{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T01:22:18Z","timestamp":1776993738181,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T00:00:00Z","timestamp":1701820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2211302"],"award-info":[{"award-number":["2211302"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2211888"],"award-info":[{"award-number":["2211888"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2213636"],"award-info":[{"award-number":["2213636"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2105494"],"award-info":[{"award-number":["2105494"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"US Army contract","award":["W911NF-17-2-0196"],"award-info":[{"award-number":["W911NF-17-2-0196"]}]},{"DOI":"10.13039\/100008536","name":"Amazon Web Services","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008536","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016682","name":"VMware","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016682","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,6]]},"DOI":"10.1145\/3583740.3628435","type":"proceedings-article","created":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T18:35:50Z","timestamp":1723055750000},"page":"53-66","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Energy Time Fairness: Balancing Fair Allocation of Energy and Time for GPU Workloads"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4702-5689","authenticated-orcid":false,"given":"Qianlin","family":"Liang","sequence":"first","affiliation":[{"name":"University of Massachusetts, Amherst, Amherst, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5765-8194","authenticated-orcid":false,"given":"Walid A.","family":"Hanafy","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9304-910X","authenticated-orcid":false,"given":"Noman","family":"Bashir","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1722-4927","authenticated-orcid":false,"given":"David","family":"Irwin","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5435-1901","authenticated-orcid":false,"given":"Prashant","family":"Shenoy","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,7]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2023. Hadoop Fair Scheduler. https:\/\/hadoop.apache.org\/docs\/stable\/hadoop-yarn\/hadoop-yarn-site\/FairScheduler.html."},{"key":"e_1_3_2_1_2_1","unstructured":"2023. Slurm Workload Manager Classic Fairshare Algorithm. https:\/\/slurm.schedmd.com\/classic_fair_share.html."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3487009"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3137133.3137147"},{"key":"e_1_3_2_1_5_1","volume-title":"Hamza Ouarnoughi, Smail Niar, Martin Wistuba, and Naigang Wang.","author":"Benmeziane Hadjer","year":"2021","unstructured":"Hadjer Benmeziane, Kaoutar El Maghraoui, Hamza Ouarnoughi, Smail Niar, Martin Wistuba, and Naigang Wang. 2021. A Comprehensive Survey on Hardware-Aware Neural Architecture Search. arXiv:2101.09336 [cs.LG]"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2898442.2898444"},{"key":"e_1_3_2_1_7_1","volume-title":"Neuralpower: Predict and deploy energy-efficient convolutional neural networks. arXiv preprint arXiv:1710.05420","author":"Cai Ermao","year":"2017","unstructured":"Ermao Cai, Da-Cheng Juan, Dimitrios Stamoulis, and Diana Marculescu. 2017. Neuralpower: Predict and deploy energy-efficient convolutional neural networks. arXiv preprint arXiv:1710.05420 (2017)."},{"key":"e_1_3_2_1_8_1","unstructured":"Han Cai Chuang Gan Tianzhe Wang Zhekai Zhang and Song Han. 2020. Once-for-All: Train One Network and Specialize it for Efficient Deployment. arXiv:1908.09791 [cs.LG]"},{"key":"e_1_3_2_1_9_1","volume-title":"TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). USENIX Association, Carlsbad, CA, 578--594. https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/chen"},{"key":"e_1_3_2_1_10_1","volume-title":"Introduction to Algorithms","author":"Cormen Thomas H.","unstructured":"Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest, and Clifford Stein. 2009. Introduction to Algorithms, Third Edition (3rd ed.). The MIT Press.","edition":"3"},{"key":"e_1_3_2_1_11_1","volume-title":"Clipper: A Low-Latency Online Prediction Serving System. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Crankshaw Daniel","year":"2017","unstructured":"Daniel Crankshaw, Xin Wang, Guilio Zhou, Michael J. Franklin, Joseph E. Gonzalez, and Ion Stoica. 2017. Clipper: A Low-Latency Online Prediction Serving System. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). USENIX Association, Boston, MA, 613--627. https:\/\/www.usenix.org\/conference\/nsdi17\/technical-sessions\/presentation\/crankshaw"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/75247.75248"},{"key":"e_1_3_2_1_13_1","volume-title":"2015 15th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing","author":"Georgiou Yiannis","year":"2015","unstructured":"Yiannis Georgiou, David Glesser, Krzysztof Rzadca, and Denis Trystram. 2015. A Scheduler-Level Incentive Mechanism for Energy Efficiency in HPC. 2015 15th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (2015), 617--626."