{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:35:21Z","timestamp":1778344521923,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,27]],"date-time":"2019-10-27T00:00:00Z","timestamp":1572134400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1614717"],"award-info":[{"award-number":["CNS-1614717"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,27]]},"DOI":"10.1145\/3341301.3359658","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T13:34:22Z","timestamp":1571664862000},"page":"322-337","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":205,"title":["Nexus"],"prefix":"10.1145","author":[{"given":"Haichen","family":"Shen","sequence":"first","affiliation":[{"name":"Amazon Web Services"}]},{"given":"Lequn","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Yuchen","family":"Jin","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Liangyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Bingyu","family":"Kong","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Matthai","family":"Philipose","sequence":"additional","affiliation":[{"name":"Microsoft Research"}]},{"given":"Arvind","family":"Krishnamurthy","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Ravi","family":"Sundaram","sequence":"additional","affiliation":[{"name":"Northeastern University"}]}],"member":"320","published-online":{"date-parts":[[2019,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"TensorFlow: A System for Large-Scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi , Paul Barham , Jianmin Chen , Zhifeng Chen , Andy Davis , Jeffrey Dean , Matthieu Devin , Sanjay Ghemawat , Geoffrey Irving , Michael Isard , Manjunath Kudlur , Josh Levenberg , Rajat Monga , Sherry Moore , Derek Gordon Murray , Benoit Steiner , Paul A. Tucker , Vijay Vasudevan , Pete Warden , Martin Wicke , Yuan Yu , and Xiaoqiang Zheng . 2016 . TensorFlow: A System for Large-Scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016 , Savannah, GA, USA, November 2--4 , 2016. USENIX Association, 265--283. Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek Gordon Murray, Benoit Steiner, Paul A. Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. TensorFlow: A System for Large-Scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016, Savannah, GA, USA, November 2--4, 2016. USENIX Association, 265--283."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2016.12.009"},{"key":"e_1_3_2_1_3_1","volume-title":"Slicer: Auto-Sharding for Datacenter Applications. In 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016","author":"Adya Atul","year":"2016","unstructured":"Atul Adya , Daniel Myers , Jon Howell , Jeremy Elson , Colin Meek , Vishesh Khemani , Stefan Fulger , Pan Gu , Lakshminath Bhuvanagiri , Jason Hunter , Roberto Peon , Larry Kai , Alexander Shraer , Arif Merchant , and Kfir Lev-Ari . 2016 . Slicer: Auto-Sharding for Datacenter Applications. In 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016 , Savannah, GA, USA, November 2--4 , 2016. USENIX Association, 739--753. Atul Adya, Daniel Myers, Jon Howell, Jeremy Elson, Colin Meek, Vishesh Khemani, Stefan Fulger, Pan Gu, Lakshminath Bhuvanagiri, Jason Hunter, Roberto Peon, Larry Kai, Alexander Shraer, Arif Merchant, and Kfir Lev-Ari. 2016. Slicer: Auto-Sharding for Datacenter Applications. In 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016, Savannah, GA, USA, November 2--4, 2016. USENIX Association, 739--753."},{"key":"e_1_3_2_1_4_1","volume-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"Chen Liang-Chieh","year":"2018","unstructured":"Liang-Chieh Chen , George Papandreou , Iasonas Kokkinos , Kevin Murphy , and Alan L Yuille . 2018 . Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs . IEEE transactions on pattern analysis and machine intelligence 40, 4 (2018), 834--848. Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. 2018. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence 40, 4 (2018), 834--848."},{"key":"e_1_3_2_1_5_1","unstructured":"Clipper contributors. 2019. Clipper v0.4. https:\/\/github.com\/ucbrise\/clipper\/tree\/release-0.4.  Clipper contributors. 2019. Clipper v0.4. https:\/\/github.com\/ucbrise\/clipper\/tree\/release-0.4."