{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T04:00:56Z","timestamp":1749355256155,"version":"3.41.0"},"reference-count":31,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Electron."],"published-print":{"date-parts":[[2025,6,1]]},"DOI":"10.1587\/transele.2024lhp0001","type":"journal-article","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T22:34:24Z","timestamp":1732660464000},"page":"293-305","source":"Crossref","is-referenced-by-count":0,"title":["High-Reuse Quantized Bit-Serial Convolutional Neural Network Processing Element Arrays with Weight Ring Dataflow"],"prefix":"10.1587","volume":"E108.C","author":[{"given":"Xiaoshu","family":"CHENG","sequence":"first","affiliation":[{"name":"School of Integrated Circuit Science and Engineering, University of Electronic Science and Technology of China"}]},{"given":"Yiwen","family":"WANG","sequence":"additional","affiliation":[{"name":"School of Integrated Circuit Science and Engineering, University of Electronic Science and Technology of China"}]},{"given":"Hongfei","family":"LOU","sequence":"additional","affiliation":[{"name":"School of Integrated Circuit Science and Engineering, University of Electronic Science and Technology of China"}]},{"given":"Weiran","family":"DING","sequence":"additional","affiliation":[{"name":"School of Integrated Circuit Science and Engineering, University of Electronic Science and Technology of China"}]},{"given":"Ping","family":"LI","sequence":"additional","affiliation":[{"name":"School of Integrated Circuit Science and Engineering, University of Electronic Science and Technology of China"},{"name":"State Key Laboratory of Electronic Thin Films and Integrated Devices, University of Electronic Science and Technology of China"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, \u201cGoing deeper with convolutions,\u201d ArXiv14094842 Cs, Sept. 2014. 10.48550\/arXiv.1409.4842","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] K. Guo, L. Sui, J. Qiu, J. Yu, J. Wang, S. Yao, S. Han, Y. Wang, and H. Yang, \u201cAngel-eye: A complete design flow for mapping CNN onto embedded FPGA,\u201d IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst., vol.37, no.1, pp.35-47, Jan. 2018. 10.1109\/tcad.2017.2705069","DOI":"10.1109\/TCAD.2017.2705069"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] B. Moons, D. Bankman, and M. Verhelst, Embedded Deep Learning: Algorithms, Architectures and Circuits for Always-on Neural Network Processing, Springer International Publishing, Cham, 2019. 10.1007\/978-3-319-99223-5","DOI":"10.1007\/978-3-319-99223-5"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] Y. LeCun, Y. Bengio, and G. Hinton, \u201cDeep learning,\u201d Nature, vol.521, no.7553, pp.436-444, May 2015. 10.1038\/nature14539","DOI":"10.1038\/nature14539"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] R. Hartley and K.K. Parhi, Digit-Serial Computation. Springer US, Boston, MA, 1995. 10.1007\/978-1-4615-2327-7","DOI":"10.1007\/978-1-4615-2327-7"},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] B. de Bruin, Z. Zivkovic, and H. Corporaal, \u201cQuantization of deep neural networks for accumulator-constrained processors,\u201d Microprocess. Microsyst., vol.72, 102872, Feb. 2020. 10.1016\/j.micpro.2019.102872","DOI":"10.1016\/j.micpro.2019.102872"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] Y.-H. Chen, J. Emer, and V. Sze, \u201cEyeriss: A spatial architecture for energy-efficient dataflow for convolutional neural networks,\u201d 2016 ACM\/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA), pp.367-379, June 2016. 10.1109\/isca.2016.40","DOI":"10.1109\/ISCA.2016.40"},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] T. Chen, Z. Du, N. Sun, J. Wang, C. Wu, Y. Chen, and O. Temam, \u201cDianNao: A small-footprint high-throughput accelerator for ubiquitous machine-learning,\u201d ACM SIGPLAN Notices, vol.49, no.4, pp.269-284, 2014. 10.1145\/2644865.2541967","DOI":"10.1145\/2644865.2541967"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] Y. Chen, T. Luo, S. Liu, S. Zhang, L. He, J. Wang, L. Li, T. Chen, Z. Xu, N. Sun, and O. Temam, \u201cDaDianNao: A machine-learning supercomputer,\u201d 2014 47th Annual IEEE\/ACM International Symposium on Microarchitecture, Cambridge, United Kingdom, pp.609-622, Dec. 2014. 