{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T21:50:51Z","timestamp":1757541051563,"version":"3.41.0"},"reference-count":39,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T00:00:00Z","timestamp":1654473600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Flemish Government (AI Research Program) and KU Leuven","award":["C14\/18\/100"],"award-info":[{"award-number":["C14\/18\/100"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2022,9,30]]},"abstract":"<jats:p>\n            <jats:bold>Analog\u00a0in\u00a0Memory\u00a0Computing\u00a0(AiMC)<\/jats:bold>\n            based neural network acceleration is a promising solution to increase the energy efficiency of deep neural networks deployment. However, the quantization requirements of these analog systems are not compatible with state-of-the-art neural network quantization techniques. Indeed, while the quantization of the weights and activations is considered by modern deep neural network quantization techniques, AiMC accelerators also impose the quantization of each\n            <jats:bold>Matrix\u00a0Vector\u00a0Multiplication\u00a0(MVM)<\/jats:bold>\n            result. In most demonstrated AiMC implementations, the quantization range of MVM results is considered a fixed parameter of the accelerator. This work demonstrates that dynamic control over this quantization range is possible but also desirable for analog neural networks acceleration. An AiMC compatible quantization flow coupled with a hardware aware quantization range driving technique is introduced to fully exploit these dynamic ranges. Using CIFAR-10 and ImageNet as benchmarks, the proposed solution results in networks that are both more accurate and more robust to the inherent vulnerability of analog circuits than fixed quantization range based approaches.\n          <\/jats:p>","DOI":"10.1145\/3498328","type":"journal-article","created":{"date-parts":[[2022,2,24]],"date-time":"2022-02-24T17:13:41Z","timestamp":1645722821000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Dynamic Quantization Range Control for Analog-in-Memory Neural Networks Acceleration"],"prefix":"10.1145","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1592-755X","authenticated-orcid":false,"given":"Nathan","family":"Laubeuf","sequence":"first","affiliation":[{"name":"Interuniversity Microelectronics Center (IMEC) and ESAT Laboratory, Katholieke Universiteit (K.U.) Leuven, Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonas","family":"Doevenspeck","sequence":"additional","affiliation":[{"name":"Interuniversity Microelectronics Center (IMEC), Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis A.","family":"Papistas","sequence":"additional","affiliation":[{"name":"Interuniversity Microelectronics Center (IMEC), Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michele","family":"Caselli","sequence":"additional","affiliation":[{"name":"Interuniversity Microelectronics Center (IMEC), Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Cosemans","sequence":"additional","affiliation":[{"name":"Interuniversity Microelectronics Center (IMEC), Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Vrancx","sequence":"additional","affiliation":[{"name":"Interuniversity Microelectronics Center (IMEC), Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Debjyoti","family":"Bhattacharjee","sequence":"additional","affiliation":[{"name":"Interuniversity Microelectronics Center (IMEC), Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arindam","family":"Mallik","sequence":"additional","affiliation":[{"name":"Interuniversity Microelectronics Center (IMEC), Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Debacker","sequence":"additional","affiliation":[{"name":"Interuniversity Microelectronics Center (IMEC), Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diederik","family":"Verkest","sequence":"additional","affiliation":[{"name":"Interuniversity Microelectronics Center (IMEC), Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francky","family":"Catthoor","sequence":"additional","affiliation":[{"name":"Interuniversity Microelectronics Center (IMEC) and ESAT Laboratory, Katholieke Universiteit (K.U.) Leuven, Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rudy","family":"Lauwereins","sequence":"additional","affiliation":[{"name":"Interuniversity Microelectronics Center (IMEC) and ESAT Laboratory, Katholieke Universiteit (K.U.) Leuven, Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,6,6]]},"reference":[{"key":"e_1_3_4_2_2","first-page":"265","volume-title":"12th  \\( \\lbrace \\) USENIX \\( \\rbrace \\)  Symposium on Operating Systems Design and Implementation ( \\( \\lbrace \\) OSDI \\( \\rbrace \\)  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, et\u00a0al. 2016. TensorFlow: A system for large-scale machine learning. In 12th \\( \\lbrace \\) USENIX \\( \\rbrace \\) Symposium on Operating Systems Design and Implementation ( \\( \\lbrace \\) OSDI \\( \\rbrace \\) 16). 