Magnetic Random-Access Memory-Based Approximate Computing: An Overview

被引:2
作者
Wang, You [1 ]
Zhang, Kaili [2 ]
Wu, Bo [2 ]
Zhang, Deming [2 ]
Zhao, Weisheng [2 ]
Cai, Hao [3 ]
机构
[1] Beihang Univ, Hefei Innovat Res Inst, Anhui High Reliabil Chips Engn Lab, Hefei 230013, Peoples R China
[2] Beihang Univ, Sch Integrated Circuit Sci & Engn, Beijing 100191, Peoples R China
[3] Southeast Univ, Sch Elect Sci & Engn, Nanjing 210096, Peoples R China
基金
国家重点研发计划;
关键词
Switches; Resistance; Delays; Writing; Magnetic tunneling; Approximate computing; Voltage; COMPACT MODEL;
D O I
10.1109/MNANO.2021.3126093
中图分类号
TB3 [工程材料学];
学科分类号
0805 ; 080502 ;
摘要
This article presents an overview of the recent developments in the magnetic random access memory (MRAM) for approximate computing. The key technique of approximate computing is to trade off limited accuracy for improvements in other metrics, such as speed, power, and area. With intrinsic current-induced threshold operation and random process variation, MRAM is regarded as a promising candidate for approximate computing. Beginning with the background of approximate computing, this article reviews prior design techniques at the circuit level and recent development trends. Then the physical mechanisms of randomness in MRAM are detailed. Several designs based on MRAM are comprehensively studied and compared in terms of performance. Finally, an outline of possible challenges and future research directions are given. © 2007-2011 IEEE.
引用
收藏
页码:25 / 32
页数:8
相关论文
共 31 条
[1]   Circuit-Level Techniques for Logic and Memory Blocks in Approximate Computing Systemsx [J].
Amanollahi, Saba ;
Kamal, Mehdi ;
Afzali-Kusha, Ali ;
Pedram, Massoud .
PROCEEDINGS OF THE IEEE, 2020, 108 (12) :2150-2177
[2]   Robust Ultra-Low Power Non-Volatile Logic-in-Memory Circuits in FD-SOI Technology [J].
Cai, Hao ;
Wang, You ;
De Barros, Lirida Alves ;
Zhao, Weisheng .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2017, 64 (04) :847-857
[3]   Ultra low-voltage low-power CMOS 4-2 and 5-2 compressors for fast arithmetic circuits [J].
Chang, CH ;
Gu, JM ;
Zhang, MY .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2004, 51 (10) :1985-1997
[4]   Synchronous 8-bit Non-Volatile Full-Adder based on Spin Transfer Torque Magnetic Tunnel Junction [J].
Deng, Erya ;
Zhang, Yue ;
Kang, Wang ;
Dieny, Bernard ;
Klein, Jacques-Olivier ;
Prenat, Guillaume ;
Zhao, Weisheng .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2015, 62 (07) :1757-1765
[5]  
Dutt N.., P 2017 ACM IEEE INT, P1, DOI [10.1109/ISLPED.2017.8009198, DOI 10.1109/ISLPED.2017.8009198]
[6]   An Overview of Nonvolatile Emerging Memories-Spintronics for Working Memories [J].
Endoh, Tetsuo ;
Koike, Hiroki ;
Ikeda, Shoji ;
Hanyu, Takahiro ;
Ohno, Hideo .
IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS, 2016, 6 (02) :109-119
[7]   Spin-Transfer Torque Memories: Devices, Circuits, and Systems [J].
Fong, Xuanyao ;
Kim, Yusung ;
Venkatesan, Rangharajan ;
Choday, Sri Harsha ;
Raghunathan, Anand ;
Roy, Kaushik .
PROCEEDINGS OF THE IEEE, 2016, 104 (07) :1449-1488
[8]  
Gupta V., 2011, 2011 International Symposium on Low Power Electronics and Design (ISLPED 2011), P409, DOI 10.1109/ISLPED.2011.5993675
[9]   Low-Power Digital Signal Processing Using Approximate Adders [J].
Gupta, Vaibhav ;
Mohapatra, Debabrata ;
Raghunathan, Anand ;
Roy, Kaushik .
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2013, 32 (01) :124-137
[10]   Validity of the thermal activation model for spin-transfer torque switching in magnetic tunnel junctions [J].
Heindl, R. ;
Rippard, W. H. ;
Russek, S. E. ;
Pufall, M. R. ;
Kos, A. B. .
JOURNAL OF APPLIED PHYSICS, 2011, 109 (07)