{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T14:29:51Z","timestamp":1782397791304,"version":"3.54.5"},"reference-count":31,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2022,12,10]],"date-time":"2022-12-10T00:00:00Z","timestamp":1670630400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"European Union\u2019s Horizon 2020 Research and Innovation program","award":["780788"],"award-info":[{"award-number":["780788"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2023,1,31]]},"abstract":"<jats:p>Many modern applications require execution of Convolutional Neural Networks (CNNs) on edge devices, such as mobile phones or embedded platforms. This can be challenging, as the state-of-the art CNNs are memory costly, whereas the memory budget of edge devices is highly limited. To address this challenge, a variety of CNN memory reduction methodologies have been proposed. Typically, the memory of a CNN is reduced using methodologies such as pruning and quantization. These methodologies reduce the number or precision of CNN parameters, thereby reducing the CNN memory cost. When more aggressive CNN memory reduction is required, the pruning and quantization methodologies can be combined with CNN memory reuse methodologies. The latter methodologies reuse device memory allocated for storage of CNN intermediate computational results, thereby further reducing the CNN memory cost. However, the existing memory reuse methodologies are unfit for CNN-based applications that exploit pipeline parallelism available within the CNNs or use multiple CNNs to perform their functionality. In this article, we therefore propose a novel CNN memory reuse methodology. In our methodology, we significantly extend and combine two existing CNN memory reuse methodologies to offer efficient memory reuse for a wide range of CNN-based applications.<\/jats:p>","DOI":"10.1145\/3527457","type":"journal-article","created":{"date-parts":[[2022,3,28]],"date-time":"2022-03-28T11:48:53Z","timestamp":1648468133000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Memory-Throughput Trade-off for CNN-Based Applications at the Edge"],"prefix":"10.1145","volume":"28","author":[{"given":"Svetlana","family":"Minakova","sequence":"first","affiliation":[{"name":"Leiden University, South Holland, The Netherlands, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Todor","family":"Stefanov","sequence":"additional","affiliation":[{"name":"Leiden University, South Holland, The Netherlands, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,12,10]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"265","volume-title":"Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201916)","year":"2016","unstructured":"Martin Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, et\u00a0al. 2016. TensorFlow: Large-scale machine learning on heterogeneous systems. In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201916). 265\u2013283."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3088525.3088527"},{"key":"e_1_3_2_4_2","unstructured":"CoRR 2018 abs\/1803.01164 The history began from AlexNet: A comprehensive survey on deep learning approaches"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783725"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/78.485935"},{"key":"e_1_3_2_7_2","volume-title":"Proceedings of Machine Learning and Systems (MLSys\u201920)","author":"Blalock Davis W.","year":"2020","unstructured":"Davis W. Blalock, Jose Javier Gonzalez Ortiz, Jonathan Frankle, and John V. Guttag. 2020. What is the state of neural network pruning? In Proceedings of Machine Learning and Systems (MLSys\u201920)."},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765695"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0638-x"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-020-07468-y"},{"key":"e_1_3_2_12_2","article-title":"A survey of quantization methods for efficient neural network inference","volume":"2103","author":"Gholami Amir","year":"2021","unstructured":"Amir Gholami, Sehoon Kim, Dong Zhen, Zhewei Yao, Michael Mahoney, and Kurt Keutzer. 2021. A survey of quantization methods for efficient neural network inference. arXiv abs\/2103.13630 (2021).","journal-title":"arXiv"},{"key":"e_1_3_2_13_2","unstructured":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201916) 2016 Deep residual learning for image recognition"},{"key":"e_1_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Steve Heath. 2002. Debugging techniques. In Embedded Systems Design (2nd ed.). Newnes Oxford UK 321\u2013325.","DOI":"10.1016\/B978-075065546-0\/50010-4"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3243904"},{"key":"e_1_3_2_17_2","unstructured":"Di Liu Hao Kong Xiangzhong Luo Weichen Liu and Ravi Subramaniam. 2020. Bringing AI to edge: From deep learning\u2019s perspective. arXiv 2011.14808 [cs.LG] (2020)."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSD51259.2020.00031"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60939-9_2"},{"key":"e_1_3_2_20_2","unstructured":"NVIDIA. 2016. TensorRT\u2014High Performance Neural Network Inference Optimizer and Runtime Engine for Production Deployment. Retrieved April 1 2022 from https:\/\/docs.nvidia.com\/deeplearning\/sdk\/tensorrt-developer-guide\/index.html."},{"key":"e_1_3_2_21_2","unstructured":"NVIDIA. 2017. Jetson TX2. Retrieved April 1 2022 from https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/jetson-tx2."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3460378"},{"key":"e_1_3_2_23_2","article-title":"Automatic differentiation in PyTorch","author":"Paszke Adam","year":"2017","unstructured":"Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Zachary DeVito Edward Yang, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic differentiation in PyTorch. In Proceedings of the NIPS 2017 Autodiff Workshop.","journal-title":"Proceedings of the NIPS 2017 Autodiff Workshop."},{"key":"e_1_3_2_24_2","volume-title":"Proceedings of the MLSys 2020 Workshop on Resource-Constrained Machine Learning (ReCoML\u201920)","author":"Pisarchyk Yury","year":"2020","unstructured":"Yury Pisarchyk and Juhyun Lee. 2020. Efficient memory management for deep neural net inference. In Proceedings of the MLSys 2020 Workshop on Resource-Constrained Machine Learning (ReCoML\u201920)."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-28356-0_4"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2019.101749"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0245230"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACSD.2006.23"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3211332.3211336"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.3390\/a12080154"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2944584"}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3527457","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3527457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:53Z","timestamp":1750191533000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3527457"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,10]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1,31]]}},"alternative-id":["10.1145\/3527457"],"URL":"https:\/\/doi.org\/10.1145\/3527457","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,10]]},"assertion":[{"value":"2021-07-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-16","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}