Compact Write-Based Computing-in-Memory (CIM) using High Speed Switching (HSS) MRAM

被引:0
|
作者
Lu, Yang [1 ]
Wang, Zhi Yuan [1 ]
Yang, Ye Cheng [1 ]
Wang, Shao Hao [1 ]
机构
[1] Fuzhou Univ, Joint Inst Microelect, FZU Jinjiang, Jinjiang Sci & Educ Pk, Jinjiang, Fujian, Peoples R China
来源
2024 9TH INTERNATIONAL CONFERENCE ON ELECTRONIC TECHNOLOGY AND INFORMATION SCIENCE, ICETIS 2024 | 2024年
关键词
computing-in-memory; magnetic RAM; non-volatile memory; full adder;
D O I
10.1109/ICETIS61828.2024.10593750
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Magnetic random-access memory (MRAM)-based computing-in-memory (CIM) schemes can be divided into write-based CIM and read-based CIM. Compared with read-based CIM, the write-based CIM can perform more operations such as AND, OR, majority (MAJ) gate, and full adder (FA). However, write-based CIM schemes require a large number of memory cells and multiple processing cycles. In this paper, we proposed a compact write-based CIM scheme by using a one transistor one high-speed switch magnetic tunnel junction (1T-1HSS-MTJ) memory cell to implement NAND, NOR, XOR, and MAJ gates within two write cycles and one read cycle. Moreover, we also demonstrated that FA operation can also be performed using three 1T-1HSS-MTJ cells within six cycles. According to the simulation results performed using the SMIC 40 nm CMOS process and the HSS-MTJ SPICE model, we have demonstrated that these logic functions can be achieved. When compared to the write-based CIM using SOT-MRAM, the proposed CIM requires fewer cells and shorter latency to achieve the same logic operations.
引用
收藏
页码:666 / 670
页数:5
相关论文
共 20 条
  • [1] An STT-MRAM based reconfigurable computing-in-memory architecture for general purpose computing
    Yu Pan
    Xiaotao Jia
    Zhen Cheng
    Peng Ouyang
    Xueyan Wang
    Jianlei Yang
    Weisheng Zhao
    CCF Transactions on High Performance Computing, 2020, 2 : 272 - 281
  • [2] An STT-MRAM based reconfigurable computing-in-memory architecture for general purpose computing
    Pan, Yu
    Jia, Xiaotao
    Cheng, Zhen
    Ouyang, Peng
    Wang, Xueyan
    Yang, Jianlei
    Zhao, Weisheng
    CCF TRANSACTIONS ON HIGH PERFORMANCE COMPUTING, 2020, 2 (03) : 272 - 281
  • [3] Computing-in-memory using voltage-controlled spin-orbit torque based MRAM array
    Shreya, Sonal
    Jain, Alkesh
    Kaushik, Brajesh Kumar
    MICROELECTRONICS JOURNAL, 2021, 109
  • [4] High-Performance STT-MRAM-Based Computing-in-Memory Scheme Utilizing Data Read Feature
    Wu, Bi
    Liu, Kai
    Yu, Tianyang
    Zhu, Haonan
    Chen, Ke
    Yan, Chenggang
    Deng, Erya
    Liu, Weiqiang
    IEEE TRANSACTIONS ON NANOTECHNOLOGY, 2023, 22 : 817 - 826
  • [5] A CFMB STT-MRAM-Based Computing-in-Memory Proposal With Cascade Computing Unit for Edge AI Devices
    Zhou, Yongliang
    Zhou, Zixuan
    Wei, Yiming
    Yang, Zhen
    Lin, Xiao
    Dai, Chenghu
    Hao, Licai
    Peng, Chunyu
    Cai, Hao
    Wu, Xiulong
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2024, 71 (01) : 187 - 200
  • [6] Accuracy Improvement With Weight Mapping Strategy and Output Transformation for STT-MRAM-Based Computing-in-Memory
    Wang, Xianggao
    Wei, Na
    Gao, Shifan
    Wu, Wenhao
    Zhao, Yi
    IEEE JOURNAL ON EXPLORATORY SOLID-STATE COMPUTATIONAL DEVICES AND CIRCUITS, 2024, 10 : 75 - 81
  • [7] An Energy-Efficient Computing-in-Memory (CiM) Scheme Using Field-Free Spin-Orbit Torque (SOT) Magnetic RAMs
    Wu, Bi
    Zhu, Haonan
    Reis, Dayane
    Wang, Zhaohao
    Wang, Ying
    Chen, Ke
    Liu, Weiqiang
    Lombardi, Fabrizio
    Hu, Xiaobo Sharon
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING, 2023, 11 (02) : 331 - 342
  • [8] A 129.83 TOPS/W Area Efficient Digital SOT/STT MRAM-Based Computing-In-Memory for Advanced Edge AI Chips
    Lu, Lu
    Mani, Aarthy
    Anh Tuan Do
    2023 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, ISCAS, 2023,
  • [9] Flash-Based Computing-in-Memory Architecture to Implement High-Precision Sparse Coding
    Qi, Yueran
    Feng, Yang
    Wang, Hai
    Wang, Chengcheng
    Bai, Maoying
    Liu, Jing
    Zhan, Xuepeng
    Wu, Jixuan
    Wang, Qianwen
    Chen, Jiezhi
    MICROMACHINES, 2023, 14 (12)
  • [10] High-performance Sum Operation with Charge Saving and Sharing Circuit for MRAM-based In-memory Computing
    Yu, Jangseok
    Lee, Geonwoo
    Na, Taehui
    JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE, 2024, 24 (02) : 111 - 121