},{"key":"e_1_3_2_1_6_1","volume-title":"Clipper: A Low-Latency Online Prediction Serving System. In 14th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2017","author":"Crankshaw Daniel","year":"2017","unstructured":"Daniel Crankshaw , Xin Wang , Giulio Zhou , Michael J. Franklin , Joseph E. Gonzalez , and Ion Stoica . 2017 . Clipper: A Low-Latency Online Prediction Serving System. In 14th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2017 , Boston, MA, USA, March 27--29 , 2017. USENIX Association, 613--627. Daniel Crankshaw, Xin Wang, Giulio Zhou, Michael J. Franklin, Joseph E. Gonzalez, and Ion Stoica. 2017. Clipper: A Low-Latency Online Prediction Serving System. In 14th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2017, Boston, MA, USA, March 27--29, 2017. USENIX Association, 613--627."},{"key":"e_1_3_2_1_7_1","unstructured":"Docker. 2014. Docker Swarm. https:\/\/github.com\/docker\/swarm.  Docker. 2014. Docker Swarm. https:\/\/github.com\/docker\/swarm."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 31th International Conference on Machine Learning, ICML 2014, Beijing, China, 21--26 June 2014 (JMLR Workshop and Conference Proceedings)","volume":"32","author":"Donahue Jeff","year":"2014","unstructured":"Jeff Donahue , Yangqing Jia , Oriol Vinyals , Judy Hoffman , Ning Zhang , Eric Tzeng , and Trevor Darrell . 2014 . DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition . In Proceedings of the 31th International Conference on Machine Learning, ICML 2014, Beijing, China, 21--26 June 2014 (JMLR Workshop and Conference Proceedings) , Vol. 32 . JMLR.org, 647--655. Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, and Trevor Darrell. 2014. DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. In Proceedings of the 31th International Conference on Machine Learning, ICML 2014, Beijing, China, 21--26 June 2014 (JMLR Workshop and Conference Proceedings), Vol. 32. JMLR.org, 647--655."},{"key":"e_1_3_2_1_9_1","unstructured":"Facebook. 2018. Caffe2: A New Lightweight Modular and Scalable Deep Learning Framework. https:\/\/caffe2.ai\/.  Facebook. 2018. Caffe2: A New Lightweight Modular and Scalable Deep Learning Framework. https:\/\/caffe2.ai\/."},{"key":"e_1_3_2_1_10_1","volume-title":"Johnson","author":"Garey Michael R.","year":"1979","unstructured":"Michael R. Garey and David S . Johnson . 1979 . Computers and Intractability: A Guide to the Theory of NP-Completeness. W. H. Freeman & Co. , New York, NY, USA. Michael R. Garey and David S. Johnson. 1979. Computers and Intractability: A Guide to the Theory of NP-Completeness. W. H. Freeman & Co., New York, NY, USA."},{"key":"e_1_3_2_1_11_1","volume-title":"Kubernetes: Production-Grade Container Orchestration. https:\/\/kubernetes.io\/","year":"2014","unstructured":"Google. 2014 . Kubernetes: Production-Grade Container Orchestration. https:\/\/kubernetes.io\/ Google. 2014. Kubernetes: Production-Grade Container Orchestration. https:\/\/kubernetes.io\/"},{"key":"e_1_3_2_1_12_1","unstructured":"Google. 2019. Cloud AutoML Vision. https:\/\/cloud.google.com\/vision\/automl\/docs\/.  Google. 2019. Cloud AutoML Vision. https:\/\/cloud.google.com\/vision\/automl\/docs\/."},{"key":"e_1_3_2_1_13_1","volume-title":"Tiresias: A GPU Cluster Manager for Distributed Deep Learning. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Gu Juncheng","year":"2019","unstructured":"Juncheng Gu , Mosharaf Chowdhury , Kang G Shin , Yibo Zhu , Myeongjae Jeon , Junjie Qian , Hongqiang Liu , and Chuanxiong Guo . 2019 . Tiresias: A GPU Cluster Manager for Distributed Deep Learning. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19) . 485--500. Juncheng Gu, Mosharaf Chowdhury, Kang G Shin, Yibo Zhu, Myeongjae Jeon, Junjie Qian, Hongqiang Liu, and Chuanxiong Guo. 2019. Tiresias: A GPU Cluster Manager for Distributed Deep Learning. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19). 485--500."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2906388.2906396"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 8th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2011","author":"Hindman Benjamin","year":"2011","unstructured":"Benjamin Hindman , Andy Konwinski , Matei Zaharia , Ali Ghodsi , Anthony D. Joseph , Randy H. Katz , Scott Shenker , and Ion Stoica . 