{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T16:53:29Z","timestamp":1791478409975,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202216"],"award-info":[{"award-number":["62202216"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2023A1515010244"],"award-info":[{"award-number":["2023A1515010244"]}]},{"name":"Shenzhen Science and Technology Program","award":["1121101752002"],"award-info":[{"award-number":["1121101752002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,12]]},"DOI":"10.1145\/3673038.3673089","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T18:29:01Z","timestamp":1723141741000},"page":"504-513","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["MIGER: Integrating Multi-Instance GPU and Multi-Process Service for Deep Learning Clusters"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1277-8164","authenticated-orcid":false,"given":"Bowen","family":"Zhang","sequence":"first","affiliation":[{"name":"Southern University of Science and Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0468-2029","authenticated-orcid":false,"given":"Shuxin","family":"Li","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1903-6428","authenticated-orcid":false,"given":"Zhuozhao","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, China and Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271739"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS48715.2020.000-1"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS49844.2020.00027"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_5_1","volume-title":"Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"key":"e_1_3_2_1_6_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_7_1","volume-title":"MuxFlow: Efficient and Safe GPU Sharing in Large-Scale Production Deep Learning Clusters. arXiv preprint arXiv:2303.13803","author":"Zhao Yihao","year":"2023","unstructured":"Yihao Zhao, Xin Liu, Shufan Liu, Xiang Li, Yibo Zhu, Gang Huang, Xuanzhe Liu, and Xin Jin. 2023. MuxFlow: Efficient and Safe GPU Sharing in Large-Scale Production Deep Learning Clusters. arXiv preprint arXiv:2303.13803 (2023)."},{"key":"e_1_3_2_1_8_1","unstructured":"NVIDIA MPS. 2023. NVIDIA Multi-Process Service (MPS) Documentation. https:\/\/docs.nvidia.com\/deploy\/mps\/index.html"},{"key":"e_1_3_2_1_9_1","unstructured":"NVIDIA MIG. 2023. NVIDIA Multi-Instance GPU (MIG) Guide. https:\/\/docs.nvidia.com\/datacenter\/tesla\/mig-user-guide\/index.html"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563510"},{"key":"e_1_3_2_1_11_1","unstructured":"IBM. 2023. IBM Spectrum LSF. https:\/\/www.ibm.com\/products\/hpc-workload-management. Accessed: 2023-04-01."},{"key":"e_1_3_2_1_12_1","unstructured":"SchedMD. 2023. Slurm Workload Manager. https:\/\/slurm.schedmd.com. Accessed: 2023-04-01."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3232715"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2954679.2872368"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.44"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_17_1","volume-title":"Learning representations by back-propagating errors. nature 323, 6088","author":"Rumelhart E","year":"1986","unstructured":"David\u00a0E Rumelhart, Geoffrey\u00a0E Hinton, and Ronald\u00a0J Williams. 1986. Learning representations by back-propagating errors. nature 323, 6088 (1986), 533\u2013536."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607060"},{"key":"e_1_3_2_1_19_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_20_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard G","year":"2017","unstructured":"Andrew\u00a0G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_21_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_22_1","volume-title":"International conference on machine learning. PMLR, 1263\u20131272","author":"Gilmer Justin","year":"2017","unstructured":"Justin Gilmer, Samuel\u00a0S Schoenholz, Patrick\u00a0F Riley, Oriol Vinyals, and George\u00a0E Dahl. 2017. Neural message passing for quantum chemistry. In International conference on machine learning. PMLR, 1263\u20131272."},{"key":"e_1_3_2_1_23_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on machine learning. PMLR, 173\u2013182","author":"Amodei Dario","year":"2016","unstructured":"Dario Amodei, Sundaram Ananthanarayanan, Rishita Anubhai, Jingliang Bai, Eric Battenberg, Carl Case, Jared Casper, Bryan Catanzaro, Qiang Cheng, Guoliang Chen, 2016. Deep speech 2: End-to-end speech recognition in english and mandarin. In International conference on machine learning. PMLR, 173\u2013182."},{"key":"e_1_3_2_1_25_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer, 234\u2013241."},{"key":"e_1_3_2_1_26_1","volume-title":"Serving DNN models with multi-instance gpus: A case of the reconfigurable machine scheduling problem. arXiv preprint arXiv:2109.11067","author":"Tan Cheng","year":"2021","unstructured":"Cheng Tan, Zhichao Li, Jian Zhang, Yu Cao, Sikai Qi, Zherui Liu, Yibo Zhu, and Chuanxiong Guo. 2021. Serving DNN models with multi-instance gpus: A case of the reconfigurable machine scheduling problem. arXiv preprint arXiv:2109.11067 (2021)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476223"},{"key":"e_1_3_2_1_28_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_29_1","volume-title":"Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. 2017. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)."},{"key":"e_1_3_2_1_30_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR (2021)."},{"key":"e_1_3_2_1_31_1","volume-title":"Deep learning workload scheduling in gpu datacenters: Taxonomy, challenges and vision. arXiv preprint arXiv:2205.11913","author":"Gao Wei","year":"2022","unstructured":"Wei Gao, Qinghao Hu, Zhisheng Ye, Peng Sun, Xiaolin Wang, Yingwei Luo, Tianwei Zhang, and Yonggang Wen. 2022. Deep learning workload scheduling in gpu datacenters: Taxonomy, challenges and vision. arXiv preprint arXiv:2205.11913 (2022)."},{"key":"e_1_3_2_1_32_1","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Crankshaw Daniel","year":"2017","unstructured":"Daniel Crankshaw, Xin Wang, Guilio Zhou, Michael\u00a0J Franklin, Joseph\u00a0E 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). 613\u2013627."},{"key":"e_1_3_2_1_33_1","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Hwang Changho","year":"2021","unstructured":"Changho Hwang, Taehyun Kim, Sunghyun Kim, Jinwoo Shin, and KyoungSoo Park. 2021. Elastic resource sharing for distributed deep learning. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21). 721\u2013739."},{"key":"e_1_3_2_1_34_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_35_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_36_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). 443\u2013462."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544224"},{"key":"e_1_3_2_1_38_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, 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_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330351"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3064352"},{"key":"e_1_3_2_1_41_1","volume-title":"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). 539\u2013558."},{"key":"e_1_3_2_1_42_1","volume-title":"Orion: Interference-aware, Fine-grained GPU Sharing for ML Applications.","author":"Strati Foteini","year":"2024","unstructured":"Foteini Strati, Xianzhe Ma, and Ana Klimovic. 2024. Orion: Interference-aware, Fine-grained GPU Sharing for ML Applications. (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00124"}],"event":{"name":"ICPP '24: the 53rd International Conference on Parallel Processing","location":"Gotland Sweden","acronym":"ICPP '24"},"container-title":["Proceedings of the 53rd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673089","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3673038.3673089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:29:49Z","timestamp":1758648589000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673089"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,12]]},"references-count":43,"alternative-id":["10.1145\/3673038.3673089","10.1145\/3673038"],"URL":"https:\/\/doi.org\/10.1145\/3673038.3673089","relation":{},"subject":[],"published":{"date-parts":[[2024,8,12]]},"assertion":[{"value":"2024-08-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}