{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T02:38:46Z","timestamp":1777343926550,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T00:00:00Z","timestamp":1691366400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Provincial Key Research and Development Program of Shandong, China"},{"name":"National Natural Science Foundation of China"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,7]]},"DOI":"10.1145\/3605573.3605627","type":"proceedings-article","created":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T16:21:16Z","timestamp":1694622076000},"page":"605-614","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["SPLIT: QoS-Aware DNN Inference on Shared GPU via Evenly-Sized Model Splitting"],"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, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6623-1491","authenticated-orcid":false,"given":"Tian","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, 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, 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, China and Chongqing School, University of Chinese Academy of Science, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5350-9773","authenticated-orcid":false,"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, China"}],"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, China and University of Chinese Academy of Sciences, Nanjing, and Nanjing Institute of Software Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,9,13]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"12th USENIX symposium on operating systems design and implementation (OSDI 16)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, 2016. { TensorFlow} : A System for { Large-Scale} Machine Learning. In 12th USENIX symposium on operating systems design and implementation (OSDI 16). 265\u2013283."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483590"},{"key":"e_1_3_2_2_3_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 2018","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie\u00a0Q. 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 2018, Carlsbad, CA, USA, October 8-10, 2018, Andrea\u00a0C. Arpaci-Dusseau and Geoff Voelker (Eds.). USENIX Association, 578\u2013594. https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/chen"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00027"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2015.2445754"},{"key":"e_1_3_2_2_6_1","unstructured":"ONNX\u00a0Runtime developers. 2021. ONNX Runtime. https:\/\/onnxruntime.ai\/. Version: x.y.z."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421284"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00062"},{"key":"e_1_3_2_2_9_1","volume-title":"Serving DNNs like Clockwork: Performance Predictability from the Bottom Up. CoRR abs\/2006.02464","author":"Gujarati Arpan","year":"2020","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:2006.02464https:\/\/arxiv.org\/abs\/2006.02464"},{"key":"e_1_3_2_2_10_1","volume-title":"Microsecond-scale Preemption for Concurrent GPU-accelerated DNN Inferences. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 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_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303949"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00075"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00071"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS49844.2020.00027"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421302"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538948"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3084689"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303950"},{"key":"e_1_3_2_2_19_1","first-page":"105","article-title":"PaddlePaddle: An open-source deep learning platform from industrial practice","volume":"1","author":"Ma Yanjun","year":"2019","unstructured":"Yanjun Ma, Dianhai Yu, Tian Wu, and Haifeng Wang. 2019. PaddlePaddle: An open-source deep learning platform from industrial practice. Frontiers of Data and Domputing 1, 1 (2019), 105\u2013115.","journal-title":"Frontiers of Data and Domputing"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1851322.1851328"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1700298"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2712560"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_2_24_1","unstructured":"NVIDIA. 2020. Cuda streams. https:\/\/developer.download.nvidia.com\/CUDA\/training\/StreamsAndConcurrencyWebinar.pdf"},{"key":"e_1_3_2_2_25_1","unstructured":"NVIDIA. 2021. NVIDIA Multi-Process Service. https:\/\/docs.nvidia.com\/deploy\/mps"},{"key":"e_1_3_2_2_26_1","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga 2019. PyTorch: An imperative style high-performance deep learning library. In Advances in Neural Information Processing Systems. 8024\u20138035."},{"key":"e_1_3_2_2_27_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460352"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359658"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2014.6853208"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3516807.3516820"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS.2019.00033"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643501"},{"key":"e_1_3_2_2_35_1","volume-title":"SLO-Aware Machine Learning Inference Serving. In 2019 USENIX Annual Technical Conference, USENIX ATC 2019","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 2019, Renton, WA, USA, July 10-12, 2019, Dahlia Malkhi and Dan Tsafrir (Eds.). USENIX Association, 1049\u20131062. https:\/\/www.usenix.org\/conference\/atc19\/presentation\/zhang-chengliang"}],"event":{"name":"ICPP 2023: 52nd International Conference on Parallel Processing","location":"Salt Lake City UT USA","acronym":"ICPP 2023"},"container-title":["Proceedings of the 52nd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605573.3605627","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3605573.3605627","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:04Z","timestamp":1750182544000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605573.3605627"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,7]]},"references-count":35,"alternative-id":["10.1145\/3605573.3605627","10.1145\/3605573"],"URL":"https:\/\/doi.org\/10.1145\/3605573.3605627","relation":{},"subject":[],"published":{"date-parts":[[2023,8,7]]},"assertion":[{"value":"2023-09-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}