2011 . Mesos: A Platform for Fine-Grained Resource Sharing in the Data Center . In Proceedings of the 8th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2011 , Boston, MA, USA, March 30 - April 1, 2011. USENIX Association. Benjamin Hindman, Andy Konwinski, Matei Zaharia, Ali Ghodsi, Anthony D.Joseph, Randy H. Katz, Scott Shenker, and Ion Stoica. 2011. Mesos: A Platform for Fine-Grained Resource Sharing in the Data Center. In Proceedings of the 8th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2011, Boston, MA, USA, March 30 - April 1, 2011. USENIX Association."},{"key":"e_1_3_2_1_17_1","volume-title":"Focus: Querying Large Video Datasets with Low Latency and Low Cost. In 13th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2018","author":"Hsieh Kevin","year":"2018","unstructured":"Kevin Hsieh , Ganesh Ananthanarayanan , Peter Bod\u00edk , Shivaram Venkataraman , Paramvir Bahl , Matthai Philipose , Phillip B. Gibbons , and Onur Mutlu . 2018 . Focus: Querying Large Video Datasets with Low Latency and Low Cost. In 13th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2018 , Carlsbad, CA, USA, October 8--10 , 2018. USENIX Association, 269--286. Kevin Hsieh, Ganesh Ananthanarayanan, Peter Bod\u00edk, Shivaram Venkataraman, Paramvir Bahl, Matthai Philipose, Phillip B. Gibbons, and Onur Mutlu. 2018. Focus: Querying Large Video Datasets with Low Latency and Low Cost. In 13th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2018, Carlsbad, CA, USA, October 8--10, 2018. USENIX Association, 269--286."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_19_1","volume-title":"2018 USENIX Annual Technical Conference (USENIX ATC 18)","author":"Jiang Angela H","year":"2018","unstructured":"Angela H Jiang , Daniel L-K Wong , Christopher Canel , Lilia Tang , Ishan Misra , Michael Kaminsky , Michael A Kozuch , Padmanabhan Pillai , David G Andersen , and Gregory R Ganger . 2018 . Mainstream: Dynamic stem-sharing for multi-tenant video processing . In 2018 USENIX Annual Technical Conference (USENIX ATC 18) . 29--42. Angela H Jiang, Daniel L-K Wong, Christopher Canel, Lilia Tang, Ishan Misra, Michael Kaminsky, Michael A Kozuch, Padmanabhan Pillai, David G Andersen, and Gregory R Ganger. 2018. Mainstream: Dynamic stem-sharing for multi-tenant video processing. In 2018 USENIX Annual Technical Conference (USENIX ATC 18). 29--42."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137664"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71844-4_18"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_23_1","unstructured":"Microsoft. 2018. Virtual Machine Scale Sets. https:\/\/docs.microsoft.com\/en-us\/azure\/virtual-machine-scale-sets\/virtual-machine-scale-sets-overview.  Microsoft. 2018. Virtual Machine Scale Sets. https:\/\/docs.microsoft.com\/en-us\/azure\/virtual-machine-scale-sets\/virtual-machine-scale-sets-overview."},{"key":"e_1_3_2_1_24_1","unstructured":"Microsoft. 2019. Custom Vision. https:\/\/azure.microsoft.com\/en-us\/services\/cognitive-services\/custom-vision-service\/.  Microsoft. 2019. Custom Vision. https:\/\/azure.microsoft.com\/en-us\/services\/cognitive-services\/custom-vision-service\/."},{"key":"e_1_3_2_1_25_1","volume-title":"Tensorflow-serving: Flexible, high-performance ml serving. arXiv preprint arXiv:1712.06139","author":"Olston Christopher","year":"2017","unstructured":"Christopher Olston , Noah Fiedel , Kiril Gorovoy , Jeremiah Harmsen , Li Lao , Fangwei Li , Vinu Rajashekhar , Sukriti Ramesh , and Jordan Soyke . 2017 . Tensorflow-serving: Flexible, high-performance ml serving. arXiv preprint arXiv:1712.06139 (2017). Christopher Olston, Noah Fiedel, Kiril Gorovoy, Jeremiah Harmsen, Li Lao, Fangwei Li, Vinu Rajashekhar, Sukriti Ramesh, and Jordan Soyke. 2017. Tensorflow-serving: Flexible, high-performance ml serving. arXiv preprint arXiv:1712.06139 (2017)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.222"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522716"},{"key":"e_1_3_2_1_28_1","volume-title":"USENIX Annual Technical Conference, General Track. 199--212","author":"Pai Vivek S","year":"1999","unstructured":"Vivek S Pai , Peter Druschel , and Willy Zwaenepoel . 1999 . Flash: An efficient and portable Web server . In USENIX Annual Technical Conference, General Track. 