Reconfigurable Bit-Serial Operation Using Toggle SOT-MRAM for High-Performance Computing in Memory Architecture

被引:15
|
作者
Wang, Jinkai [1 ,2 ]
Bai, Yining [3 ]
Wang, Hongyu [3 ]
Hao, Zuolei [3 ]
Wang, Guanda [3 ]
Zhang, Kun [3 ]
Zhang, Youguang [3 ]
Lv, Weifeng [4 ,5 ]
Zhang, Yue [3 ,6 ]
机构
[1] Beihang Univ, Fert Beijing Inst, Sch Comp Sci & Engn, State Key Lab Software Dev Environm, Beijing 100191, Peoples R China
[2] Beihang Univ, Fert Beijing Inst, Sch Comp Sci & Engn, MIIT Key Lab Spintron, Beijing 100191, Peoples R China
[3] Beihang Univ, Fert Beijing Inst, Sch Integrated Circuit Sci & Engn, MIIT Key Lab Spintron, Beijing 100191, Peoples R China
[4] Beihang Univ, Sch Comp Sci & Engn, State Key Lab Software Dev Environm, Beijing 100191, Peoples R China
[5] Beihang Univ, Res Inst, Shenzhen Key Lab Data Vitalizat Smart City, Shenzhen 518057, Peoples R China
[6] Beihang Univ, Hefei Innovat Res Inst, Nanoelect Sci & Technol Ctr, Hefei 230013, Peoples R China
基金
中国国家自然科学基金;
关键词
Computing in memory; bit-serial operation; toggle spin-orbit torque MRAM; convolution operation; digital CIM architectures; UNIT-MACRO; SRAM; EFFICIENT; ENERGY; COMPUTATION; ENGINE;
D O I
10.1109/TCSI.2022.3192165
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Computing in memory (CIM) is a promising candidate for high throughput and energy-efficient data-driven applications, which mitigates the well-known memory bottleneck in Von Neumann architecture. In this paper, we present a reconfigurable bit-serial operation using toggle spin-orbit torque magnetic random access memory (TSOT-MRAM) to perform the computation completely in the bit-cell array instead of in a peripheral circuit. This bit-serial CIM (BSCIM) scheme achieves higher throughput and energy efficiency in CIM. First, basic Boolean logic operations are realized by utilizing the feature of TSOT device. A bit-cell array that implements the bit-serial operation is then built to provide the communication between column and row necessary for arithmetic operations, such as the carry propagation of addition and multiplication. Finally, we analyze the reliability of BSCIM scheme and demonstrate the performance advantage by performing convolution operations for 28 x 28 handwritten digit images in a BSCIM architecture. The results show that the delay and energy of BSCIM architecture are respectively reduced by 1.16-5.49 times and 1.12-1.43 times compared with the existing digital CIM architectures. Besides, its throughput and energy efficiency are also enhanced to 51.2 GOPS and 9.9 TOPS/W respectively.
引用
收藏
页码:4535 / 4545
页数:11
相关论文
共 50 条
  • [1] High Performance and Energy-Efficient In-Memory Computing Architecture based on SOT-MRAM
    He, Zhezhi
    Angizi, Shaahin
    Parveen, Farhana
    Fan, Deliang
    [J]. PROCEEDINGS OF THE IEEE/ACM INTERNATIONAL SYMPOSIUM ON NANOSCALE ARCHITECTURES (NANOARCH 2017), 2017, : 97 - 102
  • [2] High-Performance in-memory Logic Scheme using Unipolar Switching SOT-MRAM
    Zhu, Haonan
    Wu, Bi
    Chen, Ke
    Yan, Chenggang
    Liu, Weiqiang
    [J]. 2022 IEEE 22ND INTERNATIONAL CONFERENCE ON NANOTECHNOLOGY (NANO), 2022, : 112 - 115
  • [3] A Potential Enabler for High-Performance In-Memory Multi-Bit Arithmetic Schemes With Unipolar Switching SOT-MRAM
    Zhu, Haonan
    Wu, Bi
    Yu, Tianyang
    Chen, Ke
    Yan, Chenggang
    Liu, Weiqiang
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2024, 71 (07) : 3165 - 3178
  • [4] MLiM: High-Performance Magnetic Logic in-Memory Scheme With Unipolar Switching SOT-MRAM
    Wu, Bi
    Zhu, Haonan
    Chen, Ke
    Yan, Chenggang
    Liu, Weiqiang
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2023, 70 (06) : 2412 - 2424
  • [5] HIGH-PERFORMANCE BIT-SERIAL ADDERS AND MULTIPLIERS
    BI, G
    JONES, EV
    [J]. IEE PROCEEDINGS-G CIRCUITS DEVICES AND SYSTEMS, 1992, 139 (01): : 109 - 113
  • [6] System and Design Technology Co-Optimization of SOT-MRAM for High-Performance AI Accelerator Memory System
    Mishty, Kaniz
    Sadi, Mehdi
    [J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2024, 43 (04) : 1065 - 1078
  • [7] A High-Performance Reconfigurable Computing Architecture using a Magnetic Configuration Memory
    Silva, Victor
    Fernandes, Jorge R.
    Vestias, Mario P.
    Neto, Horacio C.
    [J]. 2012 INTERNATIONAL CONFERENCE ON RECONFIGURABLE COMPUTING AND FPGAS (RECONFIG), 2012,
  • [8] A 6T-3M SOT-MRAM for in-memory computing with reconfigurable arith- metic operations
    Jin, Xing
    Yin, Ningyuan
    Chen, Weichong
    Li, Ximing
    Zhao, Guihua
    Yu, Zhiyi
    [J]. IEICE ELECTRONICS EXPRESS, 2023, 20 (11):
  • [9] Computing-in-Memory Architecture based on Field-Free SOT-MRAM with Self-Reference Method
    Wang, Chao
    Wang, Zhaohao
    Xu, Yansong
    Yang, Jianlei
    Zhang, Youguang
    Zhao, Weisheng
    [J]. 2020 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2020,
  • [10] Improving Memory Access Locality for Vectorized Bit-serial Matrix Multiplication in Reconfigurable Computing
    Rasnayake, Lahiru
    Sjalander, Magnus
    [J]. 2019 INTERNATIONAL CONFERENCE ON FIELD-PROGRAMMABLE TECHNOLOGY (ICFPT 2019), 2019, : 415 - 418