A Digital SRAM Computing-in-Memory Design Utilizing Activation Unstructured Sparsity for High-Efficient DNN Inference

被引：1
|
作者：
Zhong, Baiqing [1 ]
Wang, Mingyu [1 ]
Zhang, Chuanghao [1 ]
Mai, Yangzhan [1 ]
Li, Xiaojie [1 ]
Yu, Zhiyi [1 ]
机构：
[1] Sun Yat Sen Univ, Sch Microelect Sci & Technol, Guangzhou, Peoples R China
来源：
2023 IEEE COMPUTER SOCIETY ANNUAL SYMPOSIUM ON VLSI, ISVLSI | 2023年
基金：
中国国家自然科学基金;
关键词：
Compute-In-Memory; SRAM; Sparsity; Booth-encode; DNN; MACRO;
D O I：
10.1109/ISVLSI59464.2023.10238597
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
引用
收藏
页码：7 / 12
页数：6
相关论文
共 5 条
  • [1] OASIS: A 28-nm 32-kb SRAM-Based Computing-in-Memory Design With Output Activation Sparsity Support
    Guo, Qingyu
    Pan, Nanbing
    Qiao, Xin
    Cui, Xiaoxin
    Wang, Yuan
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2024, 71 (04) : 1899 - 1903
  • [2] Design of Computing-in-Memory (CIM) with Vertical Split-Gate Flash Memory for Deep Neural Network (DNN) Inference Accelerator
    Lue, Hang-Ting
    Hu, Han-Wen
    Hsu, Tzu-Hsuan
    Hsu, Po-Kai
    Wang, Keh-Chung
    Lu, Chih-Yuan
    2021 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2021,
  • [3] LSAC: A Low-Power Adder Tree for Digital Computing-in-Memory by Sparsity and Approximate Circuits Co-Design
    He, Chaojie
    Wang, Zi
    Xiang, Feibin
    Dai, Zhuoyu
    He, Yifan
    Yue, Jinshan
    Liu, Yongpan
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2024, 71 (02) : 852 - 856
  • [4] A High-Throughput Energy-Area-Efficient Computing-in-Memory SRAM Using Unified Charge-Processing Network
    Hsu, Ying-Tuan
    Yao, Chun-Yen
    Wu, Tsung-Yen
    Chiueh, Tzi-Dar
    Liu, Tsung-Te
    IEEE SOLID-STATE CIRCUITS LETTERS, 2021, 4 : 146 - 149
  • [5] A negative capacitance FET based energy efficient 6T SRAM computing-in-memory (CiM) cell design for deep neural networks
    Birudu, Venu
    Yellampalli, Siva Sankar
    Vaddi, Ramesh
    MICROELECTRONICS JOURNAL, 2023, 139
1