{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T13:05:37Z","timestamp":1780664737485,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T00:00:00Z","timestamp":1777161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3767295.3803579","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:20:04Z","timestamp":1777062004000},"page":"383-399","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Bridging the GPU Utilization Gap: Predictive Multi-Dimensional Resource Scheduling for AI Workloads"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3754-680X","authenticated-orcid":false,"given":"Yilei","family":"Lu","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"},{"name":"Baihai, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2479-7595","authenticated-orcid":false,"given":"Dongbiao","family":"He","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7104-1526","authenticated-orcid":false,"given":"Teng","family":"Ma","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5304-0713","authenticated-orcid":false,"given":"Zhe","family":"Liu","sequence":"additional","affiliation":[{"name":"Baihai, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4866-2955","authenticated-orcid":false,"given":"Letian","family":"Ruan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4034-7490","authenticated-orcid":false,"given":"Jinlei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6651-7032","authenticated-orcid":false,"given":"Yongwei","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,26]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624849"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711702"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid54584.2022.00079"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00444-8"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11749-016-0481-7"},{"key":"e_1_3_2_1_6_1","first-page":"424","article-title":"Alternative algorithm for Hubert's space-filling curve","volume":"100","author":"Butz Arthur R","year":"2006","unstructured":"Arthur R Butz. 2006. Alternative algorithm for Hubert's space-filling curve. IEEE Trans. Comput. 100, 4 (2006), 424\u2013426.","journal-title":"IEEE Trans. Comput."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539606"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_10_1","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Choi Seungbeom","year":"2022","unstructured":"Seungbeom Choi, Sunho Lee, Yeonjae Kim, Jongse Park, Youngjin Kwon, and Jaehyuk Huh. 2022. Serving heterogeneous machine learning models on Multi-GPU servers with Spatio-Temporal sharing. In 2022 USENIX Annual Technical Conference (USENIX ATC 22). 199\u2013216."},{"key":"e_1_3_2_1_11_1","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Choudhury Arnab","year":"2024","unstructured":"Arnab Choudhury, Yang Wang, Tuomas Pelkonen, Kutta Srinivasan, Abha Jain, Shenghao Lin, Delia David, Siavash Soleimanifard, Michael Chen, Abhishek Yadav, et al. 2024. MAST: Global scheduling of ML training across Geo-Distributed datacenters at hyperscale. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 563\u2013580."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00029"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421284"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486978"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639232"},{"key":"e_1_3_2_1_16_1","volume-title":"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)."},{"key":"e_1_3_2_1_17_1","volume-title":"16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Gu Juncheng","year":"2019","unstructured":"Juncheng Gu, Mosharaf Chowdhury, Kang G Shin, Yibo Zhu, Myeongjae Jeon, Junjie Qian, Hongqiang Liu, and Chuanxiong Guo. 2019. Tiresias: A GPU cluster manager for distributed deep learning. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19). 485\u2013500."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2021.02.015"},{"key":"e_1_3_2_1_19_1","volume-title":"Transformer in transformer. Advances in neural information processing systems 34","author":"Han Kai","year":"2021","unstructured":"Kai Han, An Xiao, Enhua Wu, Jianyuan Guo, Chunjing Xu, and Yunhe Wang. 2021. Transformer in transformer. Advances in neural information processing systems 34 (2021), 15908\u201315919."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476223"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3317550.3321427"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567508"},{"key":"e_1_3_2_1_23_1","volume-title":"Compiler-Directed Incremental Checkpointing for Low Latency GPU Preemption. In 2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 751\u2013761","author":"Ji Zhuoran","year":"2022","unstructured":"Zhuoran Ji and Cho-Li Wang. 2022. Compiler-Directed Incremental Checkpointing for Low Latency GPU Preemption. In 2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 751\u2013761."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629585"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582038"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-5364-9"},{"key":"e_1_3_2_1_27_1","volume-title":"Computational intelligence: a methodological introduction","author":"Kruse Rudolf","unstructured":"Rudolf Kruse, Sanaz Mostaghim, Christian Borgelt, Christian Braune, and Matthias Steinbrecher. 2022. Multi-layer perceptrons. In Computational intelligence: a methodological introduction. Springer, 53\u2013124."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569657"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00124"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00082"},{"key":"e_1_3_2_1_31_1","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Li Zhuohan","year":"2023","unstructured":"Zhuohan Li, Lianmin Zheng, Yinmin Zhong, Vincent Liu, Ying Sheng, Xin Jin, Yanping Huang, Zhifeng Chen, Hao Zhang, Joseph E Gonzalez, et al. 2023. AlpaServe: Statistical multiplexing with model parallelism for deep learning serving. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). 663\u2013679."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587437"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.1975.10479105"},{"key":"e_1_3_2_1_34_1","unstructured":"McKinsey & Company. 2024. AI power: Expanding data center capacity to meet growing demand. Online. https:\/\/www.mckinsey.com\/industries\/technology-media-and-telecommunications\/our-insights\/ai-power-expanding-data-center-capacity-to-meet-growing-demand Accessed: 2025-03-19."},{"key":"e_1_3_2_1_35_1","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Mohan Jayashree","year":"2022","unstructured":"Jayashree Mohan, Amar Phanishayee, Janardhan Kulkarni, and Vijay Chidambaram. 2022. Looking beyond GPUs for DNN scheduling on Multi-Tenant clusters. