{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T06:29:26Z","timestamp":1759991366245,"version":"3.37.3"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["24K02932"],"award-info":[{"award-number":["24K02932"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["23828673"],"award-info":[{"award-number":["23828673"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ROIS NII Open Collaborative Research","award":["24S0601"],"award-info":[{"award-number":["24S0601"]}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2021B0101400003"],"award-info":[{"award-number":["2021B0101400003"]}]},{"name":"Hong Kong RGC Research Impact Fund","award":["R5060-19"],"award-info":[{"award-number":["R5060-19"]}]},{"name":"General Research Fund","award":["152221\/19E","152203\/20E","152244\/21E"],"award-info":[{"award-number":["152221\/19E","152203\/20E","152244\/21E"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872310"],"award-info":[{"award-number":["61872310"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010877","name":"Shenzhen Science and Technology Innovation Commission","doi-asserted-by":"publisher","award":["JCYJ20200109142008673"],"award-info":[{"award-number":["JCYJ20200109142008673"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cloud Comput."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tcc.2024.3414440","type":"journal-article","created":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T17:37:11Z","timestamp":1718386631000},"page":"1011-1025","source":"Crossref","is-referenced-by-count":1,"title":["Non-Clairvoyant Scheduling of Distributed Machine Learning With Inter-Job and Intra-Job Parallelism on Heterogeneous GPUs"],"prefix":"10.1109","volume":"12","author":[{"given":"Fahao","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4981-0496","authenticated-orcid":false,"given":"Peng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6853-5878","authenticated-orcid":false,"given":"Celimuge","family":"Wu","sequence":"additional","affiliation":[{"name":"Meta-Networking Research Center, University of Electro-Communications, Chofu, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9831-2202","authenticated-orcid":false,"given":"Song","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref2","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Des. Implementation","author":"Xiao"},{"key":"ref3","first-page":"1","article-title":"Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning","volume-title":"Proc. 15th USENIX Symp. Operating Syst. Des. Implementation","author":"Qiao"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3397166.3409128"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387547"},{"key":"ref7","first-page":"481","article-title":"Heterogeneity-aware cluster scheduling policies for deep learning workloads","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation","author":"Narayanan"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531462"},{"key":"ref9","article-title":"Automl."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218676"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3127490"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486978"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544224"},{"key":"ref15","first-page":"289","article-title":"Themis: Fair and efficient GPU cluster scheduling","volume-title":"Proc. 17th USENIX Symp. Networked Syst. Des. Implementation","author":"Mahajan"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2007.06.028"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787480"},{"key":"ref18","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","volume-title":"Proc. 16th USENIX Symp. Networked Syst. Des. Implementation","author":"Gu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref20","first-page":"533","article-title":"Antman: Dynamic scaling on GPU clusters for deep learning","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation","author":"Xiao"},{"year":"2021","key":"ref21","article-title":"Apache hadoop"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2307\/2273574"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/781027.781055"},{"key":"ref24","first-page":"455","article-title":"$\\lbrace${Information-Agnostic$\\rbrace$} flow scheduling for commodity data centers","volume-title":"Proc. 12th USENIX Symp. Networked Syst. Des. Implementation","author":"Bai"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626315"},{"year":"2019","key":"ref26","article-title":"Google cluster traces"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404415"},{"key":"ref28","first-page":"945","article-title":"$\\lbrace${MLaaS $\\rbrace$} in the wild: Workload analysis and scheduling in $\\lbrace${ Large-Scale $\\rbrace$} heterogeneous $\\lbrace${ GPU$\\rbrace$} clusters","volume-title":"Proc. 19th USENIX Symp. Networked Syst. Des. Implementation","author":"Weng"},{"key":"ref29","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Deep speech: Scaling up end-to-end speech recognition","year":"2014","author":"Hannun","key":"ref35"},{"key":"ref36","first-page":"1","article-title":"FastGCN: Fast learning with graph convolutional networks via importance sampling","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref37","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref38","first-page":"499","article-title":"PipeSwitch: Fast pipelined context switching for deep learning applications","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation","author":"Bai"},{"issue":"10\/10","key":"ref39","article-title":"Spark: Cluster computing with working sets","volume":"10","author":"Zaharia","year":"2010","journal-title":"USENIX HotCloud"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"article-title":"Horovod: Fast and easy distributed deep learning in tensorflow","year":"2018","author":"Sergeev","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2015.2472014"},{"key":"ref43","first-page":"579","article-title":"Looking beyond $\\lbrace${GPUs $\\rbrace$} for $\\lbrace${ DNN$\\rbrace$} scheduling on $\\lbrace${Multi-Tenant$\\rbrace$} clusters","volume-title":"Proc. 16th USENIX Symp. Operating Syst. Des. Implementation","author":"Mohan"}],"container-title":["IEEE Transactions on Cloud Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6245519\/10780435\/10557720.pdf?arnumber=10557720","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T02:01:38Z","timestamp":1733882498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10557720\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":43,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcc.2024.3414440","relation":{},"ISSN":["2168-7161","2372-0018"],"issn-type":[{"type":"electronic","value":"2168-7161"},{"type":"electronic","value":"2372-0018"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}