10.1109\/micro.2014.58","DOI":"10.1109\/MICRO.2014.58"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] A. Parashar, M. Rhu, A. Mukkara, A. Puglielli, R. Venkatesan, B. Khailany, J. Emer, S.W. Keckler, and W. J. Dally, \u201cSCNN: An accelerator for compressed-sparse convolutional neural networks,\u201d Proc. 44th Annual International Symposium on Computer Architecture, Toronto, Canada, pp.27-40, June 2017. 10.1145\/3079856.3080254","DOI":"10.1145\/3079856.3080254"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] M. Kim and J.-S. Seo, \u201cDeep convolutional neural network accelerator featuring conditional computing and low external memory access,\u201d 2020 IEEE Custom Integrated Circuits Conference (CICC), pp.1-4, March 2020. 10.1109\/cicc48029.2020.9075931","DOI":"10.1109\/CICC48029.2020.9075931"},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] Y. Zheng, H. Yang, Y. Shu, Y. Jia, and Z. Huang, \u201cOptimizing off-chip memory access for deep neural network accelerator,\u201d IEEE Trans. Circuits Syst. II Express Briefs, vol.69, no.4, pp.2316-2320, 2022. 10.1109\/tcsii.2022.3150030","DOI":"10.1109\/TCSII.2022.3150030"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] H. Lee, Y.-H. Wu, Y.-S. Lin, and S.-Y. Chien, \u201cConvolutional neural network accelerator with vector quantization,\u201d 2019 IEEE International Symposium on Circuits and Systems (ISCAS), pp.1-5, May 2019. 10.1109\/iscas.2019.8702105","DOI":"10.1109\/ISCAS.2019.8702105"},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] H. Jia, D. Ren, and X. Zou, \u201cAn FPGA-based accelerator for deep neural network with novel reconfigurable architecture,\u201d IEICE Electron. Express, vol.18, no.4, 20210012, Feb. 2021. 10.1587\/elex.18.20210012","DOI":"10.1587\/elex.18.20210012"},{"key":"15","doi-asserted-by":"publisher","unstructured":"[15] Y. Choi, D. Bae, J. Sim, S. Choi, M. Kim, and L.-S. Kim, \u201cEnergy-efficient design of processing element for convolutional neural network,\u201d IEEE Trans. Circuits Syst. II Express Briefs, vol.64, no.11, pp.1332-1336, Nov. 2017. 10.1109\/tcsii.2017.2691771","DOI":"10.1109\/TCSII.2017.2691771"},{"key":"16","doi-asserted-by":"publisher","unstructured":"[16] L.-C. Hsu, C.-T. Chiu, K.-T. Lin, H.-H. Chou, and Y.-Y. Pu, \u201cESSA: An energy-aware bit-serial streaming deep convolutional neural network accelerator,\u201d J. Syst. Archit., vol.111, 101831, Dec. 2020. 10.1016\/j.sysarc.2020.101831","DOI":"10.1016\/j.sysarc.2020.101831"},{"key":"17","doi-asserted-by":"publisher","unstructured":"[17] F. Tu, S. Yin, P. Ouyang, S. Tang, L. Liu, and S. Wei, \u201cDeep convolutional neural network architecture with reconfigurable computation patterns,\u201d IEEE Trans. Very Large Scale Integr. VLSI Syst., vol.25, no.8, pp.2220-2233, Aug. 2017. 10.1109\/tvlsi.2017.2688340","DOI":"10.1109\/TVLSI.2017.2688340"},{"key":"18","unstructured":"[18] T. Isshiki, \u201cHigh-performance bit-serial datapath implementation for large-scale configurable systems,\u201d Ph.D. dissertation, University of California, Santa Cruz, CA, USA, p.187, April 1996."},{"key":"19","doi-asserted-by":"publisher","unstructured":"[19] X. Cheng, Y. Wang, J. Liu, W. Ding, H. Lou, and P. Li, \u201cBooth encoded bit-serial multiply-accumulate units with improved area and energy efficiencies,\u201d Electronics, vol.12, no.10, 2177, May 2023. 10.3390\/electronics12102177","DOI":"10.3390\/electronics12102177"},{"key":"20","doi-asserted-by":"publisher","unstructured":"[20] A. Ruospo, E. Sanchez, M. Traiola, I. O\u2019Connor, and A. Bosio, \u201cInvestigating data representation for efficient and reliable convolutional neural networks,\u201d Microprocess. Microsyst., vol.86, 104318, Oct. 2021. 10.1016\/j.micpro.2021.104318","DOI":"10.1016\/j.micpro.2021.104318"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] N. Mitschke, M. Heizmann, K.