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2342356.2342358"},{"key":"e_1_3_2_1_15_1","volume-title":"Dominant Resource Fairness: Fair Allocation of Multiple Resource Types. In 8th USENIX Symposium on Networked Systems Design and Implementation (NSDI 11)","author":"Ghodsi Ali","year":"2011","unstructured":"Ali Ghodsi, Matei Zaharia, Benjamin Hindman, Andy Konwinski, Scott Shenker, and Ion Stoica. 2011. Dominant Resource Fairness: Fair Allocation of Multiple Resource Types. In 8th USENIX Symposium on Networked Systems Design and Implementation (NSDI 11). USENIX Association, Boston, MA. https:\/\/www.usenix.org\/conference\/nsdi11\/dominant-resource-fairness-fair-allocation-multiple-resource-types"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/90.649569"},{"key":"e_1_3_2_1_17_1","volume-title":"little processing with arm cortex-a15 & cortex-a7. ARM White paper 17","author":"Greenhalgh Peter","year":"2011","unstructured":"Peter Greenhalgh. 2011. Big. little processing with arm cortex-a15 & cortex-a7. ARM White paper 17 (2011)."},{"key":"e_1_3_2_1_18_1","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Gujarati Arpan","year":"2020","unstructured":"Arpan Gujarati, Reza Karimi, Safya Alzayat, Wei Hao, Antoine Kaufmann, Ymir Vigfusson, and Jonathan Mace. 2020. Serving DNNs like Clockwork: Performance Predictability from the Bottom Up. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). USENIX Association, 443--462. https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/gujarati"},{"key":"e_1_3_2_1_19_1","volume-title":"Laurent Broto, Alain Tchana, and Noel De Palma.","author":"Hagimont Daniel","year":"2013","unstructured":"Daniel Hagimont, Christine Mayap Kamga, Laurent Broto, Alain Tchana, and Noel De Palma. 2013. DVFS Aware CPU Credit Enforcement in a Virtualized System. In Middleware 2013, David Eyers and Karsten Schwan (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 123--142."},{"key":"e_1_3_2_1_20_1","volume-title":"Microsecond-scale Preemption for Concurrent GPU-accelerated DNN Inferences. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Han Mingcong","year":"2022","unstructured":"Mingcong Han, Hanze Zhang, Rong Chen, and Haibo Chen. 2022. Microsecond-scale Preemption for Concurrent GPU-accelerated DNN Inferences. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). USENIX Association, Carlsbad, CA, 539--558. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/han"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems -","volume":"1","author":"Han Song","unstructured":"Song Han, Jeff Pool, John Tran, and William J. Dally. 2015. Learning Both Weights and Connections for Efficient Neural Networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1 (Montreal, Canada) (NIPS'15). MIT Press, Cambridge, MA, USA, 1135--1143."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447555.3465326"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/3130379.3130725"},{"key":"e_1_3_2_1_24_1","volume-title":"Distilling the Knowledge in a Neural Network. ArXiv abs\/1503.02531","author":"Hinton Geoffrey E.","year":"2015","unstructured":"Geoffrey E. Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the Knowledge in a Neural Network. ArXiv abs\/1503.02531 (2015)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Andrew Howard Mark Sandler Grace Chu Liang-Chieh Chen Bo Chen Mingxing Tan Weijun Wang Yukun Zhu Ruoming Pang Vijay Vasudevan Quoc V. Le and Hartwig Adam. 2019. Searching for MobileNetV3. arXiv:1905.02244 [cs.CV]","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave.jors.2600523"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2018.2796077"},{"key":"e_1_3_2_1_28_1","volume-title":"2011 38th Annual International Symposium on Computer Architecture (ISCA). 45--56","author":"Kwon Youngjin","year":"2011","unstructured":"Youngjin Kwon, Changdae Kim, Seungryoul Maeng, and Jaehyuk Huh. 2011. Virtualizing performance asymmetric multi-core systems. In 2011 38th Annual International Symposium on Computer Architecture (ISCA). 45--56."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","unstructured":"Da Li Xinbo Chen Michela Becchi and Ziliang Zong. 2016. Evaluating the Energy Efficiency of Deep Convolutional Neural Networks on CPUs and GPUs. In 2016 IEEE International Conferences on Big Data and Cloud Computing (BD-Cloud) Social Computing and Networking (SocialCom) Sustainable Computing and Communications (SustainCom) (BDCloud-SocialCom-SustainCom). 477--484. 10.1109\/BDCloud-SocialCom-SustainCom.2016.76","DOI":"10.1109\/BDCloud-SocialCom-SustainCom.2016.76"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362694"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","unstructured":"Tong Li Paul Brett Rob Knauerhase David Koufaty Dheeraj Reddy and Scott Hahn. 2010. Operating system support for overlapping-ISA heterogeneous multi-core architectures. In HPCA - 16 2010 The Sixteenth International Symposium on High-Performance Computer Architecture. 1--12. 10.1109\/HPCA.2010.5416660","DOI":"10.1109\/HPCA.2010.5416660"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582080"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3576842.3582375"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2016.0110"},{"key":"e_1_3_2_1_35_1","unstructured":"Seyed Morteza Nabavinejad and Tian Guo. 2023. Opportunities of Renewable Energy Powered DNN Inference. arXiv:2306.12247 [cs.DC]"},{"key":"e_1_3_2_1_36_1","volume-title":"Completely Fair Scheduler. Linux J","author":"Pabla Chandandeep Singh","year":"2009","unstructured":"Chandandeep Singh Pabla. 