{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:40:03Z","timestamp":1766220003774,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100002367","name":"Strategic Priority Research Program of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XDA 0360301"],"award-info":[{"award-number":["XDA 0360301"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFB3308702"],"award-info":[{"award-number":["2023YFB3308702"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302489"],"award-info":[{"award-number":["62302489"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3754598.3754623","type":"proceedings-article","created":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:34:32Z","timestamp":1766219672000},"page":"541-552","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Scheduling based on Block Features for Concurrent Inference with Unseen DNN Models on GPU"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4063-6818","authenticated-orcid":false,"given":"Diaohan","family":"Luo","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4778-7029","authenticated-orcid":false,"given":"Zhen","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5985-9395","authenticated-orcid":false,"given":"Heran","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1323-2455","authenticated-orcid":false,"given":"Yuewen","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7903-5879","authenticated-orcid":false,"given":"Heng","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3385-1245","authenticated-orcid":false,"given":"Xi","family":"Han","sequence":"additional","affiliation":[{"name":"University College London, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0237-5100","authenticated-orcid":false,"given":"Wenbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Nanjing, Nanjing, China and Nanjing Institute of Software Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,20]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2018. Amazon rekognition. https:\/\/aws.amazon.com\/rekognition\/."},{"key":"e_1_3_3_2_3_2","unstructured":"2018. Amazon translate. https:\/\/aws.amazon.com\/translate\/."},{"key":"e_1_3_3_2_4_2","unstructured":"2018. Google translate. https:\/\/translate.google.com."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1145\/3037697.3037700","volume-title":"Proceedings of the Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems","author":"Chen Quan","year":"2017","unstructured":"Quan Chen, Hailong Yang, Minyi Guo, Ram\u00a0Srivatsa Kannan, Jason Mars, and Lingjia Tang. 2017. Prophet: Precise qos prediction on non-preemptive accelerators to improve utilization in warehouse-scale computers. In Proceedings of the Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems. 17\u201332."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Quan Chen Hailong Yang Jason Mars and Lingjia Tang. 2016. Baymax: Qos awareness and increased utilization for non-preemptive accelerators in warehouse scale computers. ACM SIGPLAN Notices 51 4 (2016) 681\u2013696.","DOI":"10.1145\/2954679.2872368"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673091"},{"key":"e_1_3_3_2_8_2","first-page":"199","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_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00027"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476143"},{"key":"e_1_3_3_2_11_2","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1810.04805 (2018)."},{"key":"e_1_3_3_2_12_2","unstructured":"Google. 2023. Google Machine Learning. https:\/\/developers.google.com\/machine-learning\/guides\/rules-of-ml"},{"key":"e_1_3_3_2_13_2","unstructured":"Arpan Gujarati Reza Karimi Safya Alzayat Antoine Kaufmann Ymir Vigfusson and Jonathan Mace. 2020. Serving DNNs like Clockwork: Performance Predictability from the Bottom Up. CoRR abs\/2006.02464 (2020). arXiv:https:\/\/arXiv.org\/abs\/2006.02464https:\/\/arxiv.org\/abs\/2006.02464"},{"key":"e_1_3_3_2_14_2","first-page":"539","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022, Carlsbad, CA, USA, July 11-13, 2022","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 2022, Carlsbad, CA, USA, July 11-13, 2022, Marcos\u00a0K. Aguilera and Hakim Weatherspoon (Eds.). USENIX Association, 539\u2013558. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/han"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303949"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421302"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538948"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3623278.3624753"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00048"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605627"},{"key":"e_1_3_3_2_23_2","unstructured":"Christopher Olston Noah Fiedel Kiril Gorovoy Jeremiah Harmsen Li Lao Fangwei Li Vinu Rajashekhar Sukriti Ramesh and Jordan Soyke. 2017. Tensorflow-serving: Flexible high-performance ml serving. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1712.06139 (2017)."},{"key":"e_1_3_3_2_24_2","first-page":"8024","volume-title":"Advances in Neural Information Processing Systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et\u00a0al. 2019. PyTorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems. 8024\u20138035."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Wonik Seo Sanghoon Cha Yeonjae Kim Jaehyuk Huh and Jongse Park. 2021. SLO-aware inference scheduler for heterogeneous processors in edge platforms. ACM Transactions on Architecture and Code Optimization (TACO) 18 4 (2021) 1\u201326.","DOI":"10.1145\/3460352"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1145\/3341301.3359658","volume-title":"Proceedings of the 27th ACM Symposium on Operating Systems Principles","author":"Shen Haichen","year":"2019","unstructured":"Haichen Shen, Lequn Chen, Yuchen Jin, Liangyu Zhao, Bingyu Kong, Matthai Philipose, Arvind Krishnamurthy, and Ravi Sundaram. 2019. Nexus: A GPU cluster engine for accelerating DNN-based video analysis. In Proceedings of the 27th ACM Symposium on Operating Systems Principles. 322\u2013337."},{"key":"e_1_3_3_2_27_2","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1145\/3627703.3629578","volume-title":"Proceedings of the Nineteenth European Conference on Computer Systems","author":"Strati Foteini","year":"2024","unstructured":"Foteini Strati, Xianzhe Ma, and Ana Klimovic. 2024. Orion: Interference-aware, fine-grained GPU sharing for ML applications. In Proceedings of the Nineteenth European Conference on Computer Systems. 1075\u20131092."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Ivan Tanasic Isaac Gelado Javier Cabezas Alex Ramirez Nacho Navarro and Mateo Valero. 2014. Enabling preemptive multiprogramming on GPUs. ACM SIGARCH Computer Architecture News 42 3 (2014) 193\u2013204.","DOI":"10.1145\/2678373.2665702"},{"key":"e_1_3_3_2_32_2","first-page":"995","volume-title":"2023 USENIX Annual Technical Conference, USENIX ATC 2023, Boston, MA, USA, July 10-12, 2023","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 2023, Boston, MA, USA, July 10-12, 2023, Julia Lawall and Dan Williams (Eds.). USENIX Association, 995\u20131008. https:\/\/www.usenix.org\/conference\/atc23\/presentation\/weng"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3516807.3516820"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1145\/3627703.3650074","volume-title":"Proceedings of the Nineteenth European Conference on Computer Systems","author":"Yang Qizheng","year":"2024","unstructured":"Qizheng Yang, Tianyi Yang, Mingcan Xiang, Lijun Zhang, Haoliang Wang, Marco Serafini, and Hui Guan. 2024. GMorph: Accelerating multi-dnn inference via model fusion. In Proceedings of the Nineteenth European Conference on Computer Systems. 505\u2013523."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643501"},{"key":"e_1_3_3_2_36_2","first-page":"1049","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Zhang Chengliang","year":"2019","unstructured":"Chengliang Zhang, Minchen Yu, Wei Wang, and Feng Yan. 2019. { MArk} : Exploiting cloud services for { Cost-Effective}, { SLO-Aware} machine learning inference serving. In 2019 USENIX Annual Technical Conference (USENIX ATC 19). 1049\u20131062."},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330351"}],"event":{"name":"ICPP '25: 54th International Conference on Parallel Processing","location":"San Diego CA USA","acronym":"ICPP '25"},"container-title":["Proceedings of the 54th International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3754598.3754623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:38:44Z","timestamp":1766219924000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3754598.3754623"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":36,"alternative-id":["10.1145\/3754598.3754623","10.1145\/3754598"],"URL":"https:\/\/doi.org\/10.1145\/3754598.3754623","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]},"assertion":[{"value":"2025-12-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}