skip to main content
10.1145/3566097.3567862acmconferencesArticle/Chapter ViewAbstractPublication PagesaspdacConference Proceedingsconference-collections
research-article

Accelerating Convolutional Neural Networks in Frequency Domain via Kernel-Sharing Approach

Published: 31 January 2023 Publication History

Abstract

Convolutional neural networks (CNNs) are typically computationally heavy. Fast algorithms such as fast Fourier transforms (FFTs), are promising in significantly reducing computation complexity by replacing convolutions with frequency-domain element-wise multiplication. However, the increased high memory access overhead of complex weights counteracts the computing benefit, because frequency-domain convolutions not only pad weights to the same size as input maps, but also have no sharable complex kernel weights. In this work, we propose an FFT-based kernel-sharing technique called FS-Conv to reduce memory access. Based on FS-Conv, we derive the sharable complex weights in frequency-domain convolutions, which has never been solved. FS-Conv includes a hybrid padding approach, which utilizes the inherent periodic characteristic of FFT transformation to provide sharable complex weights for different blocks of complex input maps. We in addition build a frequency-domain inference accelerator (called Yixin) that can utilize the sharable complex weights for CNN accelerations. Evaluation results demonstrate the significant performance and energy efficiency benefits compared with the state-of-the-art baseline.

References

[1]
A. Antoniou. 2006. Digital signal processing. McGraw-Hill Toronto, Canada.
[2]
Yu-Hsin Chen et al. 2016. Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks. JSSC (2016), 127--138.
[3]
James W Cooley et al. 1965. An algorithm for the machine calculation of complex Fourier series. Mathematics of computation 19, 90 (1965), 297--301.
[4]
Jia Deng et al. 2009. Imagenet: A large-scale hierarchical image database. In CVPR. 248--255.
[5]
Kaiming He et al. 2016. Deep residual learning for image recognition. In CVPR. 770--778.
[6]
Jong Hwan Ko et al. 2017. Design of an energy-efficient accelerator for training of convolutional neural networks using frequency-domain computation. In DAC. 1--6.
[7]
Alex Krizhevsky, Geoffrey Hinton, et al. 2009. Learning multiple layers of features from tiny images. (2009).
[8]
B. Liu et al. 2021. F3D: Accelerating 3D Convolutional Neural Networks in Frequency Space Using ReRAM. In DAC. 571--576.
[9]
Zhenhua Liu et al. 2018. Frequency-domain dynamic pruning for convolutional neural networks. In NeurIPS. 1051--1061.
[10]
Richard G Lyons. 2004. Understanding digital signal processing, 3/E. Pearson Education India.
[11]
M. Mathieu et al. 2014. Fast training of convolutional networks through ffts. In ICLR.
[12]
Muralimanohar et al. 2009. CACTI 6.0: A tool to model large caches. HP laboratories 27 (2009), 28.
[13]
Ananda Samajdar et al. 2018. Scale-sim: Systolic cnn accelerator simulator. arXiv preprint arXiv:1811.02883 (2018).
[14]
K. Simonyan et al. 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014).
[15]
S. Wen et al. 2019. Variational Autoencoder based Image Compression with Pyramidal Features and Context Entropy Model. In CVPR Workshops. 0.
[16]
J. Yang et al. 2019. Quantization networks. In CVPR. 7308--7316.

Index Terms

  1. Accelerating Convolutional Neural Networks in Frequency Domain via Kernel-Sharing Approach

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    ASPDAC '23: Proceedings of the 28th Asia and South Pacific Design Automation Conference
    January 2023
    807 pages
    ISBN:9781450397834
    DOI:10.1145/3566097
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Sponsors

    In-Cooperation

    • IPSJ
    • IEEE CAS
    • IEEE CEDA
    • IEICE

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 31 January 2023

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. acceleration
    2. frequency-domain DNN architecture

    Qualifiers

    • Research-article

    Funding Sources

    • National Natural Science Foundation of China
    • State Key Laboratory of Computer Architecture (ICT,CAS)
    • Guangzhou Basic and Applied Basic Research Foundation

    Conference

    ASPDAC '23
    Sponsor:

    Acceptance Rates

    ASPDAC '23 Paper Acceptance Rate 102 of 328 submissions, 31%;
    Overall Acceptance Rate 466 of 1,454 submissions, 32%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 118
      Total Downloads
    • Downloads (Last 12 months)35
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 14 Feb 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media