https://scholars.lib.ntu.edu.tw/handle/123456789/611194
標題: | A 7.8-13.6 pJ/b Ultra-Low latency and reconfigurable neural network-assisted polar decoder with multi-code length support | 作者: | AN-YEU(ANDY) WU | 關鍵字: | Belief propagation; Multi-code length support; Neural network; Polar codes; Reconfigurable architecture | 公開日期: | 2021 | 卷: | 68 | 期: | 5 | 起(迄)頁: | 1956-1965 | 來源出版物: | IEEE Transactions on Circuits and Systems I: Regular Papers | 摘要: | Polar codes have been officially selected as the channel coding in 5G standard. To meet the requirements of enhanced mobile broadband (eMBB), most published polar decoder chips aim to improve throughput rate and error-correction performance. However, to meet with the requirements of another two 5G new radio (NR) application scenarios, ultra-reliable low-latency communications (URLLC), and massive machine-type communications (mMTC), the design features of low latency and energy efficiency are also desirable. In this article, we present a 7.8-13.6 pJ/b ultra-low latency and energy-efficient polar decoder fabricated in 40nm CMOS technology. By adopting the decoding algorithm of recurrent neural network-assisted belief propagation (RNN-BP), the learned scaling parameters can improve the convergence rate by 8 times with reasonable hardware and memory overhead. Then, by taking advantage of BP's regular structure, we propose a fully-reconfigurable RNN-BP decoder architecture to support multiple code lengths with negligible hardware complexity. It contributes to 2-8× improved hardware utilization rate while providing a flexible adjustment between throughput and error-correction performance. At the architectural level, two optimization techniques for the design of the processing element (PE) are proposed to jointly reduce the chip's area and power by 73% and 67%, respectively. From the measurement results, our reconfigurable RNN-BP polar decoder chip has 2.3×, 2.3×, and 10.0× enhancement over prior designs in terms of latency, throughput rate, and energy efficiency. Consequently, our reconfigurable design has great potential to meet various 5G NR applications. © 2004-2012 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85102264469&doi=10.1109%2fTCSI.2021.3060585&partnerID=40&md5=f14a0c1cac632f43d7b5b12bf0721d7d https://scholars.lib.ntu.edu.tw/handle/123456789/611194 |
ISSN: | 15498328 | DOI: | 10.1109/TCSI.2021.3060585 | SDG/關鍵字: | 5G mobile communication systems; Backpropagation; Computer hardware; Decoding; Energy efficiency; Error correction; Network coding; Reconfigurable architectures; Application scenario; Architectural levels; Correction performance; Hardware utilization; Low-latency communication; Machine type communications; Optimization techniques; Reconfigurable designs; Recurrent neural networks |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。