{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T04:51:47Z","timestamp":1793335907083,"version":"4.5.0"},"reference-count":73,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T00:00:00Z","timestamp":1664496000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2022,9,30]]},"abstract":"<jats:p>Convolutional Neural Networks (CNNs) are currently widely used in various fields, particularly for computer vision applications. Edge platforms have drawn tremendous attention from academia and industry due to their ability to improve execution time and preserve privacy. However, edge platforms struggle to satisfy CNNs\u2019 needs due to their computation and energy constraints. Thus, it is challenging to find the most efficient CNN that respects accuracy, time, energy, and memory footprint constraints for a target edge platform. Furthermore, given the size of the design space of CNNs and hardware platforms, performance evaluation of CNNs entails several efforts. Consequently, designers need tools to quickly explore large design space and select the CNN that offers the best performance trade-off for a set of hardware platforms. This article proposes a Machine Learning (ML)\u2013based modeling approach for CNN performances on edge GPU-based platforms for vision applications. We implement and compare five of the most successful ML algorithms for accurate and rapid CNN performance predictions on three different edge GPUs in image classification. Experimental results demonstrate the robustness and usefulness of our proposed methodology. For three of the five ML algorithms \u2014 XGBoost, Random Forest, and Ridge Polynomial regression \u2014 average errors of 11%, 6%, and 8% have been obtained for CNN inference execution time, power consumption, and memory usage, respectively.<\/jats:p>","DOI":"10.1145\/3527169","type":"journal-article","created":{"date-parts":[[2022,3,26]],"date-time":"2022-03-26T11:20:19Z","timestamp":1648293619000},"page":"1-33","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Performance Modeling of Computer Vision-based CNN on Edge GPUs"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1885-6080","authenticated-orcid":false,"given":"Halima","family":"Bouzidi","sequence":"first","affiliation":[{"name":"Universit\u00e9 Polytechnique Hauts-de-France, LAMIH\/CNRS, Valenciennes CEDEX 9"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamza","family":"Ouarnoughi","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Polytechnique Hauts-de-France, LAMIH\/CNRS, INSA Hauts-de-France, Valenciennes CEDEX 9"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Smail","family":"Niar","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Polytechnique Hauts-de-France, LAMIH\/CNRS, INSA Hauts-de-France, Valenciennes CEDEX 9"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdessamad Ait El","family":"Cadi","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Polytechnique Hauts-de-France, LAMIH\/CNRS, INSA Hauts-de-France, Valenciennes CEDEX 9"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,8]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"265","volume-title":"12th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201916)","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, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. TensorFlow: A system for large-scale machine learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201916). USENIX Association, Savannah, GA, 265\u2013283. https:\/\/www.usenix.org\/conference\/osdi16\/technical-sessions\/presentation\/abadi."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218596"},{"key":"e_1_3_2_4_2","first-page":"508","article-title":"The Kendall rank correlation coefficient","author":"Abdi Herv\u00e9","year":"2007","unstructured":"Herv\u00e9 Abdi. 2007. The Kendall rank correlation coefficient. Encyclopedia of Measurement and Statistics. Sage, Thousand Oaks, CA (2007), 508\u2013510.","journal-title":"Encyclopedia of Measurement and Statistics. Sage, Thousand Oaks, CA"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/NCA.2016.7778637"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3392717.3392761"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4302-5990-9_4"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00296-0_5"},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Hadjer Benmeziane Kaoutar El Maghraoui Hamza Ouarnoughi Smail Niar Martin Wistuba and Naigang Wang. 2021. A comprehensive survey on hardware-aware neural architecture search. arXiv:2101.09336 [cs.LG].","DOI":"10.1109\/ISPASS55109.2022.00040"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2877890"},{"key":"e_1_3_2_11_2","series-title":"Proceedings of the 9th Asian Conference on Machine Learning","first-page":"622","volume":"77","author":"Cai Ermao","year":"2017","unstructured":"Ermao Cai, Da-Cheng Juan, Dimitrios Stamoulis, and Diana Marculescu. 2017. NeuralPower: Predict and deploy energy-efficient convolutional neural networks. In Proceedings of the 9th Asian Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 77), Min-Ling Zhang and Yung-Kyun Noh (Eds.). PMLR, Yonsei University, Seoul, Republic of Korea, 622\u2013637. https:\/\/proceedings.mlr.press\/v77\/cai17a.html."},{"key":"e_1_3_2_12_2","first-page":"11285","volume-title":"Advances in Neural Information Processing Systems","author":"Cai Han","year":"2020","unstructured":"Han Cai, Chuang Gan, Ligeng Zhu, and Song Han. 2020. TinyTL: Reduce memory, not parameters for efficient on-device learning. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 11285\u201311297. https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/81f7acabd411274fcf65ce2070ed568a-Paper.pdf."},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_15_2","volume-title":"Advances in Neural Information Processing Systems","author":"Chen Yunpeng","year":"2017","unstructured":"Yunpeng Chen, Jianan Li, Huaxin Xiao, Xiaojie Jin, Shuicheng Yan, and Jiashi Feng. 2017. Dual path networks. In Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/f7e0b956540676a129760a3eae309294-Paper.pdf."},{"key":"e_1_3_2_16_2","article-title":"CuDNN: Efficient primitives for deep learning","author":"Chetlur Sharan","year":"2014","unstructured":"Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, Bryan Catanzaro, and Evan Shelhamer. 2014. CuDNN: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014).","journal-title":"arXiv preprint arXiv:1410.0759"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.12.114"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00215"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/5254.708428"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1970.10488634"},{"key":"e_1_3_2_25_2","article-title":"A fast method to fine-tune neural networks for the least energy consumption on FPGAs","author":"Hosseini Morteza","year":"2021","unstructured":"Morteza Hosseini, Mohammad Ebrahimabadi, Arnab Neelim Mazumder, Houman Homayoun, and Tinoosh Mohsenin. 