A temperature and process compensation circuit for resistive-based in-memory computing arrays

被引:3
|
作者
Monga, Dipesh C. [1 ]
Numan, Omar [1 ]
Andraud, Martin [1 ]
Halonen, Kari [1 ]
机构
[1] Aalto Univ, Sch Elect Engn, Dept Elect & Nanoengn, Espoo, Finland
基金
芬兰科学院;
关键词
Thermal compensation; process compensation; ultra-low power; variable temperature coefficient; In-memory computing; Resistive random access memory;
D O I
10.1109/ISCAS46773.2023.10181619
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In-Memory Computing (IMC) architectures promise increased energy-efficiency for embedded artificial intelligence. Many IMC circuits rely on analog computation, which is more sensitive to process and temperature variations than digital. Thus, maintaining a suitable computation accuracy may require process and temperature compensation. Focusing on resistive-based IMC architectures, we propose an ultra-low power circuit to compensate for the temperature and process-based non-linearities of resistive computing elements. The proposed circuit, implemented in 65 nm CMOS can provide a temperature coefficient between 10 and 1938 ppm/degrees C for a wide temperature range (-40 degrees C to 80 degrees C) and output current range (few pA up to 600 nA) at 1.2 V operating voltage. Used in a resistive IMC array, the variation of output currents from each multiply-accumulate (MAC) operation can be reduced by up to 84% to maintain computation accuracy across process and temperature variations.
引用
收藏
页数:5
相关论文
共 50 条
  • [41] Impact of Aging and Process Variability on SRAM-Based In-Memory Computing Architectures
    Shaik, Jani Babu
    Guo, Xinfei
    Singhal, Sonal
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2024, 71 (06) : 2696 - 2708
  • [42] On the Reliability of In-Memory Computing: Impact of Temperature on Ferroelectric TCAM
    Thomann, Simon
    Li, Chao
    Zhuo, Cheng
    Prakash, Om
    Yin, Xunzhao
    Hu, Xiaobo Sharon
    Amrouch, Hussam
    2021 IEEE 39TH VLSI TEST SYMPOSIUM (VTS), 2021,
  • [43] Temperature-Resilient RRAM-Based In-Memory Computing for DNN Inference
    Meng, Jian
    Shim, Wonbo
    Yang, Li
    Yeo, Injune
    Fan, Deliang
    Yu, Shimeng
    Seo, Jae-sun
    IEEE MICRO, 2022, 42 (01) : 89 - 98
  • [44] A linear compensation method for inference accuracy improvement of memristive in-memory computing
    Dai, Yuehua
    Wang, Zeqing
    Feng, Zhe
    Zou, Jianxun
    Guo, Wenbin
    Tan, Su
    Yu, Ruihan
    Hu, Yang
    Qian, Zhibin
    Hu, Junliang
    Xu, Zuyu
    Zhu, Yunlai
    Wu, Zuheng
    NANOTECHNOLOGY, 2024, 35 (47)
  • [45] Energy-Accuracy Trade-Offs for Resistive In-Memory Computing Architectures
    Roy, Saion K.
    Shanbhag, Naresh R.
    IEEE JOURNAL ON EXPLORATORY SOLID-STATE COMPUTATIONAL DEVICES AND CIRCUITS, 2024, 10 : 22 - 30
  • [46] An energy-efficient in-memory computing architecture for survival data analysis based on resistive switching memories
    Baroni, Andrea
    Glukhov, Artem
    Perez, Eduardo
    Wenger, Christian
    Calore, Enrico
    Schifano, Sebastiano Fabio
    Olivo, Piero
    Ielmini, Daniele
    Zambelli, Cristian
    FRONTIERS IN NEUROSCIENCE, 2022, 16
  • [47] Eliminating Capacitive Sneak Paths in Associative Capacitive Networks based on Complementary Resistive Switches for In-Memory Computing
    Ziegler, Tobias
    Brackmann, Leon
    Hennen, Tyler
    Bengel, Christopher
    Menzel, Stephan
    Wouters, Dirk J.
    2023 IEEE INTERNATIONAL MEMORY WORKSHOP, IMW, 2023, : 49 - 52
  • [48] In-memory search with learning to hash based on resistive memory for recommendation acceleration
    Fei Wang
    Woyu Zhang
    Zhi Li
    Ning Lin
    Rui Bao
    Xiaoxin Xu
    Chunmeng Dou
    Zhongrui Wang
    Dashan Shang
    npj Unconventional Computing, 1 (1):
  • [49] Optimization of Multi-Level Operation in RRAM Arrays for In-Memory Computing
    Perez, Eduardo
    Perez-avila, Antonio Javier
    Romero-Zaliz, Rocio
    Mahadevaiah, Mamathamba Kalishettyhalli
    Perez-Bosch Quesada, Emilio
    Roldan, Juan Bautista
    Jimenez-Molinos, Francisco
    Wenger, Christian
    ELECTRONICS, 2021, 10 (09)
  • [50] A Crossbar-Based In-Memory Computing Architecture
    Wang, Xinxin
    Zidan, Mohammed A.
    Lu, Wei D.
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2020, 67 (12) : 4224 - 4232