{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T05:18:34Z","timestamp":1751606314620,"version":"3.37.3"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF-1827674","CCF-1822965"],"award-info":[{"award-number":["NSF-1827674","CCF-1822965"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Microsoft Research Faculty Fellowship","award":["8300751"],"award-info":[{"award-number":["8300751"]}]},{"name":"AWS Machine Learning Research Awards"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cloud Comput."],"published-print":{"date-parts":[[2023,7,1]]},"DOI":"10.1109\/tcc.2022.3206206","type":"journal-article","created":{"date-parts":[[2022,9,13]],"date-time":"2022-09-13T19:42:36Z","timestamp":1663098156000},"page":"2392-2406","source":"Crossref","is-referenced-by-count":4,"title":["Cooperative Job Scheduling and Data Allocation in Data-Intensive Parallel Computing Clusters"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3604-4799","authenticated-orcid":false,"given":"Haoyu","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Virginia, Charlottesville, VA, USA"}]},{"given":"Guoxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Epic Systems, Verona, WI, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7681-6255","authenticated-orcid":false,"given":"Haiying","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Virginia, Charlottesville, VA, USA"}]}],"member":"263","reference":[{"key":"ref13","first-page":"81","article-title":"$\\lbrace${GRAPHENE $\\rbrace$}: Packing and dependency-aware scheduling for data-parallel clusters","author":"grandl","year":"2016","journal-title":"Proc 12th USENIX Symp Oper Syst Des Implementation"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3975(76)90059-1"},{"key":"ref12","first-page":"177","article-title":"Hydra: a federated resource manager for data-center scale analytics","author":"curino","year":"2019","journal-title":"Proc 16th USENIX Symp Netw Syst Des Implementation"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1137\/0109047"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00062"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2011.12"},{"key":"ref14","first-page":"1","article-title":"$\\lbrace${ShuffleWatcher $\\rbrace$}: Shuffle-aware scheduling in multi-tenant $\\lbrace${ MapReduce$\\rbrace$} clusters","author":"ahmad","year":"2014","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1137\/0105003"},{"journal-title":"Information Retrieval","year":"1979","author":"van rijsbergen","key":"ref53"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2012.6195556"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787488"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s004530010013"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2013.6566958"},{"journal-title":"Computers and Intractability A Guide to the Theory of NP-Completeness","year":"1979","author":"garey","key":"ref54"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2018.00015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2016.48"},{"key":"ref19","first-page":"1","article-title":"Natjam: Eviction policies for supporting priorities and deadlines in mapreduce clusters","author":"gupta","year":"2013","journal-title":"Proc 4th Annu Symp Cloud Comput"},{"key":"ref18","first-page":"367","article-title":"Orchestrating the deployment of computations in the cloud with conductor","author":"wieder","year":"2012","journal-title":"Proc 9th USENIX Symp Netw Syst Des Implementation"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1867"},{"key":"ref50","first-page":"234","article-title":"RIA: Automatic resource inference and allocation for MapReduce environments","author":"verma","year":"2011","journal-title":"Proc 8th ACM Int Conf Autonomic Comput"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2018.00074"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1807128.1807162"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2591971.2592007"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1145\/2796314.2745861","article-title":"Distributed proportional fair load balancing in heterogeneous systems","author":"yun","year":"2015","journal-title":"Proc ACM SIGMETRICS Int Conf Meas Model Comput Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2591971.2591998"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2745844.2745869"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1807128.1807164"},{"key":"ref43","first-page":"357","article-title":"Robustness in the Salus Scalable Block Store","author":"wang","year":"2013","journal-title":"Proc 10th USENIX Symp Netw Syst Des Implementation"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3357223.3362710"},{"journal-title":"Apache fair scheduler","year":"2020","key":"ref8"},{"journal-title":"Apache Capacity Scheduler Guide","year":"2020","key":"ref7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1755913.1755940"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2465351.2465386"},{"journal-title":"Apache Hadoop NextGen MapReduce (YARN)","year":"2021","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2010.5496972"},{"journal-title":"Apache Mesos","year":"2020","key":"ref5"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref34","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","author":"gu","year":"2019","journal-title":"Proc 16th USENIX Symp Netw Syst Des Implementation"},{"key":"ref37","first-page":"289","article-title":"Themis: Fair and efficient $\\lbrace${GPU $\\rbrace$} cluster scheduling","author":"mahajan","year":"2020","journal-title":"Proc 17th USENIX Symp Netw Syst Des Implementation"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737460"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486422"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3127490"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref2","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc 12th USENIX Symp Operating Syst Des Implementation"},{"key":"ref39","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","author":"xiao","year":"2018","journal-title":"Proc 13th USENIX Symp Oper Syst Des Implementation"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626334"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E48712.2020.00019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MSN48538.2019.00018"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337864"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267819"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267838"},{"key":"ref20","first-page":"99","article-title":"Jockey: Guaranteed job latency in data parallel clusters","author":"ferguson","year":"2013","journal-title":"Proc 7th ACM Eur Conf Comput Syst"},{"journal-title":"Palmetto Cluster","year":"2020","key":"ref64"},{"key":"ref63","first-page":"1","article-title":"Scale-up versus scale-out for hadoop: Time to rethink?","author":"appuswamy","year":"2013","journal-title":"Proc 4th Annu Symp Cloud Comput"},{"key":"ref22","first-page":"519","article-title":"Hugo: a cluster scheduler that efficiently learns to select complementary data-parallel jobs","author":"thamsen","year":"2019","journal-title":"Proc Eur Conf Parallel Process"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3386367.3432588"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"journal-title":"Microsfot phyilly trace","year":"2021","key":"ref65"},{"key":"ref28","first-page":"99","article-title":"Firmament: Fast, centralized cluster scheduling at scale","author":"gog","year":"2016","journal-title":"Proc 12th USENIX Symp Oper Syst Des Implementation"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901355"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2873373"},{"article-title":"Scaling the Facebook data warehouse to 300 PB","year":"0","author":"vagata","key":"ref60"},{"journal-title":"Apache hadoop file system and its usage in Facebook","year":"2020","key":"ref62"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/1402958.1402967"}],"container-title":["IEEE Transactions on Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6245519\/10241247\/9889160-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6245519\/10241247\/09889160.pdf?arnumber=9889160","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T17:10:09Z","timestamp":1717693809000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9889160\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,1]]},"references-count":67,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcc.2022.3206206","relation":{},"ISSN":["2168-7161","2372-0018"],"issn-type":[{"type":"electronic","value":"2168-7161"},{"type":"electronic","value":"2372-0018"}],"subject":[],"published":{"date-parts":[[2023,7,1]]}}}