-H. Noffz, and R. Wittmann, \u201cA fixed-point quantization technique for convolutional neural networks based on weight scaling,\u201d 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, pp.3836-3840, Sept. 2019. 10.1109\/icip.2019.8803490","DOI":"10.1109\/ICIP.2019.8803490"},{"key":"22","doi-asserted-by":"publisher","unstructured":"[22] S.I. Young, W. Zhe, D. Taubman, and B. Girod, \u201cTransform quantization for CNN compression,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.44, no.9, pp.5700-5714, 2021. 10.1109\/tpami.2021.3084839","DOI":"10.1109\/TPAMI.2021.3084839"},{"key":"23","doi-asserted-by":"publisher","unstructured":"[23] S. Seo and J. Kim, \u201cEfficient weights quantization of convolutional neural networks using kernel density estimation based non-uniform quantizer,\u201d Appl. Sci., vol.9, no.12, 2559, June 2019. 10.3390\/app9122559","DOI":"10.3390\/app9122559"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] S.-E. Chang, Y. Li, M. Sun, R. Shi, H.K.-H. So, X. Qian, Y. Wang, and X. Lin, \u201cMix and match: A novel FPGA-centric deep neural network quantization framework,\u201d arXiv, 11-Dec-2020. 10.48550\/arXiv.2012.04240","DOI":"10.1109\/HPCA51647.2021.00027"},{"key":"25","unstructured":"[25] \u201cQuantization \u2014 PyTorch 2.0 documentation,\u201d https:\/\/pytorch.org\/docs\/stable\/quantization.html, accessed Oct. 2, 2023."},{"key":"26","doi-asserted-by":"publisher","unstructured":"[26] J.-C. See, H.-F. Ng, H.-K. Tan, J.-J. Chang, W.-K. Lee, and S.O. Hwang, \u201cDoubleQExt: Hardware and memory efficient CNN through two levels of quantization,\u201d IEEE Access, vol.9, pp.169082-169091, 2021. 10.1109\/access.2021.3138756","DOI":"10.1109\/ACCESS.2021.3138756"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] G. Tatar, S. Bayar, and I. Cicek, \u201cPerformance evaluation of low-precision quantized LeNet and ConvNet neural networks,\u201d 2022 International Conference on INnovations in Intelligent SysTems and Applications (INISTA), Biarritz, France, pp.1-6, Aug. 2022. 10.1109\/inista55318.2022.9894261","DOI":"10.1109\/INISTA55318.2022.9894261"},{"key":"28","doi-asserted-by":"publisher","unstructured":"[28] V. Sze, Y.-H. Chen, T.-J. Yang, and J.S. Emer, \u201cEfficient processing of deep neural networks: A tutorial and survey,\u201d Proc. IEEE, vol.105, no.12, pp.2295-2329, Dec. 2017. 10.1109\/jproc.2017.2761740","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"29","doi-asserted-by":"publisher","unstructured":"[29] W. Huang, H. Wu, Q. Chen, C. Luo, S. Zeng, T. Li, and Y. Huang, \u201cFPGA-based high-throughput CNN hardware accelerator with high computing resource utilization ratio,\u201d IEEE Trans. Neural Netw. Learn. Syst., vol.33, no.8, pp.4069-4083, 2021. 10.1109\/tnnls.2021.3055814","DOI":"10.1109\/TNNLS.2021.3055814"},{"key":"30","doi-asserted-by":"publisher","unstructured":"[30] B. Zhao, M. Wang, and M. Liu, \u201cAn energy-efficient coarse grained spatial architecture for convolutional neural networks AlexNet,\u201d IEICE Electron. Express, vol.14, no.15, 20170595, 2017. 10.1587\/elex.14.20170595","DOI":"10.1587\/elex.14.20170595"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] V. Sriram, D. Cox, K.H. Tsoi, and W. Luk, \u201cTowards an embedded biologically-inspired machine vision processor,\u201d 2010 International Conference on Field-Programmable Technology, Beijing, China, pp.273-278, Dec. 2010. 10.1109\/fpt.2010.5681487","DOI":"10.1109\/FPT.2010.5681487"}],"container-title":["IEICE Transactions on Electronics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transele\/E108.C\/6\/E108.C_2024LHP0001\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T03:43:13Z","timestamp":1749267793000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transele\/E108.C\/6\/E108.C_2024LHP0001\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,1]]},"references-count":31,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1587\/transele.2024lhp0001","relation":{},"ISSN":["0916-8524","1745-1353"],"issn-type":[{"type":"print","value":"0916-8524"},{"type":"electronic","value":"1745-1353"}],"subject":[],"published":{"date-parts":[[2025,6,1]]},"article-number":"2024LHP0001"}}