• 中国精品科技期刊
  • CCF推荐A类中文期刊
  • 计算领域高质量科技期刊T1类
Advanced Search
Mao Haiyu, Shu Jiwu. 3D Memristor Array Based Neural Network Processing in Memory Architecture[J]. Journal of Computer Research and Development, 2019, 56(6): 1149-1160. DOI: 10.7544/issn1000-1239.2019.20190099
Citation: Mao Haiyu, Shu Jiwu. 3D Memristor Array Based Neural Network Processing in Memory Architecture[J]. Journal of Computer Research and Development, 2019, 56(6): 1149-1160. DOI: 10.7544/issn1000-1239.2019.20190099

3D Memristor Array Based Neural Network Processing in Memory Architecture

Funds: This work was supported by the National Key Research and Development Program of China (2018YFB1003301) and the National Natural Science Foundation of China (61832011).
More Information
  • Published Date: May 31, 2019
  • Nowadays, due to the rapid development of artificial intelligence, the memristor-based processing in memory (PIM) architecture for neural network (NN) attracts a lot of researchers’ interests since it performs much better than traditional von Neumann architecture. Equipped with the peripheral circuit to support function units, memristor arrays can process a forward propagation with higher parallelism and much less data movement than that in CPU and GPU. However, the hardware of the memristor-based PIM suffers from the large area overhead of peripheral circuit outside the memristor array and non-trivial under-utilization of function units. This paper proposes a 3D memristor array based PIM architecture for NNs (FMC) by gathering the peripheral circuit of function units into a function pool for sharing among memristor arrays that pile up on the pool. We also propose a data mapping scheme for the 3D memristor array based PIM architecture to further increase the utilization of function units and reduce the data transmission among different cubes. The software-hardware co-design for the 3D memristor array based PIM not only makes the most of function units but also shortens the wire interconnections for better high-performance and energy-efficient data transmission. Experiments show that when training a single neural network, our proposed FMC can achieve up to 43.33 times utilization of the function units and can achieve up to 58.51 times utilization of the function units when training multiple neural networks. At the same time, compared with the 2D-PIM which has the same amount of compute array and storage array, FMC only occupies 42.89% area of 2D-PIM. What’s more, FMC has 1.5 times speedup and 1.7 times energy saving compared with 2D-PIM.
  • Related Articles

    [1]He Renhua, Li Bing, Du Yibo, Wang Ying, Li Xiaowei, Han Yinhe. A Survey on Algorithm and Hardware Optimization to LWE-Based Fully Homomorphic Encryption[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202331022
    [2]Bai Lifang, Zhu Yuefei, Li Yongjun, Wang Shuai, Yang Xiaoqi. Research Progress of Fully Homomorphic Encryption[J]. Journal of Computer Research and Development, 2024, 61(12): 3069-3087. DOI: 10.7544/issn1000-1239.202221052
    [3]Zhao Xiufeng, Fu Yu, Song Weitao. Circular Secure Homomorphic Encryption Scheme[J]. Journal of Computer Research and Development, 2020, 57(10): 2117-2124. DOI: 10.7544/issn1000-1239.2020.20200422
    [4]Xu Ming, Fan Yimeng, Jiang Changjun. Time-Varying Underwater Acoustic Channel Based Physical Layer Secret Key Generation Scheme[J]. Journal of Computer Research and Development, 2019, 56(12): 2660-2670. DOI: 10.7544/issn1000-1239.2019.20190040
    [5]Ye Qing, Hu Mingxing, Tang Yongli, Liu Kun, Yan Xixi. Efficient Hierarchical Identity-Based Encryption Scheme from Learning with Errors[J]. Journal of Computer Research and Development, 2017, 54(10): 2193-2204. DOI: 10.7544/issn1000-1239.2017.20170394
    [6]Chen Zhigang, Song Xinxia, Zhao Xiufeng. A Multi-Bit Fully Homomorphic Encryption with Better Key Size from LWE[J]. Journal of Computer Research and Development, 2016, 53(10): 2216-2223. DOI: 10.7544/issn1000-1239.2016.20160431
    [7]Fu Wei, Wu Xiaoping, Ye Qing, Xiao Nong, Lu Xicheng. A Multiple Replica Possession Proving Scheme Based on Public Key Partition[J]. Journal of Computer Research and Development, 2015, 52(7): 1672-1681. DOI: 10.7544/issn1000-1239.2015.20140353
    [8]Liu Mingjie, Wang An. Fully Homomorphic Encryption and Its Applications[J]. Journal of Computer Research and Development, 2014, 51(12): 2593-2603. DOI: 10.7544/issn1000-1239.2014.20131168
    [9]Yang Xiaoyuan, Cai Weiyi, Chen Haibin. Multiple-Authority-Key Functional Encryption: A M-KP-ABE Scheme Based on LMSSS[J]. Journal of Computer Research and Development, 2011, 48(8): 1363-1369.
    [10]Tian Junfeng, Jiao Hongqiang, Li Ning, and Liu Tao. Double Secret Keys and Double Random Numbers Authentication Scheme[J]. Journal of Computer Research and Development, 2008, 45(5): 779-785.
  • Cited by

    Periodical cited type(4)

    1. 张黎,骆春山,谢委员,李蓓蓓. 基于分支混淆算法的隐私数据库自适应加密方法. 计算机与现代化. 2022(03): 43-47 .
    2. 赵武清,王甜,耿新. 基于同态加密的电力业务数据安全研究. 微型电脑应用. 2021(06): 113-116 .
    3. 韩舒艳,努尔买买提·黑力力. 选择性隐藏树型访问结构的CP-ABE方案. 计算机工程. 2020(07): 150-158 .
    4. 刘建华,郑晓坤,郑东,敖章衡. 基于属性加密且支持密文检索的安全云存储系统. 信息网络安全. 2019(07): 50-58 .

    Other cited types(0)

Catalog

    Article views (1573) PDF downloads (760) Cited by(4)

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return