265\u2013283."},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_3_4_4_2","unstructured":"Dario Amodei Danny Hernandez Girish Sastry Jack Clark Greg Brockman and Ilya Sutskever. [n.d.]. AI and Compute. https:\/\/openai.com\/blog\/ai-and-compute\/. Accessed: 2021-05-04."},{"key":"e_1_3_4_5_2","unstructured":"Chaim Baskin Natan Liss Yoav Chai Evgenii Zheltonozhskii Eli Schwartz Raja Giryes Avi Mendelson and Alexander M. Bronstein. 2018. NICE: Noise injection and clamping estimation for neural network quantization. arXiv preprint arXiv:1810.00162 (2018)."},{"key":"e_1_3_4_6_2","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Nicholas L\u00e9onard, and Aaron Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013).","journal-title":"arXiv preprint arXiv:1308.3432"},{"key":"e_1_3_4_7_2","first-page":"1","volume-title":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","author":"Bhattacharjee Debjyoti","year":"2021","unstructured":"Debjyoti Bhattacharjee, Nathan Laubeuf, Stefan Cosemans, Ioannis Papistas, Arindam Mallik, Peter Debacker, Myung Hee Na, and Diederik Verkest. 2021. Design-technology space exploration for energy efficient AiMC-based inference acceleration. In 2021 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 1\u20135."},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2018.2880918"},{"key":"e_1_3_4_9_2","article-title":"Pact: Parameterized clipping activation for quantized neural networks","author":"Choi Jungwook","year":"2018","unstructured":"Jungwook Choi, Zhuo Wang, Swagath Venkataramani, Pierce I-Jen Chuang, Vijayalakshmi Srinivasan, and Kailash Gopalakrishnan. 2018. Pact: Parameterized clipping activation for quantized neural networks. arXiv preprint arXiv:1805.06085 (2018).","journal-title":"arXiv preprint arXiv:1805.06085"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.022071131"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533684"},{"key":"e_1_3_4_12_2","volume-title":"ICLR","author":"Esser Steven K.","year":"2020","unstructured":"Steven K. Esser, Jeffrey L. McKinstry, Deepika Bablani, Rathinakumar Appuswamy, and Dharmendra S. Modha. 2020. Learned step size quantization. In ICLR. OpenReview.net."},{"key":"e_1_3_4_13_2","article-title":"VecQ: Minimal loss DNN model compression with vectorized weight quantization","author":"Gong Cheng","year":"2020","unstructured":"Cheng Gong, Yao Chen, Ye Lu, Tao Li, Cong Hao, and Deming Chen. 2020. VecQ: Minimal loss DNN model compression with vectorized weight quantization. IEEE Trans. Comput. (2020).","journal-title":"IEEE Trans. Comput."},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_4_15_2","article-title":"Neural networks for machine learning.","author":"Hinton Geoffrey","year":"2012","unstructured":"Geoffrey Hinton. 2012. Neural networks for machine learning.Coursera (video lectures).","journal-title":"Coursera (video lectures)"},{"key":"e_1_3_4_16_2","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3242044"},{"key":"e_1_3_4_17_2","first-page":"112","volume-title":"Proceedings of Machine Learning and Systems","volume":"2","author":"Jain Sambhav","year":"2020","unstructured":"Sambhav Jain, Albert Gural, Michael Wu, and Chris Dick. 2020. Trained quantization thresholds for accurate and efficient fixed-point inference of deep neural networks. In Proceedings of Machine Learning and Systems, I. Dhillon, D. Papailiopoulos, and V. Sze (Eds.), Vol. 2. 112\u2013128."},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2020.2992886"},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_4_20_2","article-title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","author":"Krishnamoorthi Raghuraman","year":"2018","unstructured":"Raghuraman Krishnamoorthi. 