199--212 . Vivek S Pai, Peter Druschel, and Willy Zwaenepoel. 1999. Flash: An efficient and portable Web server. In USENIX Annual Technical Conference, General Track. 199--212."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5244\/C29.41"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"e_1_3_2_1_32_1","unstructured":"Joseph Redmon. 2013--2016. Darknet: Open Source Neural Networks in C. http:\/\/pjreddie.com\/darknet\/.  Joseph Redmon. 2013--2016. Darknet: Open Source Neural Networks in C. http:\/\/pjreddie.com\/darknet\/."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2465351.2465386"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.236"},{"key":"e_1_3_2_1_36_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. In Advances in neural information processing systems. 568--576.  Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. In Advances in neural information processing systems. 568--576."},{"key":"e_1_3_2_1_37_1","unstructured":"Twitch. 2011. Twitch. https:\/\/www.twitch.tv\/.  Twitch. 2011. Twitch. https:\/\/www.twitch.tv\/."},{"key":"e_1_3_2_1_38_1","volume-title":"Gandiva: Introspective Cluster Scheduling for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Xiao Wencong","year":"2018","unstructured":"Wencong Xiao , Romil Bhardwaj , Ramachandran Ramjee , Muthian Sivathanu , Nipun Kwatra , Zhenhua Han , Pratyush Patel , Xuan Peng , Hanyu Zhao , Quanlu Zhang , Fan Yang , and Lidong Zhou . 2018 . Gandiva: Introspective Cluster Scheduling for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18) . USENIX Association, Carlsbad, CA, 595--610. Wencong Xiao, Romil Bhardwaj, Ramachandran Ramjee, Muthian Sivathanu, Nipun Kwatra, Zhenhua Han, Pratyush Patel, Xuan Peng, Hanyu Zhao, Quanlu Zhang, Fan Yang, and Lidong Zhou. 2018. Gandiva: Introspective Cluster Scheduling for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). USENIX Association, Carlsbad, CA, 595--610."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299023"},{"key":"e_1_3_2_1_40_1","unstructured":"Jason Yosinski Jeff Clune Yoshua Bengio and Hod Lipson. 2014. How transferable are features in deep neural networks?. In Advances in neural information processing systems. 3320--3328.  Jason Yosinski Jeff Clune Yoshua Bengio and Hod Lipson. 2014. How transferable are features in deep neural networks?. In Advances in neural information processing systems. 3320--3328."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288897"},{"key":"e_1_3_2_1_42_1","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Zhang Haoyu","year":"2017","unstructured":"Haoyu Zhang , Ganesh Ananthanarayanan , Peter Bodik , Matthai Philipose , Paramvir Bahl , and Michael J Freedman . 2017 . Live video analytics at scale with approximation and delay-tolerance . In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17) . 377--392. Haoyu Zhang, Ganesh Ananthanarayanan, Peter Bodik, Matthai Philipose, Paramvir Bahl, and Michael J Freedman. 2017. Live video analytics at scale with approximation and delay-tolerance. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). 377--392."}],"event":{"name":"SOSP '19: ACM SIGOPS 27th Symposium on Operating Systems Principles","location":"Huntsville Ontario Canada","acronym":"SOSP '19","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems","USENIX Assoc USENIX Assoc"]},"container-title":["Proceedings of the 27th ACM Symposium on Operating Systems Principles"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3341301.3359658","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3341301.3359658","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3341301.3359658","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:12:56Z","timestamp":1750201976000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3341301.3359658"}},"subtitle":["a GPU cluster engine for accelerating DNN-based video analysis"],"short-title":[],"issued":{"date-parts":[[2019,10,27]]},"references-count":42,"alternative-id":["10.1145\/3341301.3359658","10.1145\/3341301"],"URL":"https:\/\/doi.org\/10.1145\/3341301.3359658","relation":{},"subject":[],"published":{"date-parts":[[2019,10,27]]},"assertion":[{"value":"2019-10-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}