{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:21:38Z","timestamp":1785421298416,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,12]],"date-time":"2023-11-12T00:00:00Z","timestamp":1699747200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Research Grants Council (RGC) of Hong Kong under Collaborative Research Fund (CRF) C4072-21G","award":["C4072-21G and C4034-21G"],"award-info":[{"award-number":["C4072-21G and C4034-21G"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3625687.3625789","type":"proceedings-article","created":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T12:07:18Z","timestamp":1714133238000},"page":"97-110","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["Miriam: Exploiting Elastic Kernels for Real-time Multi-DNN Inference on Edge GPU"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7997-1798","authenticated-orcid":false,"given":"Zhihe","family":"Zhao","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2072-1502","authenticated-orcid":false,"given":"Neiwen","family":"Ling","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3775-911X","authenticated-orcid":false,"given":"Nan","family":"Guan","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1772-7751","authenticated-orcid":false,"given":"Guoliang","family":"Xing","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,26]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2023. AMD Ryzen\u2122 Embedded Family. https:\/\/www.amd.com\/en\/products\/embedded-ryzen-series?gclid=Cj0KCQjwtsCgBhDEARIsAE7RYh1ldW0JK-snwE61wNNbhkSG8acBGKg5IpqwGrFXC7Hs85Fj4jWHcA8aAtj0EALw_wcB."},{"key":"e_1_3_2_1_2_1","unstructured":"2023. NVIDIA Nsight Systems. https:\/\/developer.nvidia.com\/nsight-systems."},{"key":"e_1_3_2_1_3_1","unstructured":"2023. NVIDIA Triton Inference Server Organization. https:\/\/github.com\/triton-inference-server."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018748"},{"key":"e_1_3_2_1_5_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_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476143"},{"key":"e_1_3_2_1_7_1","volume-title":"Gate-variants of gated recurrent unit (GRU) neural networks. In 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS)","author":"Dey Rahul","unstructured":"Rahul Dey and Fathi M Salem. 2017. Gate-variants of gated recurrent unit (GRU) neural networks. In 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS). IEEE, 1597--1600."},{"key":"e_1_3_2_1_8_1","first-page":"167","article-title":"Ios: Inter-operator scheduler for cnn acceleration","volume":"3","author":"Ding Yaoyao","year":"2021","unstructured":"Yaoyao Ding, Ligeng Zhu, Zhihao Jia, Gennady Pekhimenko, and Song Han. 2021. Ios: Inter-operator scheduler for cnn acceleration. Proceedings of Machine Learning and Systems 3 (2021), 167--180.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241559"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453953.3453972"},{"key":"e_1_3_2_1_11_1","volume-title":"A study of persistent threads style GPU programming for GPGPU workloads","author":"Gupta Kshitij","unstructured":"Kshitij Gupta, Jeff A Stuart, and John D Owens. 2012. A study of persistent threads style GPU programming for GPGPU workloads. IEEE."},{"key":"e_1_3_2_1_12_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_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988336.2988355"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_15_1","volume-title":"Long short-term memory. Neural computation 9, 8","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_1_16_1","volume-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv preprint arXiv:1602.07360","author":"Iandola Forrest N","year":"2016","unstructured":"Forrest N Iandola, Song Han, Matthew W Moskewicz, Khalid Ashraf, William J Dally, and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv preprint arXiv:1602.07360 (2016)."},{"key":"e_1_3_2_1_17_1","unstructured":"LG Electronics Inc. 2020. LGSVL Simulator: An Autonomous Vehicle Simulator. https:\/\/www.svlsimulator.com\/docs\/archive\/2020.06\/getting-started\/."},{"key":"e_1_3_2_1_18_1","volume-title":"Alexey Tumanov, Joseph Gonzalez, and Ion Stoica.","author":"Jain Paras","year":"2019","unstructured":"Paras Jain, Xiangxi Mo, Ajay Jain, Harikaran Subbaraj, Rehan Sohail Durrani, Alexey Tumanov, Joseph Gonzalez, and Ion Stoica. 2019. Dynamic Space-Time Scheduling for GPU Inference. CoRR abs\/1901.00041 (2019). arXiv:1901.00041 http:\/\/arxiv.org\/abs\/1901.00041"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS.2019.00011"},{"key":"e_1_3_2_1_20_1","volume-title":"Monte Carlo theory and practice. Reports on progress in Physics 43, 9","author":"James Frederick","year":"1980","unstructured":"Frederick James. 1980. Monte Carlo theory and practice. Reports on progress in Physics 43, 9 (1980), 1145."