2009. Completely Fair Scheduler. Linux J. 2009, 184, Article 4 (aug 2009)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/90.234856"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/SEC54971.2022.00026"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"e_1_3_2_1_40_1","volume-title":"INFaaS: Automated Model-less Inference Serving. In 2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Romero Francisco","year":"2021","unstructured":"Francisco Romero, Qian Li, Neeraja J. Yadwadkar, and Christos Kozyrakis. 2021. INFaaS: Automated Model-less Inference Serving. In 2021 USENIX Annual Technical Conference (USENIX ATC 21). USENIX Association, 397--411. https:\/\/www.usenix.org\/conference\/atc21\/presentation\/romero"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2984607"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3381831"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/90.502236"},{"key":"e_1_3_2_1_44_1","volume-title":"Ecovisor: A Virtual Energy System for Carbon-Efficient Applications. In ASPLOS.","author":"Souza Abel","year":"2023","unstructured":"Abel Souza, Noman Bashir, Jorge Murillo, Walid Hanafy, Qianlin Liang, David Irwin, and Prashant Shenoy. 2023. Ecovisor: A Virtual Energy System for Carbon-Efficient Applications. In ASPLOS."},{"key":"e_1_3_2_1_45_1","volume-title":"Le","author":"Tan M.","year":"2019","unstructured":"M. Tan and Quoc V. Le. 2019. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. ArXiv abs\/1905.11946 (2019)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2013.6618815"},{"key":"e_1_3_2_1_48_1","volume-title":"Karma: Resource Allocation for Dynamic Demands. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Vuppalapati Midhul","year":"2023","unstructured":"Midhul Vuppalapati, Giannis Fikioris, Rachit Agarwal, Asaf Cidon, Anurag Khandelwal, and \u00c9va Tardos. 2023. Karma: Resource Allocation for Dynamic Demands. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). USENIX Association, Boston, MA, 645--662. https:\/\/www.usenix.org\/conference\/osdi23\/presentation\/vuppalapati"},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of the 1st USENIX conference on Operating Systems Design and Implementation. 1--es.","author":"Waldspurger Carl A","year":"1994","unstructured":"Carl A Waldspurger and William E Weihl. 1994. Lottery scheduling: Flexible proportional-share resource management. In Proceedings of the 1st USENIX conference on Operating Systems Design and Implementation. 1--es."},{"key":"e_1_3_2_1_50_1","volume-title":"ALERT: Accurate Learning for Energy and Timeliness. In 2020 USENIX Annual Technical Conference (USENIX ATC 20)","author":"Wan Chengcheng","year":"2020","unstructured":"Chengcheng Wan, Muhammad Santriaji, Eri Rogers, Henry Hoffmann, Michael Maire, and Shan Lu. 2020. ALERT: Accurate Learning for Energy and Timeliness. In 2020 USENIX Annual Technical Conference (USENIX ATC 20). USENIX Association, 353--369. https:\/\/www.usenix.org\/conference\/atc20\/presentation\/wan"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","unstructured":"Chengjian Wen Jun He Jiong Zhang and Xiang Long. 2010. PCFS: Power Credit Based Fair Scheduler Under DVFS for Muliticore Virtualization Platform. In 2010 IEEE\/ACM Int'l Conference on Green Computing and Communications & Int'l Conference on Cyber Physical and Social Computing. 163--170. 10.1109\/GreenCom-CPSCom.2010.126","DOI":"10.1109\/GreenCom-CPSCom.2010.126"},{"key":"e_1_3_2_1_52_1","unstructured":"Xen. 2018. Credit Scheduler. https:\/\/wiki.xenproject.org\/wiki\/Credit_Scheduler."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2017.8335698"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.643"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3197747"},{"key":"e_1_3_2_1_56_1","unstructured":"Jiahui Yu Linjie Yang Ning Xu Jianchao Yang and Thomas Huang. 2018. Slimmable Neural Networks. arXiv:1812.08928 [cs.CV]"},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops.","author":"Zhang Li Lyna","year":"2020","unstructured":"Li Lyna Zhang, Yuqing Yang, Yuhang Jiang, Wenwu Zhu, and Yunxin Liu. 2020. Fast Hardware-Aware Neural Architecture Search. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops."},{"key":"e_1_3_2_1_58_1","volume-title":"Le","author":"Zoph Barret","year":"2017","unstructured":"Barret Zoph and Quoc V. Le. 2017. Neural Architecture Search with Reinforcement Learning. arXiv:1611.01578 [cs.LG]"}],"event":{"name":"SEC '23: Eighth ACM\/IEEE Symposium on Edge Computing","location":"Wilmington DE USA","acronym":"SEC '23","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","IEEE Computer Society"]},"container-title":["Proceedings of the Eighth ACM\/IEEE Symposium on Edge Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583740.3628435","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583740.3628435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:29Z","timestamp":1750178789000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583740.3628435"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,6]]},"references-count":58,"alternative-id":["10.1145\/3583740.3628435","10.1145\/3583740"],"URL":"https:\/\/doi.org\/10.1145\/3583740.3628435","relation":{},"subject":[],"published":{"date-parts":[[2023,12,6]]},"assertion":[{"value":"2024-08-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}