CVPR, pp. 5927\u20135935 (2017)","DOI":"10.1109\/CVPR.2017.668"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"33_CR16","volume-title":"Kubernetes: Up and Running: Dive into the Future of Infrastructure","author":"K Hightower","year":"2017","unstructured":"Hightower, K., Burns, B., Beda, J.: Kubernetes: Up and Running: Dive into the Future of Infrastructure. O\u2019Reilly Media Inc., Sebastopol (2017)"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: IEEE CVPR, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"33_CR18","unstructured":"Iandola, F.N., Han, S., et al.: Squeezenet: alexnet-level accuracy with 50x fewer parameters and $$<$$0.5 mb model size. arXiv preprint \narXiv:1602.07360\n\n (2016)"},{"key":"33_CR19","unstructured":"Jeon, M., et al.: Analysis of large-scale multi-tenant GPU clusters for DNN training workloads. arXiv preprint \narXiv:1901.05758\n\n (2019)"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Kambatla, K., Yarlagadda, V., Goiri, \u00cd., Grama, A.: UBIS: utilization-aware cluster scheduling. In: IEEE IPDPS (2018)","DOI":"10.1109\/IPDPS.2018.00045"},{"key":"33_CR21","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Tech. rep, Citeseer (2009)"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.T., Sun, J.: Shufflenet v2: practical guidelines for efficient CNN architecture design. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Mars, J., Tang, L., et al.: Bubble-up: increasing utilization in modern warehouse scale computers via sensible co-locations. In: IEEE\/ACM MICRO (2011)","DOI":"10.1145\/2155620.2155650"},{"key":"33_CR24","unstructured":"Merity, S., Xiong, C., Bradbury, J., Socher, R.: Pointer sentinel mixture models. arXiv preprint \narXiv:1609.07843\n\n (2016)"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Peng, Y., Bao, Y., Chen, Y., Wu, C., Guo, C.: Optimus: an efficient dynamic resource scheduler for deep learning clusters. In: ACM EuroSys (2018)","DOI":"10.1145\/3190508.3190517"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Phull, R., et al.: Interference-driven resource management for GPU-based heterogeneous clusters. In: Proceedings of HDPC. ACM (2012)","DOI":"10.1145\/2287076.2287091"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: IEEE CVPR, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Schwarzkopf, M., Konwinski, A., Abd-El-Malek, M., Wilkes, J.: Omega: flexible, scalable schedulers for large compute clusters. In: ACM EuroSys (2013)","DOI":"10.1145\/2465351.2465386"},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Shen, H., et al.: Nexus: a GPU cluster engine for accelerating DNN-based video analysis. In: ACM SOSP (2019)","DOI":"10.1145\/3341301.3359658"},{"key":"33_CR30","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR \narXiv:1409.1556\n\n (2014)"},{"key":"33_CR31","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"33_CR32","unstructured":"Tan, M., Le, Q.V.: Efficientnet: rethinking model scaling for convolutional neural networks. arXiv preprint \narXiv:1905.11946\n\n (2019)"},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Tan, M., et al.: MNASNet: platform-aware neural architecture search for mobile. In: IEEE CVPR, pp. 2820\u20132828 (2019)","DOI":"10.1109\/CVPR.2019.00293"},{"key":"33_CR34","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"33_CR35","doi-asserted-by":"crossref","unstructured":"Vavilapalli, V.K., et al.: Apache hadoop yarn: yet another resource negotiator. In: ACM SoCC (2013)","DOI":"10.1145\/2523616.2523633"},{"key":"33_CR36","unstructured":"(WMT19), A.M.T.: Shared task: machine translation of news. \nhttp:\/\/www.statmt.org\/wmt19\/translation-task.html"},{"key":"33_CR37","unstructured":"Xiao, W., et al.: Gandiva: introspective cluster scheduling for deep learning. In: USENIX OSDI (2018)"},{"key":"33_CR38","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: IEEE CVPR (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"33_CR39","unstructured":"Xu, X., et al.: Characterization and prediction of performance interference on mediated passthrough GPUs for interference-aware scheduler. In: HotCloud (2019)"},{"key":"33_CR40","unstructured":"Yeung, G.F., Borowiec, D., Friday, A., Harper, R., Garraghan, P.: Towards GPU utilization prediction for cloud deep learning. In: USENIX HotCloud (2020)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60239-0_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,29]],"date-time":"2020-09-29T09:56:06Z","timestamp":1601373366000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-60239-0_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030602383","9783030602390"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60239-0_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New York, NY","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cloud-conf.net\/ica3pp2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"495","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"142","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"29% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"305","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"10","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}