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538948"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454038"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00021"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3568520"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485938"},{"key":"e_1_3_2_1_27_1","volume-title":"VELTAIR: Towards High-Performance Multi-tenant Deep Learning Services via Adaptive Compilation and Scheduling. arXiv preprint arXiv:2201.06212","author":"Liu Zihan","year":"2022","unstructured":"Zihan Liu, Jingwen Leng, Zhihui Zhang, Quan Chen, Chao Li, and Minyi Guo. 2022. VELTAIR: Towards High-Performance Multi-tenant Deep Learning Services via Adaptive Compilation and Scheduling. arXiv preprint arXiv:2201.06212 (2022)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3081333.3081359"},{"key":"e_1_3_2_1_29_1","volume-title":"Light-weight, Generalpurpose, and Mobile-friendly Vision Transformer. CoRR abs\/2110.02178","author":"Mehta Sachin","year":"2021","unstructured":"Sachin Mehta and Mohammad Rastegari. 2021. MobileViT: Light-weight, Generalpurpose, and Mobile-friendly Vision Transformer. CoRR abs\/2110.02178 (2021). arXiv:2110.02178 https:\/\/arxiv.org\/abs\/2110.02178"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437984.3458837"},{"key":"e_1_3_2_1_31_1","unstructured":"NVIDIA. 2014. CUDA Dynamic Parallelism API and Principles. https:\/\/developer.nvidia.com\/blog\/cuda-dynamic-parallelism-api-principles\/."},{"key":"e_1_3_2_1_32_1","unstructured":"NVIDIA. 2020. NVIDIA MIG. https:\/\/www.nvidia.com\/en-us\/technologies\/multi-instance-gpu\/."},{"key":"e_1_3_2_1_33_1","unstructured":"NVIDIA. 2020. NVIDIA MPS. https:\/\/docs.nvidia.com\/deploy\/pdf\/CUDA_Multi_Process_Service_Overview.pdf."},{"key":"e_1_3_2_1_34_1","volume-title":"CUDA by example: an introduction to general-purpose GPU programming","author":"Sanders Jason","unstructured":"Jason Sanders and Edward Kandrot. 2010. CUDA by example: an introduction to general-purpose GPU programming. Addison-Wesley Professional."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN54338.2022.00029"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2958343"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2958343"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751213"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377138"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS46320.2019.00042"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001161"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3079202"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419192"},{"key":"e_1_3_2_1_45_1","volume-title":"Automated Runtime-Aware Scheduling for Multi-Tenant DNN Inference on GPU. In 2021 IEEE\/ACM International Conference On Computer Aided Design (ICCAD). IEEE, 1--9.","author":"Yu Fuxun","year":"2021","unstructured":"Fuxun Yu, Shawn Bray, Di Wang, Longfei Shangguan, Xulong Tang, Chenchen Liu, and Xiang Chen. 2021. Automated Runtime-Aware Scheduling for Multi-Tenant DNN Inference on GPU. In 2021 IEEE\/ACM International Conference On Computer Aided Design (ICCAD). IEEE, 1--9."},{"key":"e_1_3_2_1_46_1","volume-title":"RMDDQN-Learning: Computation Offloading Algorithm Based on Dynamic Adaptive Multi-Objective Reinforcement Learning in Internet of Vehicles","author":"Zhang Xiangjun","year":"2023","unstructured":"Xiangjun Zhang, Weiguo Wu, Zhihe Zhao, Jinyu Wang, and Song Liu. 2023. RMDDQN-Learning: Computation Offloading Algorithm Based on Dynamic Adaptive Multi-Objective Reinforcement Learning in Internet of Vehicles. IEEE Transactions on Vehicular Technology (2023)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583120.3586953"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378457"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3275199"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3568050"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3572864.3580330"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450268.3453520"},{"key":"e_1_3_2_1_53_1","volume-title":"Ansor: Generating High-Performance Tensor Programs for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, Joseph E. Gonzalez, and Ion Stoica. 2020. Ansor: Generating High-Performance Tensor Programs for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). USENIX Association, 863--879. https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/zheng"}],"event":{"name":"SenSys '23: 21st ACM Conference on Embedded Networked Sensor Systems","location":"Istanbul Turkiye","acronym":"SenSys '23","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems","SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3625687.3625789","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3625687.3625789","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:11Z","timestamp":1750182551000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3625687.3625789"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,12]]},"references-count":53,"alternative-id":["10.1145\/3625687.3625789","10.1145\/3625687"],"URL":"https:\/\/doi.org\/10.1145\/3625687.3625789","relation":{},"subject":[],"published":{"date-parts":[[2023,11,12]]},"assertion":[{"value":"2024-04-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}