2018. Quantizing deep convolutional networks for efficient inference: A whitepaper. arXiv preprint arXiv:1806.08342 (2018).","journal-title":"arXiv preprint arXiv:1806.08342"},{"key":"e_1_3_4_21_2","unstructured":"Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. Technical Report. University of Toronto."},{"key":"e_1_3_4_22_2","article-title":"Ternary weight networks","author":"Li Fengfu","year":"2016","unstructured":"Fengfu Li, Bo Zhang, and Bin Liu. 2016. Ternary weight networks. arXiv preprint arXiv:1605.04711 (2016).","journal-title":"arXiv preprint arXiv:1605.04711"},{"key":"e_1_3_4_23_2","article-title":"Discovering low-precision networks close to full-precision networks for efficient embedded inference","author":"McKinstry Jeffrey L.","year":"2018","unstructured":"Jeffrey L. McKinstry, Steven K. Esser, Rathinakumar Appuswamy, Deepika Bablani, John V. Arthur, Izzet B. Yildiz, and Dharmendra S. Modha. 2018. Discovering low-precision networks close to full-precision networks for efficient embedded inference. arXiv preprint arXiv:1809.04191 (2018).","journal-title":"arXiv preprint arXiv:1809.04191"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2020.3020286"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CICC51472.2021.9431575"},{"key":"e_1_3_4_26_2"},{"key":"e_1_3_4_27_2","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","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. Advances in Neural Information Processing Systems 32 (2019), 8026\u20138037.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553486"},{"key":"e_1_3_4_30_2"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_4_32_2","first-page":"T168\u2013T169","volume-title":"2019 Symposium on VLSI Technology","author":"Sebastian Abu","year":"2019","unstructured":"Abu Sebastian, Irem Boybat, Martino Dazzi, Iason Giannopoulos, V. Jonnalagadda, Vinay Joshi, Geethan Karunaratne, Benedikt Kersting, Riduan Khaddam-Aljameh, S. R. Nandakumar, et\u00a0al. 2019. Computational memory-based inference and training of deep neural networks. In 2019 Symposium on VLSI Technology. IEEE, T168\u2013T169."},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662392"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2005.251"},{"key":"e_1_3_4_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC47756.2020.9045192"},{"key":"e_1_3_4_36_2","volume-title":"Opencores Floating Point Unit","author":"Usselmann Rudolf","year":"2018","unstructured":"Rudolf Usselmann. 2018. Opencores Floating Point Unit. https:\/\/opencores.org\/projects\/fpu."},{"issue":"6","key":"e_1_3_4_37_2","first-page":"1733","article-title":"XNOR-SRAM: In-memory computing SRAM macro for binary\/ternary deep neural networks","volume":"55","author":"Yin Shihui","year":"2020","unstructured":"Shihui Yin, Zhewei Jiang, Jae-Sun Seo, and Mingoo Seok. 2020. XNOR-SRAM: In-memory computing SRAM macro for binary\/ternary deep neural networks. IEEE Journal of Solid-State Circuits 55, 6 (2020), 1733\u20131743.","journal-title":"IEEE Journal of Solid-State Circuits"},{"key":"e_1_3_4_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"e_1_3_4_39_2","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou Shuchang","year":"2016","unstructured":"Shuchang Zhou, Yuxin Wu, Zekun Ni, Xinyu Zhou, He Wen, and Yuheng Zou. 2016. DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160 (2016).","journal-title":"arXiv preprint arXiv:1606.06160"},{"key":"e_1_3_4_40_2","article-title":"Trained ternary quantization","author":"Zhu Chenzhuo","year":"2016","unstructured":"Chenzhuo Zhu, Song Han, Huizi Mao, and William J. Dally. 2016. Trained ternary quantization. arXiv preprint arXiv:1612.01064 (2016).","journal-title":"arXiv preprint arXiv:1612.01064"}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3498328","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3498328","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:04Z","timestamp":1750188604000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3498328"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,6]]},"references-count":39,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,9,30]]}},"alternative-id":["10.1145\/3498328"],"URL":"https:\/\/doi.org\/10.1145\/3498328","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"type":"print","value":"1084-4309"},{"type":"electronic","value":"1557-7309"}],"subject":[],"published":{"date-parts":[[2022,6,6]]},"assertion":[{"value":"2021-07-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-06-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}