Xingzhi Fu,Qingjiang Li,Weihe Wang,Hui Xu,Yinan Wang,Wei Wang,Hongqi Yu,Zhiwei Li
出处
期刊:IEEE Transactions on Circuits and Systems Ii-express Briefs [Institute of Electrical and Electronics Engineers] 日期:2022-05-11卷期号:69 (9): 3889-3893被引量:5
标识
DOI:10.1109/tcsii.2022.3174219
摘要
Memristor can store calculation results while computing, and utilizing memristor to realize in-memory computing is considered as one of the potential methods to break the bottleneck of Von Neumann architecture. To construct high performance computing systems, it is necessary to design memristor-based computing units with great advantages in delay, area, and integratability. This brief presents a high speed memristor-based $N$ -bit ripple carry adder (RCA), with special design to facilitate the implementation with 1T1R arrays. After carries are calculated and aligned efficiently, we adopt Memristor-Aided LoGIC (MAGIC) to calculate and store the outputs of RCA in parallel, where The proposed $N$ -bit RCA only consists of $5N+1$ memristors, $8N+1$ MOSFETs, and its delay is $N+4$ . Compared with the existing memristive RCA, the proposed RCA has great advantage in delay, while it is easy for integration in 1T1R array.