{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T01:21:39Z","timestamp":1743124899438,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030050535"},{"type":"electronic","value":"9783030050542"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","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":[[2018]]},"DOI":"10.1007\/978-3-030-05054-2_46","type":"book-chapter","created":{"date-parts":[[2018,12,7]],"date-time":"2018-12-07T00:33:21Z","timestamp":1544142801000},"page":"611-629","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["GAI: A Centralized Tree-Based Scheduler for Machine Learning Workload in Large Shared Clusters"],"prefix":"10.1007","author":[{"given":"Ce","family":"Gao","sequence":"first","affiliation":[]},{"given":"Rui","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Hongming","family":"Cai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,12,7]]},"reference":[{"key":"46_CR1","unstructured":"Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation, vol. 16, pp. 265\u2013283 (2016)"},{"issue":"5","key":"46_CR2","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.: Borg, omega, and kubernetes. Commun. ACM 59(5), 50\u201357 (2016)","journal-title":"Commun. ACM"},{"key":"46_CR3","unstructured":"Chen, T., et al.: MXNet: a flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274 (2015)"},{"key":"46_CR4","unstructured":"Delgado, P., Dinu, F., Kermarrec, A.M., Zwaenepoel, W.: Hawk: hybrid datacenter scheduling. In: Proceedings of the 2015 USENIX Annual Technical Conference, No. EPFL-CONF-208856, pp. 499\u2013510. USENIX Association (2015)"},{"key":"46_CR5","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1145\/2499368.2451125","volume":"48","author":"C Delimitrou","year":"2013","unstructured":"Delimitrou, C., Kozyrakis, C.: Paragon: QoS-aware scheduling for heterogeneous datacenters. ACM SIGPLAN Not. 48, 77\u201388 (2013)","journal-title":"ACM SIGPLAN Not."},{"key":"46_CR6","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1145\/2644865.2541941","volume":"49","author":"C Delimitrou","year":"2014","unstructured":"Delimitrou, C., Kozyrakis, C.: Quasar: resource-efficient and QoS-aware cluster management. ACM SIGPLAN Not. 49, 127\u2013144 (2014)","journal-title":"ACM SIGPLAN Not."},{"key":"46_CR7","unstructured":"Gog, I., Schwarzkopf, M., Gleave, A., Watson, R.N., Hand, S.: Firmament: fast, centralized cluster scheduling at scale. In: 12th USENIX Symposium on Operating Systems Design and Implementation. USENIX (2016)"},{"key":"46_CR8","doi-asserted-by":"crossref","unstructured":"Hazelwood, K., et al.: Applied machine learning at Facebook: a datacenter infrastructure perspective. In: 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 620\u2013629. IEEE (2018)","DOI":"10.1109\/HPCA.2018.00059"},{"key":"46_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"46_CR10","unstructured":"Hindman, B., et al.: Mesos: a platform for fine-grained resource sharing in the data center. In: 8th USENIX Symposium on Networked Systems Design and Implementation, vol. 11, p. 22 (2011)"},{"key":"46_CR11","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 675\u2013678. ACM (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"46_CR12","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1093\/nsr\/nwx018","volume":"5","author":"J Jiang","year":"2017","unstructured":"Jiang, J., Yu, L., Jiang, J., Liu, Y., Cui, B.: Angel: a new large-scale machine learning system. Natl. Sci. Rev. 5, 216\u2013236 (2017). https:\/\/doi.org\/10.1093\/nsr\/nwx018","journal-title":"Natl. Sci. Rev."},{"key":"46_CR13","doi-asserted-by":"crossref","unstructured":"Jin, J., Luo, J., Song, A., Dong, F., Xiong, R.: Bar: an efficient data locality driven task scheduling algorithm for cloud computing. In: Proceedings of the 2011 11th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing, pp. 295\u2013304. IEEE Computer Society (2011)","DOI":"10.1109\/CCGrid.2011.55"},{"key":"46_CR14","unstructured":"Karanasos, K., et al.: Mercury: hybrid centralized and distributed scheduling in large shared clusters. In: USENIX Annual Technical Conference, pp. 485\u2013497 (2015)"},{"issue":"11","key":"46_CR15","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":"46_CR16","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.jpdc.2017.11.013","volume":"113","author":"D Lee","year":"2018","unstructured":"Lee, D., Mehta, N., Shearer, A., Kastner, R.: A hardware accelerated system for high throughput cellular image analysis. J. Parallel Distrib. Comput. 