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). 579\u2013596."},{"key":"e_1_3_2_1_36_1","volume-title":"13th USENIX symposium on operating systems design and implementation (OSD1 18)","author":"Moritz Philipp","year":"2018","unstructured":"Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael I Jordan, et al. 2018. Ray: A distributed framework for emerging AI applications. In 13th USENIX symposium on operating systems design and implementation (OSD1 18). 561\u2013577."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613163"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/1594371.1594375"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.3102\/1076998619872761"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2022.3148714"},{"key":"e_1_3_2_1_41_1","volume-title":"CASSINI:Network-Aware Job Scheduling in Machine Learning Clusters. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Rajasekaran Sudarsanan","year":"2024","unstructured":"Sudarsanan Rajasekaran, Manya Ghobadi, and Aditya Akella. 2024. CASSINI:Network-Aware Job Scheduling in Machine Learning Clusters. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 1403\u20131420."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544788"},{"key":"e_1_3_2_1_43_1","volume-title":"Space-filling curves","author":"Sagan Hans","unstructured":"Hans Sagan. 2012. Space-filling curves. Springer Science & Business Media."},{"key":"e_1_3_2_1_44_1","volume-title":"Hidden technical debt in machine learning systems. Advances in neural information processing systems 28","author":"Sculley David","year":"2015","unstructured":"David Sculley, Gary Holt, Daniel Golovin, Eugene Davydov, Todd Phillips, Dietmar Ebner, Vinay Chaudhary, Michael Young, Jean-Francois Crespo, and Dan Dennison. 2015. Hidden technical debt in machine learning systems. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13677-023-00471-1"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629578"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i09.7123"},{"key":"e_1_3_2_1_48_1","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Sun Biao","year":"2024","unstructured":"Biao Sun, Ziming Huang, Hanyu Zhao, Wencong Xiao, Xinyi Zhang, Yong Li, and Wei Lin. 2024. Llumnix: Dynamic scheduling for large language model serving. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 173\u2013191."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3329027"},{"key":"e_1_3_2_1_50_1","volume-title":"HyTGraph: GPU-Accelerated Graph Processing with Hybrid Transfer Management. In 2023 IEEE 39th International Conference on Data Engineering (ICDE). IEEE, 558\u2013571","author":"Wang Qiange","year":"2023","unstructured":"Qiange Wang, Xin Ai, Yanfeng Zhang, Jing Chen, and Ge Yu. 2023. HyTGraph: GPU-Accelerated Graph Processing with Hybrid Transfer Management. In 2023 IEEE 39th International Conference on Data Engineering (ICDE). IEEE, 558\u2013571."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS52674.2021.00021"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1002\/0471704091"},{"key":"e_1_3_2_1_53_1","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Weng Qizhen","year":"2022","unstructured":"Qizhen Weng, Wencong Xiao, Yinghao Yu, Wei Wang, Cheng Wang, Jian He, Yong Li, Liping Zhang, Wei Lin, and Yu Ding. 2022. MLaaS in the wild: Workload analysis and scheduling in Large-Scale heterogeneous GPU clusters. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). 945\u2013960."},{"key":"e_1_3_2_1_54_1","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Weng Qizhen","year":"2023","unstructured":"Qizhen Weng, Lingyun Yang, Yinghao Yu, Wei Wang, Xiaochuan Tang, Guodong Yang, and Liping Zhang. 2023. Beware of fragmentation: Scheduling GPU-Sharing workloads with fragmentation gradient descent. In 2023 USENIX Annual Technical Conference (USENIX ATC 23). 995\u20131008."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_56_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Wu Bingyang","year":"2023","unstructured":"Bingyang Wu, Zili Zhang, Zhihao Bai, Xuanzhe Liu, and Xin Jin. 2023. Transparent GPU sharing in container clouds for deep learning workloads. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 69\u201385."},{"key":"e_1_3_2_1_57_1","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Xiao Wencong","year":"2018","unstructured":"Wencong Xiao, Romil Bhardwaj, Ramachandran Ramjee, Muthian Sivathanu, Nipun Kwatra, Zhenhua Han, Pratyush Patel, Xuan Peng, Hanyu Zhao, Quanlu Zhang, et al. 2018. Gandiva: Introspective cluster scheduling for deep learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 595\u2013610."},{"key":"e_1_3_2_1_58_1","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Xiao Wencong","year":"2020","unstructured":"Wencong Xiao, Shiru Ren, Yong Li, Yang Zhang, Pengyang Hou, Zhi Li, Yihui Feng, Wei Lin, and Yangqing Jia. 2020. AntMan: Dynamic scaling on GPU clusters for deep learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). 533\u2013548."},{"key":"e_1_3_2_1_59_1","volume-title":"GREEN: Carbon-efficient Resource Scheduling for Machine Learning Clusters. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Xu Kaiqiang","year":"2025","unstructured":"Kaiqiang Xu, Decang Sun, Han Tian, Junxue Zhang, and Kai Chen. 2025. GREEN: Carbon-efficient Resource Scheduling for Machine Learning Clusters. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). 999\u20131014."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707266"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2018.00119"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3317550.3321443"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3638757"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3136245"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685817"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3710848.3710863"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472456.3472467"}],"event":{"name":"EUROSYS '26: 21st European Conference on Computer Systems","location":"McEwan Hall\/The University of Edinburgh Edinburgh Scotland UK","acronym":"EUROSYS '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 21st European Conference on Computer Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3767295.3803579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T12:14:36Z","timestamp":1780661676000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767295.3803579"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,26]]},"references-count":67,"alternative-id":["10.1145\/3767295.3803579","10.1145\/3767295"],"URL":"https:\/\/doi.org\/10.1145\/3767295.3803579","relation":{},"subject":[],"published":{"date-parts":[[2026,4,26]]},"assertion":[{"value":"2026-04-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}