{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T16:16:40Z","timestamp":1774541800021,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Provincial Key Research and Development Program of Shandong","award":["2021CXGC010101"],"award-info":[{"award-number":["2021CXGC010101"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972386"],"award-info":[{"award-number":["61972386"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2023,8,1]]},"DOI":"10.1109\/tc.2023.3242200","type":"journal-article","created":{"date-parts":[[2023,2,3]],"date-time":"2023-02-03T18:57:24Z","timestamp":1675450644000},"page":"2224-2236","source":"Crossref","is-referenced-by-count":15,"title":["Hydra: Deadline-Aware and Efficiency-Oriented Scheduling for Deep Learning Jobs on Heterogeneous GPUs"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0699-394X","authenticated-orcid":false,"given":"Zichao","family":"Yang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7903-5879","authenticated-orcid":false,"given":"Heng","family":"Wu","sequence":"additional","affiliation":[{"name":"Chongqing School, University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Yuanjia","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Yuewen","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Hua","family":"Zhong","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0237-5100","authenticated-orcid":false,"given":"Wenbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISPDC52870.2021.9521640"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901355"},{"key":"ref34","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/321738.321743"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/FiCloud49777.2021.00063"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-010-2824-y"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286238"},{"key":"ref31","first-page":"533","article-title":"On the diversity of cluster workloads and its impact on research results","author":"amvrosiadis","year":"2018","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref30","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2931558"},{"key":"ref33","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","author":"xiao","year":"2018","journal-title":"Proc 13th USENIX Symp Operating Syst Des Implementation"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404415"},{"key":"ref32","first-page":"481","article-title":"{Heterogeneity-aware} cluster scheduling policies for deep learning workloads","author":"narayanan","year":"2020","journal-title":"Proc 14th USENIX Symp Operating Syst Des Implementation"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190515"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3357223.3362719"},{"key":"ref19","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015"},{"key":"ref18","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref24","article-title":"Alibaba cluster trace program","year":"2020"},{"key":"ref23","author":"burns","year":"2019","journal-title":"Kubernetes Up and Running Dive Into the Future of Infrastructure"},{"key":"ref45","first-page":"503","article-title":"Habitat: A Runtime-Based Computational Performance Predictor for Deep Neural Network Training","author":"yu","year":"2021","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref25","first-page":"1","article-title":"Branch and bound algorithms-principles and examples","author":"clausen","year":"1999","journal-title":"Dept Comput Sci Univ of Copenhagen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476223"},{"key":"ref42","first-page":"117","article-title":"Morpheus: Towards automated {SLOs} for enterprise clusters","author":"jyothi","year":"2016","journal-title":"Proc 12th USENIX Symp Operating Syst Des Implementation"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.262"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref44","article-title":"Runtime performance prediction for deep learning models with graph neural network","author":"gao","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737460"},{"key":"ref43","first-page":"363","article-title":"Ernest: Efficient performance prediction for Large-Scale advanced analytics","author":"venkataraman","year":"2016","journal-title":"Proc 13th USENIX Symp Netw Syst Des Implementation"},{"key":"ref28","year":"2022"},{"key":"ref27","year":"2022"},{"key":"ref29","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486978"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387547"},{"key":"ref9","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":"ref4","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15353\/vsnl.v3i1.171"},{"key":"ref6","first-page":"945","article-title":"{MLaaS} in the wild: Workload analysis and scheduling in {Large-scale} heterogeneous {GPU} clusters","author":"weng","year":"2022","journal-title":"Proc 19th USENIX Symp Netw Syst Des Implementation"},{"key":"ref5","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2465351.2465387"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/10177816\/10036352.pdf?arnumber=10036352","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T17:29:48Z","timestamp":1690824588000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10036352\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,1]]},"references-count":45,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tc.2023.3242200","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,1]]}}}