{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T21:59:49Z","timestamp":1757627989332,"version":"3.44.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T00:00:00Z","timestamp":1751414400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T00:00:00Z","timestamp":1751414400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,2]]},"DOI":"10.1109\/iwqos65803.2025.11143379","type":"proceedings-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T17:29:52Z","timestamp":1757438992000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["CROP: Efficient and Robust Multi-Job Placement in Deep Learning Clusters"],"prefix":"10.1109","author":[{"given":"Peng","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China"}]},{"given":"Gongming","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China"}]},{"given":"Jing","family":"Wen","sequence":"additional","affiliation":[{"name":"Guangxi Zhuang Autonomous Region Information Center,Guangxi Key Laboratory of Digital Infrastructure"}]},{"given":"Hongli","family":"Xu","sequence":"additional","affiliation":[{"name":"Suzhou Institute for Advanced Research, University of Science and Technology of China"}]},{"given":"Haibo","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Kentucky"}]},{"given":"Wentao","family":"Fan","sequence":"additional","affiliation":[{"name":"China Mobile (Suzhou) Software Technology Co. Ltd."}]},{"given":"Xiaohu","family":"Xu","sequence":"additional","affiliation":[{"name":"China Mobile (Suzhou) Software Technology Co. Ltd."}]},{"given":"Jun","family":"Yao","sequence":"additional","affiliation":[{"name":"China Mobile (Suzhou) Software Technology Co. Ltd."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"140","key":"ref3","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref5","volume-title":"AWS accelerator offerings"},{"key":"ref6","volume-title":"GPU-accelerated Microsoft Azure"},{"key":"ref7","volume-title":"Cloud GPUs on GCP"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796688"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00045"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/DSN48987.2021.00043"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3179405"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3464994.3464996"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629583"},{"key":"ref15","first-page":"515","article-title":"HiveD: Sharing a GPU cluster for deep learning with guarantees","volume-title":"Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Zhao","year":"2020"},{"key":"ref16","article-title":"Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning","volume-title":"Proceedings of the 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Qiao","year":"2021"},{"key":"ref17","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","volume-title":"Proceedings of the 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Gu","year":"2019"},{"key":"ref18","article-title":"Synergy: Resource sensitive DNN scheduling in multi-tenant clusters","author":"Mohan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2013.23"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539700382820"},{"issue":"2","key":"ref23","first-page":"159","article-title":"The Gurobi optimizer","volume":"41","author":"Bixby","year":"2007","journal-title":"Transportation Research Part B"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139177801.004"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/0201010"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1287\/moor.3.3.177"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796938"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3369583.3392679"},{"issue":"4","key":"ref29","first-page":"1","volume":"5","author":"Krizhevsky","year":"2010","journal-title":"CIFAR-10 (Canadian Institute for Advanced Research)"},{"key":"ref30","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Karen","year":"2014","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Index of algorithms provided by Gloo and their semantics"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ColComCon.2014.6860404"},{"key":"ref33","volume-title":"Elasticflow traces"},{"key":"ref34","volume-title":"Pollux traces"}],"event":{"name":"2025 IEEE\/ACM International Symposium on Quality of Service (IWQoS)","location":"Gold Coast, Australia","start":{"date-parts":[[2025,7,2]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE\/ACM 33rd International Symposium on Quality of Service (IWQoS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11143240\/11143247\/11143379.pdf?arnumber=11143379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T05:22:50Z","timestamp":1757481770000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11143379\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,2]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iwqos65803.2025.11143379","relation":{},"subject":[],"published":{"date-parts":[[2025,7,2]]}}}