{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:54:49Z","timestamp":1760147689943,"version":"build-2065373602"},"reference-count":29,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T00:00:00Z","timestamp":1676937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NSFC","award":["92064004"],"award-info":[{"award-number":["92064004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Processing-in-Memory (PIM) based on Resistive Random Access Memory (RRAM) is an emerging acceleration architecture for artificial neural networks. This paper proposes an RRAM PIM accelerator architecture that does not use Analog-to-Digital Converters (ADCs) and Digital-to-Analog Converters (DACs). Additionally, no additional memory usage is required to avoid the need for a large amount of data transportation in convolution computation. Partial quantization is introduced to reduce the accuracy loss. The proposed architecture can substantially reduce the overall power consumption and accelerate computation. The simulation results show that the image recognition rate for the Convolutional Neural Network (CNN) algorithm can reach 284 frames per second at 50 MHz using this architecture. The accuracy of the partial quantization remains almost unchanged compared to the algorithm without quantization.<\/jats:p>","DOI":"10.3390\/s23052401","type":"journal-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T02:08:34Z","timestamp":1677031714000},"page":"2401","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Ultra-High-Speed Accelerator Architecture for Convolutional Neural Network Based on Processing-in-Memory Using Resistive Random Access Memory"],"prefix":"10.3390","volume":"23","author":[{"given":"Hongzhe","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Electronic Thin Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu 610054, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7183-422X","authenticated-orcid":false,"given":"Junjie","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Electronic Thin Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu 610054, China"}]},{"given":"Hao","family":"Hu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Electronic Thin Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu 610054, China"}]},{"given":"Guo","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Electronic Thin Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu 610054, China"}]},{"given":"Shaogang","family":"Hu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Electronic Thin Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu 610054, China"}]},{"given":"Qi","family":"Yu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Electronic Thin Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu 610054, China"}]},{"given":"Zhen","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Materials and Energy, Guangdong University of Technology, Guangzhou 510006, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1098-9575","authenticated-orcid":false,"given":"Tupei","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore"}]},{"given":"Shijie","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Electronic Thin Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu 610054, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1109\/LCA.2018.2885752","article-title":"PIMSim: A flexible and detailed processing-in-memory simulator","volume":"18","author":"Xu","year":"2018","journal-title":"IEEE Comput. Archit. Lett."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Hayashikoshi, M., Suzuki, J., Watanabe, Y., Furuya, A., Yabuta, T., Ido, M., Kiyota, Y., and Kono, T. (2020, January 17\u201320). Processing in-memory architecture with on-chip transfer learning function for compensating characteristic variation. Proceedings of the 2020 IEEE International Memory Workshop (IMW), Dresden, Germany.","DOI":"10.1109\/IMW48823.2020.9108132"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Kim, S., Kim, S., Cho, K., Shin, T., Park, H., Lho, D., Park, S., Son, K., Park, G., and Kim, J. (2019, January 6\u20139). Processing-in-memory in high bandwidth memory (PIM-HBM) architecture with energy-efficient and low latency channels for high bandwidth system. Proceedings of the 2019 IEEE 28th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS), Montreal, QC, Canada.","DOI":"10.1109\/EPEPS47316.2019.193209"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Xie, P., Sun, G., Wang, F., and Luo, G. (2018, January 28\u201331). V-PIM: An analytical