{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:47:14Z","timestamp":1773154034229,"version":"3.50.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Research and Development Program of China","award":["2022YFF0902702"],"award-info":[{"award-number":["2022YFF0902702"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61825205"],"award-info":[{"award-number":["61825205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Zhejiang Provence, China","award":["2021C01017"],"award-info":[{"award-number":["2021C01017"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tpds.2023.3293835","type":"journal-article","created":{"date-parts":[[2023,7,11]],"date-time":"2023-07-11T17:28:01Z","timestamp":1689096481000},"page":"2553-2567","source":"Crossref","is-referenced-by-count":13,"title":["DeepBoot: Dynamic Scheduling System for Training and Inference Deep Learning Tasks in GPU Cluster"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7519-2295","authenticated-orcid":false,"given":"Zhenqian","family":"Chen","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1115-5652","authenticated-orcid":false,"given":"Xinkui","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1273-2992","authenticated-orcid":false,"given":"Chen","family":"Zhi","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4703-7348","authenticated-orcid":false,"given":"Jianwei","family":"Yin","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456245"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref15","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":"ref14","article-title":"Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning","author":"qiao","year":"2021","journal-title":"Proc 15th USENIX Symp Operating Syst Des Implementation"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452773"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"ref11","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","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":"ref54","article-title":"A runtime-based computational performance predictor for deep neural network training","author":"yu","year":"2021"},{"key":"ref17","first-page":"397","article-title":"INFaaS: Automated model-less inference serving","author":"romero","year":"2021","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref16","first-page":"613","article-title":"Clipper: A. Low-Latency online prediction serving system","author":"crankshaw","year":"2017","journal-title":"Proc 14th USENIX Symp Networked Syst Des Implementation"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00059"},{"key":"ref18","first-page":"1877","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","first-page":"1","article-title":"Measuring the effects of data parallelism on neural network training","volume":"20","author":"shallue","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref50","article-title":"The CMU arctic speech databases","author":"kominek","year":"2004","journal-title":"Proc 5th ISCA Workshop Speech Synth"},{"key":"ref46","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3064966"},{"key":"ref48","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018"},{"key":"ref47","year":"2022"},{"key":"ref42","year":"2022"},{"key":"ref41","first-page":"203","article-title":"CheckFreq: Frequent, fine-grained DNN checkpointing","author":"mohan","year":"2021","journal-title":"Proc 19th USENIX Conf File Storage Technol"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800220110"},{"key":"ref43","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2890784"},{"key":"ref9","first-page":"721","article-title":"Elastic resource sharing for distributed deep learning","author":"hwang","year":"2021","journal-title":"Proc 18th USENIX Symp Networked Syst Des Implementation"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"ref3","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":"ref6","first-page":"265","article-title":"TensorFlow: A system for Large-Scale machine learning","author":"abadi","year":"0","journal-title":"Proc 12th USENIX Symp Operating Syst Des Implementation"},{"key":"ref5","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796896"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2827872"},{"key":"ref37","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref31","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00018"},{"key":"ref33","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3104242"},{"key":"ref2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref1","first-page":"770","article-title":"Deep residual learning for image recognition","author":"he","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155237"},{"key":"ref38","first-page":"539","article-title":"Microsecond-scale preemption for concurrent GPU-accelerated DNN inferences","author":"han","year":"2022","journal-title":"Proc 16th USENIX Symp Operating Syst Des Implementation"},{"key":"ref24","year":"2022"},{"key":"ref23","article-title":"Aryl: An elastic cluster scheduler for deep learning","author":"li","year":"2022"},{"key":"ref26","first-page":"443","article-title":"Serving DNNs like clockwork: Performance predictability from the bottom up","author":"gujarati","year":"2020","journal-title":"Proc 14th USENIX Symp Operating Syst Des Implementation"},{"key":"ref25","year":"2022"},{"key":"ref20","first-page":"947","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","author":"jeon","year":"0","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476223"},{"key":"ref21","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 Networked Syst Des Implementation"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486978"},{"key":"ref27","first-page":"499","article-title":"PipeSwitch: Fast pipelined context switching for deep learning applications","author":"bai","year":"2020","journal-title":"Proc 14th USENIX Symp Operating Syst Des Implementation"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10180399\/10179169.pdf?arnumber=10179169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T19:14:17Z","timestamp":1694459657000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10179169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":54,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3293835","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":[[2023,9]]}}}