2021. A fast method to fine-tune neural networks for the least energy consumption on FPGAs. UMBC Student Collection (2021).","journal-title":"UMBC Student Collection"},{"key":"e_1_3_2_26_2","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard Andrew G.","year":"2017","unstructured":"Andrew G. 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).","journal-title":"arXiv preprint arXiv:1704.04861"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_29_2","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV\u201918) Workshops","author":"Ignatov Andrey","year":"2018","unstructured":"Andrey Ignatov, Radu Timofte, William Chou, Ke Wang, Max Wu, Tim Hartley, and Luc Van Gool. 2018. AI benchmark: Running deep neural networks on Android smartphones. In Proceedings of the European Conference on Computer Vision (ECCV\u201918) Workshops, Munich, Germany. 1\u20138."},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1561\/0600000079"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigComp48618.2020.00-89"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622396"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09825-6"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-020-03483-9"},{"key":"e_1_3_2_35_2","volume-title":"Advances in Neural Information Processing Systems","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems, F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger (Eds.), Vol. 25. Curran Associates, Inc."},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSI-DAT.2018.8373244"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00042"},{"issue":"3","key":"e_1_3_2_38_2","first-page":"18","article-title":"Classification and regression by randomForest","volume":"2","author":"Liaw Andy","year":"2002","unstructured":"Andy Liaw and Matthew Wiener.2002. Classification and regression by randomForest. R News 2, 3 (2002), 18\u201322.","journal-title":"R News"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"e_1_3_2_40_2","article-title":"Channel pruning via automatic structure search","author":"Lin Mingbao","year":"2020","unstructured":"Mingbao Lin, Rongrong Ji, Yuxin Zhang, Baochang Zhang, Yongjian Wu, and Yonghong Tian. 2020. Channel pruning via automatic structure search. arXiv preprint arXiv:2001.08565 (2020).","journal-title":"arXiv preprint arXiv:2001.08565"},{"key":"e_1_3_2_41_2","article-title":"MemNet: Memory-efficiency guided neural architecture search with augment-trim learning","author":"Liu Peiye","year":"2019","unstructured":"Peiye Liu, Bo Wu, Huadong Ma, and Mingoo Seok. 2019. MemNet: Memory-efficiency guided neural architecture search with augment-trim learning. arXiv preprint arXiv:1907.09569 (2019).","journal-title":"arXiv preprint arXiv:1907.09569"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123389"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2897634"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394885.3431539"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397514"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/0925-2312(91)90023-5"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/2554850.2555022"},{"key":"e_1_3_2_48_2","volume-title":"NVIDIA Profiler (nvprof)","year":"2007","unstructured":"NVIDIA. 2007. NVIDIA Profiler (nvprof). Retrieved June 30, 2020 from https:\/\/docs.nvidia.com\/cuda\/profiler-users-guide\/index.html#nvprof-overview."},{"key":"e_1_3_2_49_2","volume-title":"Tegrastats Utility","year":"2019","unstructured":"NVIDIA. 2019. Tegrastats Utility. Retrieved December 01, 2020 from https:\/\/docs.nvidia.com\/jetson\/l4t\/index.html#page\/Tegra."},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.proeng.2012.09.545"},{"key":"e_1_3_2_51_2","unstructured":"Hang Qi Evan R. Sparks and Ameet Talwalkar. 2017. PALEO: A performance model for deep neural networks."},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107281"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2017.8167764"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2017.8167764"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.187"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/DASC\/PiCom\/DataCom\/CyberSciTec.2018.000-4"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573527"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8341973"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942085"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"e_1_3_2_62_2","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc V. Le. 2019. EfficientNet: Rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946 (2019).","journal-title":"arXiv preprint arXiv:1905.11946"},{"key":"e_1_3_2_63_2","volume-title":"Efficient Inference with TensorRT","author":"Vanholder Han","year":"2016","unstructured":"Han Vanholder. 2016. Efficient Inference with TensorRT. Retrieved June 30, 2020 from https:\/\/developer.nvidia.com\/tensorrt."},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2869929"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2981684"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC47752.2019.9042047"},{"key":"e_1_3_2_67_2","article-title":"Benchmarking TPU, GPU, and CPU platforms for deep learning","author":"Wang Yu Emma","year":"2019","unstructured":"Yu Emma Wang, Gu-Yeon Wei, and David Brooks. 2019. Benchmarking TPU, GPU, and CPU platforms for deep learning. arXiv preprint arXiv:1907.10701 (2019).","journal-title":"arXiv preprint arXiv:1907.10701"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.60"},{"key":"e_1_3_2_70_2","article-title":"InferBench: Understanding deep learning inference serving with an automatic benchmarking system","author":"Zhang Huaizheng","year":"2020","unstructured":"Huaizheng Zhang, Yizheng Huang, Yonggang Wen, Jianxiong Yin, and Kyle Guan. 2020. InferBench: Understanding deep learning inference serving with an automatic benchmarking system. arXiv preprint arXiv:2011.02327 (2020).","journal-title":"arXiv preprint arXiv:2011.02327"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415609"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2018.01.036"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3527169","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3527169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:01Z","timestamp":1750182661000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3527169"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,30]]},"references-count":73,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,9,30]]}},"alternative-id":["10.1145\/3527169"],"URL":"https:\/\/doi.org\/10.1145\/3527169","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,30]]},"assertion":[{"value":"2021-07-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-14","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-10-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}