overhead model for processing-in-memory architectures. Proceedings of the 2018 IEEE 7th Non-Volatile Memory Systems and Applications Symposium (NVMSA), Sapporo, Japan.","DOI":"10.1109\/NVMSA.2018.00026"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wu, Y.N., Sze, V., and Emer, J.S. (2020, January 23\u201326). An architecture-level energy and area estimator for processing-in-memory accelerator designs. Proceedings of the 2020 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), Virtual.","DOI":"10.1109\/ISPASS48437.2020.00024"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Chang, L., Wang, Z., Zhang, Y., and Zhao, W. (2017, January 25\u201326). Reconfigurable processing in memory architecture based on spin orbit torque. Proceedings of the 2017 IEEE\/ACM International Symposium on Nanoscale Architectures (NANOARCH), Newport, RI, USA.","DOI":"10.1109\/NANOARCH.2017.8053713"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Jang, Y.J., Kim, B.S., Kim, D.S., and Hwang, T.h. (2016, January 23\u201326). Implementation of a low-overhead processing-in-memory architecture. Proceedings of the 2016 International SoC Design Conference (ISOCC), Jeju, Republic of Korea.","DOI":"10.1109\/ISOCC.2016.7799849"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Sun, H., Lin, Y., Dai, G., Xia, L., Han, S., Wang, Y., and Yang, H. (2019, January 2\u20136). A configurable multi-precision CNN computing framework based on single bit RRAM. Proceedings of the 2019 56th ACM\/IEEE Design Automation Conference (DAC), Las Vegas, NV, USA.","DOI":"10.1145\/3316781.3317739"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ling, Y., Wang, Z., Yang, Y., Yu, Z., Zheng, Q., Qin, Y., Cai, Y., and Huang, R. (2021, January 8\u201311). A RRAM based Max-Pooling Scheme for Convolutional Neural Network. Proceedings of the 2021 5th IEEE Electron Devices Technology & Manufacturing Conference (EDTM), Chengdu, China.","DOI":"10.1109\/EDTM50988.2021.9421061"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1414","DOI":"10.1109\/TCAD.2019.2917852","article-title":"Low bit-width convolutional neural network on rram","volume":"39","author":"Cai","year":"2019","journal-title":"IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Qu, S., Li, B., Wang, Y., Xu, D., Zhao, X., and Zhang, L. (2020, January 20\u201324). RaQu: An automatic high-utilization CNN quantization and mapping framework for general-purpose RRAM Accelerator. Proceedings of the 2020 57th ACM\/IEEE Design Automation Conference (DAC), San Francisco, CA, USA.","DOI":"10.1109\/DAC18072.2020.9218724"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Liang, Y., Yin, L., and Xu, N. (2020, January 25\u201327). A Field Programmable Process-in-Memory Architecture Based on RRAM Technology. Proceedings of the 2020 5th International Conference on Mechanical, Control and Computer Engineering (ICMCCE), Harbin, China.","DOI":"10.1109\/ICMCCE51767.2020.00502"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Cai, Y., Tang, T., Xia, L., Cheng, M., Zhu, Z., Wang, Y., and Yang, H. (2018, January 22\u201325). Training low bitwidth convolutional neural network on RRAM. Proceedings of the 2018 23rd Asia and South Pacific Design Automation Conference (ASP-DAC), Jeju, Republic of Korea.","DOI":"10.1109\/ASPDAC.2018.8297292"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Xia, L., Tang, T., Huangfu, W., Cheng, M., Yin, X., Li, B., Wang, Y., and Yang, H. (2016, January 5\u20139). Switched by input: Power efficient structure for RRAM-based convolutional neural network. Proceedings of the 53rd Annual Design Automation Conference, Austin, TX, USA.","DOI":"10.1145\/2897937.2898101"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1109\/TCAD.2020.2989373","article-title":"ITT-RNA: Imperfection tolerable training for RRAM-crossbar-based deep neural-network accelerator","volume":"40","author":"Song","year":"2020","journal-title":"IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Tang, S., Yin, S., Zheng, S., Ouyang, P., Tu, F., Yao, L., Wu, J., Cheng, W., Liu, L., and Wei, S. (2017, January 16\u201318). AEPE: An area and power efficient RRAM crossbar-based accelerator for deep CNNs. Proceedings of the 2017 IEEE 6th Non-Volatile Memory Systems and Applications Symposium (NVMSA), Hsinchu, Taiwan.","DOI":"10.1109\/NVMSA.2017.8064475"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Qiu, K., Chen, W., Xu, Y., Xia, L., Wang, Y., and Shao, Z. (2018, January 19\u201323). A peripheral circuit reuse structure integrated