113, 167\u2013178 (2018)","journal-title":"J. Parallel Distrib. Comput."},{"key":"46_CR17","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Scaling distributed machine learning with the parameter server. In: 11th USENIX Symposium on Operating Systems Design and Implementation, vol. 1, p. 3 (2014)","DOI":"10.1145\/2640087.2644155"},{"key":"46_CR18","doi-asserted-by":"crossref","unstructured":"Lu, C., Ye, K., Xu, G., Xu, C.Z., Bai, T.: Imbalance in the cloud: an analysis on Alibaba cluster trace. In: 2017 IEEE International Conference on Big Data (Big Data), pp. 2884\u20132892. IEEE (2017)","DOI":"10.1109\/BigData.2017.8258257"},{"key":"46_CR19","doi-asserted-by":"crossref","unstructured":"Ousterhout, K., Wendell, P., Zaharia, M., Stoica, I.: Sparrow: distributed, low latency scheduling. In: Proceedings of the Twenty-Fourth ACM Symposium on Operating Systems Principles, pp. 69\u201384. ACM (2013)","DOI":"10.1145\/2517349.2522716"},{"key":"46_CR20","doi-asserted-by":"crossref","unstructured":"Schwarzkopf, M., Konwinski, A., Abd-El-Malek, M., Wilkes, J.: Omega: flexible, scalable schedulers for large compute clusters. In: Proceedings of the 8th ACM European Conference on Computer Systems, pp. 351\u2013364. ACM (2013)","DOI":"10.1145\/2465351.2465386"},{"key":"46_CR21","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"46_CR22","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"46_CR23","doi-asserted-by":"crossref","unstructured":"Vavilapalli, V.K., et al.: Apache Hadoop YARN: yet another resource negotiator. In: Proceedings of the 4th Annual Symposium on Cloud Computing, p. 5. ACM (2013)","DOI":"10.1145\/2523616.2523633"},{"key":"46_CR24","doi-asserted-by":"crossref","unstructured":"Verma, A., Pedrosa, L., Korupolu, M., Oppenheimer, D., Tune, E., Wilkes, J.: Large-scale cluster management at Google with borg. In: Proceedings of the Tenth European Conference on Computer Systems, p. 18. ACM (2015)","DOI":"10.1145\/2741948.2741964"},{"key":"46_CR25","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1109\/TNSM.2017.2777885","volume":"15","author":"Y Xia","year":"2017","unstructured":"Xia, Y., Ren, R., Cai, H., Vasilakos, A.V., Lv, Z.: Daphne: a flexible and hybrid scheduling framework in multi-tenant clusters. IEEE Trans. Netw. Serv. Manag. 15, 330\u2013343 (2017)","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"issue":"1","key":"46_CR26","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TCC.2014.2306427","volume":"2","author":"Q Zhang","year":"2014","unstructured":"Zhang, Q., Zhani, M.F., Boutaba, R., Hellerstein, J.L.: Dynamic heterogeneity-aware resource provisioning in the cloud. IEEE Trans. Cloud Comput. 2(1), 14\u201328 (2014)","journal-title":"IEEE Trans. Cloud Comput."}],"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\/978-3-030-05054-2_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T22:22:23Z","timestamp":1694470943000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-05054-2_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030050535","9783030050542"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05054-2_46","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"7 December 2018","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":"Guangzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 November 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/nsclab.org\/ica3pp2018\/authors.html","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"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"407","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"141","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"50","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"35% - 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"}},{"value":"2.3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"7.3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}