CSCNN: Algorithm-hardware Co-design for CNN Accelerators using Centrosymmetric Filters

Jiajun Li, Ahmed Louri, Avinash Karanth, Razvan Bunescu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Scopus citations

Abstract

Convolutional neural networks (CNNs) are at the core of many state-of-The-Art deep learning models in computer vision, speech, and text processing. Training and deploying such CNN-based architectures usually require a significant amount of computational resources. Sparsity has emerged as an effective compression approach for reducing the amount of data and computation for CNNs. However, sparsity often results in computational irregularity, which prevents accelerators from fully taking advantage of its benefits for performance and energy improvement. In this paper, we propose CSCNN, an algorithm/hardware co-design framework for CNN compression and acceleration that mitigates the effects of computational irregularity and provides better performance and energy efficiency. On the algorithmic side, CSCNN uses centrosymmetric matrices as convolutional filters. In doing so, it reduces the number of required weights by nearly 50% and enables structured computational reuse without compromising regularity and accuracy. Additionally, complementary pruning techniques are leveraged to further reduce computation by a factor of 2.8-7.2\times with a marginal accuracy loss. On the hardware side, we propose a CSCNN accelerator that effectively exploits the structured computational reuse enabled by centrosymmetric filters, and further eliminates zero computations for increased performance and energy efficiency. Compared against a dense accelerator, SCNN and SparTen, the proposed accelerator performs 3.7\times , 1.6\times and 1.3\times better, and improves the EDP (Energy Delay Product) by 8.9\times , 2.8\times and 2.0\times , respectively.

Original languageEnglish (US)
Title of host publicationProceeding - 27th IEEE International Symposium on High Performance Computer Architecture, HPCA 2021
PublisherIEEE Computer Society
Pages612-625
Number of pages14
ISBN (Electronic)9780738123370
DOIs
StatePublished - Feb 2021
Event27th Annual IEEE International Symposium on High Performance Computer Architecture, HPCA 2021 - Virtual, Seoul, Korea, Republic of
Duration: Feb 27 2021Mar 1 2021

Publication series

NameProceedings - International Symposium on High-Performance Computer Architecture
Volume2021-February
ISSN (Print)1530-0897

Conference

Conference27th Annual IEEE International Symposium on High Performance Computer Architecture, HPCA 2021
Country/TerritoryKorea, Republic of
CityVirtual, Seoul
Period2/27/213/1/21

Keywords

  • Convolutional Neural Networks
  • Domain-specific Accelerators

ASJC Scopus subject areas

  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'CSCNN: Algorithm-hardware Co-design for CNN Accelerators using Centrosymmetric Filters'. Together they form a unique fingerprint.

Cite this