with a retimed data flow for low power RRAM crossbar-based CNN. Proceedings of the 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE), Dresden, Germany.","DOI":"10.23919\/DATE.2018.8342168"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1109\/TCAD.2020.2998728","article-title":"Efficient and robust RRAM-based convolutional weight mapping with shifted and duplicated kernel","volume":"40","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Rios, M., Ponzina, F., Ansaloni, G., Levisse, A., and Atienza, D. (2021, January 1\u20135). Running efficiently cnns on the edge thanks to hybrid sram-rram in-memory computing. Proceedings of the 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), Grenoble, France.","DOI":"10.23919\/DATE51398.2021.9474233"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Su, F., Chen, W.H., Xia, L., Lo, C.P., Tang, T., Wang, Z., Hsu, K.H., Cheng, M., Li, J.Y., and Xie, Y. (2017, January 5\u20138). A 462GOPs\/J RRAM-based nonvolatile intelligent processor for energy harvesting IoE system featuring nonvolatile logics and processing-in-memory. Proceedings of the 2017 Symposium on VLSI Technology, Kyoto, Japan.","DOI":"10.23919\/VLSIT.2017.7998149"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Peng, X., Liu, R., and Yu, S. (2019, January 26\u201329). Optimizing weight mapping and data flow for convolutional neural networks on RRAM based processing-in-memory architecture. Proceedings of the 2019 IEEE International Symposium on Circuits and Systems (ISCAS), Sapporo, Japan.","DOI":"10.1109\/ISCAS.2019.8702715"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ni, Y., Chen, W., Cui, W., Zhou, Y., and Qiu, K. (2018, January 19\u201323). Power optimization through peripheral circuit reusing integrated with loop tiling for RRAM crossbar-based CNN. Proceedings of the 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE), Dresden, Germany.","DOI":"10.23919\/DATE.2018.8342193"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Lin, J., Cheng, M., Xia, L., Sun, H., Chen, X., Wang, Y., and Yang, H. (2018, January 5\u20138). Mixed size crossbar based RRAM CNN accelerator with overlapped mapping method. Proceedings of the 2018 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD), San Diego, CA, USA.","DOI":"10.1145\/3240765.3240825"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"7522","DOI":"10.1038\/ncomms8522","article-title":"Associative memory realized by a reconfigurable memristive Hopfield neural network","volume":"6","author":"Hu","year":"2015","journal-title":"Nat. Commun."},{"key":"ref_25","unstructured":"Molter, T., and Nugent, A. (2021, May 22). The Mean Metastable Switch Memristor Model in Xyce\u2013Knowm.org. Available online: https:\/\/knowm.org\/the-mean-metastable-switch-memristor-model-in-xyce\/."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., and Ferrari, V. (2018, January 18\u201323). Coco-stuff: Thing and stuff classes in context. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Miller, N.E., Wang, Z., Dash, S., Khan, A.I., and Mukhopadhyay, S. (2021, January 6\u20139). Characterization of Drain Current Variations in FeFETs for PIM-based DNN Accelerators. Proceedings of the 2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems (AICAS), Washington, DC, USA.","DOI":"10.1109\/AICAS51828.2021.9458437"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Jiao, B., Zhang, J., Xie, Y., Wang, S., Zhu, H., Kang, X., Dong, Z., Zhang, L., and Chen, C. (2021, January 18\u201321). A 0.57-GOPS\/DSP Object Detection PIM Accelerator on FPGA. Proceedings of the 2021 26th Asia and South Pacific Design Automation Conference (ASP-DAC), Tokyo, Japan.","DOI":"10.1145\/3394885.3431659"},{"key":"ref_29","first-page":"1","article-title":"A 40-nm, 2M-cell, 8b-precision, hybrid SLC-MLC PCM computing-in-memory macro with 20.5\u201365.0 TOPS\/W for tiny-Al edge devices","volume":"Volume 65","author":"Khwa","year":"2022","journal-title":"Proceedings of the 2022 IEEE International Solid-State Circuits Conference (ISSCC)"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/5\/2401\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:38:39Z","timestamp":1760121519000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/5\/2401"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,21]]},"references-count":29,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["s23052401"],"URL":"https:\/\/doi.org\/10.3390\/s23052401","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2023,2,21]]}}}