{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T21:58:51Z","timestamp":1768514331918,"version":"3.49.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032001"],"award-info":[{"award-number":["62032001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672053"],"award-info":[{"award-number":["61672053"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1611461"],"award-info":[{"award-number":["U1611461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032008"],"award-info":[{"award-number":["62032008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"RIE2020 Industry Alignment Fund - Industry Collaboration Projects"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2022,11,1]]},"DOI":"10.1109\/tpds.2021.3136245","type":"journal-article","created":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T20:27:17Z","timestamp":1639772837000},"page":"2781-2793","source":"Crossref","is-referenced-by-count":20,"title":["ASTRAEA: A Fair Deep Learning Scheduler for Multi-Tenant GPU Clusters"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4568-0244","authenticated-orcid":false,"given":"Zhisheng","family":"Ye","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}]},{"given":"Peng","family":"Sun","sequence":"additional","affiliation":[{"name":"SenseTime Research, Beijing, China"}]},{"given":"Wei","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-6650","authenticated-orcid":false,"given":"Tianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}]},{"given":"Xiaolin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}]},{"given":"Shengen","family":"Yan","sequence":"additional","affiliation":[{"name":"SenseTime Research, Beijing, China"}]},{"given":"Yingwei","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1012888.1005704"},{"key":"ref38","first-page":"65","article-title":"Altruistic scheduling in multi-resource clusters","author":"grandl","year":"2016","journal-title":"Proc 12th USENIX Conf Oper Syst Des Implementation"},{"key":"ref33","first-page":"1","article-title":"Centrifuge: Integrated lease management and partitioning for cloud services","author":"adya","year":"2010","journal-title":"Proc 7th USENIX Symp Netw Syst Des Implementation"},{"key":"ref32","article-title":"Method, system and article for advance lease negotiation in DHCP","author":"banerjee","year":"2006"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref30","first-page":"323","article-title":"Dominant resource fairness: Fair allocation of multiple resource types","author":"ghodsi","year":"2011","journal-title":"Proc 8th USENIX Conf Netw Syst Des Implementation"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387547"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901355"},{"key":"ref35","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304067"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483588"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486978"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190515"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476223"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456245"},{"key":"ref21","first-page":"919","article-title":"Retiarii: A deep learning exploratory-training framework","author":"zhang","year":"2020","journal-title":"Proc 14th USENIX Conf Oper Syst Des Implementation"},{"key":"ref24","article-title":"A survey of scheduling in multiprogrammed parallel systems","author":"feitelson","year":"1994"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1755913.1755940"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2465351.2465386"},{"key":"ref50","first-page":"533","article-title":"Antman: Dynamic scaling on GPU clusters for deep learning","author":"xiao","year":"2020","journal-title":"Proc 14th USENIX Conf Operating Syst Des Implementation"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2011.112"},{"key":"ref55","first-page":"481","article-title":"Heterogeneity-aware cluster scheduling policies for deep learning workloads","author":"narayanan","year":"2020","journal-title":"Proc 14th USENIX Conf Oper Syst Des Implementation"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3127490"},{"key":"ref53","first-page":"363","article-title":"Ernest: Efficient performance prediction for large-scale advanced analytics","author":"venkataraman","year":"2016","journal-title":"Proc 13th Usenix Conf Netw Syst Des Implementation"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2014.09.011"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2890784"},{"key":"ref11","first-page":"515","article-title":"Hived: Sharing a GPU cluster for deep learning with guarantees","author":"zhao","year":"2020","journal-title":"Proc 14th USENIX Conf Oper Syst Des Implementation"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2004.1327920"},{"key":"ref12","first-page":"1","article-title":"Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning","author":"qiao","year":"2021","journal-title":"Proc 15th USENIX Symp Oper Syst Des Implementation"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1629575.1629601"},{"key":"ref15","article-title":"Job scheduling with the fair and capacity schedulers","volume":"9","author":"zaharia","year":"2009"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2465351.2465387"},{"key":"ref17","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc 12th USENIX Conf Oper Syst Des Implementation"},{"key":"ref18","first-page":"1","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc 33rd Conf Neural Inf Process Syst"},{"key":"ref19","first-page":"947","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","author":"jeon","year":"2019","journal-title":"Proc USENIX Conf USENIX Annu Tech Conf"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2957478"},{"key":"ref6","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","author":"xiao","year":"2018","journal-title":"Proc 13th USENIX Conf Oper Syst Des Implementation"},{"key":"ref5","first-page":"295","article-title":"Mesos: A platform for fine-grained resource sharing in the data center","author":"hindman","year":"2011","journal-title":"Proc 8th USENIX Conf Netw Syst Des Implementation"},{"key":"ref8","first-page":"289","article-title":"Themis: Fair and efficient GPU cluster scheduling","author":"mahajan","year":"2020","journal-title":"Proc 17th USENIX Symp Netw Syst Des Implementation"},{"key":"ref7","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","author":"gu","year":"2019","journal-title":"Proc 16th USENIX Conf Netw Syst Des Implementation"},{"key":"ref49","first-page":"98","article-title":"Fine-grained GPU sharing primitives for deep learning applications","volume":"2","author":"yu","year":"2020","journal-title":"Proc Mach Learn Syst"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1007\/10968987_3","article-title":"Slurm: Simple Linux utility for resource management","author":"yoo","year":"2003","journal-title":"Proc Workshop Job Scheduling Strategies Parallel Process"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/71.932708"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/956993.956995"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2597652.2597672"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2005.05.003"},{"key":"ref42","first-page":"1","article-title":"Lottery scheduling: Flexible proportional-share resource management","author":"waldspurger","year":"1994","journal-title":"Proc 1st USENIX Conf Operating Syst Des Implementation"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/11605300_12"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/292523.292535"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/223586.223597"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/9782123\/9655467-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9782123\/09655467.pdf?arnumber=9655467","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T00:43:55Z","timestamp":1670373835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9655467\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,1]]},"references-count":55,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2021.3136245","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":[[2022,11,1]]}}}