{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:47:38Z","timestamp":1783439258576,"version":"3.54.6"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000196","name":"Canada Foundation for Innovation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000196","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007711","name":"British Columbia Knowledge Development Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tpds.2024.3390109","type":"journal-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T17:37:18Z","timestamp":1713375438000},"page":"1029-1043","source":"Crossref","is-referenced-by-count":7,"title":["Sampling-Based Multi-Job Placement for Heterogeneous Deep Learning Clusters"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1114-8030","authenticated-orcid":false,"given":"Kaiyang","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Computer Science, Memorial University of Newfoundland, St. John’s, NL, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3392-7016","authenticated-orcid":false,"given":"Jingrong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6465-591X","authenticated-orcid":false,"given":"Zhiming","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Victoria, Victoria, BC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4893-6847","authenticated-orcid":false,"given":"Jianping","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Victoria, Victoria, BC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/PCCC.2018.8711202"},{"key":"ref3","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref4","first-page":"481","article-title":"Heterogeneity-aware cluster scheduling policies for deep learning workloads","volume-title":"Proc. 14th USENIX Conf. Operating Syst. Des. Implementation","author":"Narayanan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2021.3102593"},{"key":"ref6","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","volume-title":"Proc. 16th USENIX Conf. Netw. Syst. Des. Implementation","author":"Gu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404415"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737460"},{"key":"ref10","first-page":"289","article-title":"THEMIS: Fair and efficient GPU cluster scheduling","volume-title":"Proc. 17th USENIX Conf. Netw. Syst. Des. Implementation","author":"Mahajan"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483588"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.14778\/3636218.3636227"},{"key":"ref13","article-title":"Deep learning workload scheduling in GPU datacenters: Taxonomy, challenges and vision","author":"Gao","year":"2022"},{"issue":"3","key":"ref14","first-page":"416","article-title":"Analysis of variants in round robin algorithms for load balancing in cloud computing","volume":"4","author":"Samal","year":"2013","journal-title":"Int. J. Comput. Sci. Inf. Technol."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3149.3156"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2987550.2987554"},{"key":"ref17","first-page":"1","article-title":"Adaptive load balancing for parallel GNN training","volume-title":"Proc. MLSys Workshop GNNSys","author":"Su"},{"key":"ref18","first-page":"739","article-title":"TopoOpt: Co-optimizing network topology and parallelization strategy for distributed training jobs","volume-title":"Proc. 20th USENIX Conf. Netw. Syst. Des. Implementation","author":"Wang"},{"key":"ref19","first-page":"1","article-title":"Beyond data and model parallelism for deep neural networks","volume-title":"Proc. Mach. Learn. Syst.","author":"Jia"},{"key":"ref20","first-page":"827","article-title":"Building scalable and flexible cluster managers using declarative programming","volume-title":"Proc. 14th USENIX Conf. Operating Syst. Des. Implementation","author":"Suresh"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511761942"},{"key":"ref22","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Conf. Operating Syst. Des. Implementation","author":"Abadi"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref24","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"Chen","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"ref26","article-title":"Communication-efficient distributed deep learning: A comprehensive survey","author":"Tang","year":"2020"},{"key":"ref30","first-page":"629","article-title":"Gaia: Geo-distributed machine learning approaching LAN speeds","volume-title":"Proc. 14th USENIX Conf. Netw. Syst. Des. Implementation","author":"Hsieh"},{"key":"ref31","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. 26th Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref32","first-page":"693","article-title":"HOGWILD: A lock-free approach to parallelizing stochastic gradient descent","volume-title":"Proc. 24th Int. Conf. Neural Inf. Process. Syst.","author":"Recht"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2644865.2541941"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1080\/00224065.1986.11979014"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-7997-1_44"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511801655"},{"key":"ref37","first-page":"1","article-title":"A quantitative measure of fairness and discrimination for resource allocation in shared computer systems","author":"Jain","year":"1984"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2022.3168662"},{"key":"ref42","first-page":"463","article-title":"A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters","volume-title":"Proc. 14th USENIX Conf. Operating Syst. Des. Implementation","author":"Jiang"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1402958.1402967"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10494199\/10504599.pdf?arnumber=10504599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T17:43:05Z","timestamp":1715794985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10504599\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":37,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2024.3390109","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}