Energy efficiency optimization of FPGA-based CNN accelerators with full data reuse and VFS

Weixiong Jiang, Heng Yu, Xinzhe Liu, Yajun Ha

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

While FPGA has been recognized as a promising platform to accelerate Convolutional Neural Networks (CNNs) in embedded computing given its high flexibility and power efficiency, two challenges still have to be addressed to enhance its applicability on the edge-computing paradigm. First, the power and performance of the CNN accelerator are still bounded by memory throughput, and a CNN-customized architecture is desirable to fully utilize the on-chip storage. Second, power optimization algorithms are insufficiently explored on CNN-targeted platforms. In this paper, we design a novel FPGA-based CNN accelerator architecture that makes full use of the on-chip storage resources leveraging data reuse and loop unrolling strategies. We also present an efficient FPGA-based voltage and frequency scaling (VFS) system that enables VFS of the CNN accelerator for power optimization. We devise a VFS policy that fully exploits the power efficiency potential of the FPGA. Experiment results show up to 40% energy can be saved with our VFS platform and policy.

Original languageEnglish
Title of host publication2019 26th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages446-449
Number of pages4
ISBN (Electronic)9781728109961
DOIs
Publication statusPublished - Nov 2019
Event26th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2019 - Genoa, Italy
Duration: 27 Nov 201929 Nov 2019

Publication series

Name2019 26th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2019

Conference

Conference26th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2019
Country/TerritoryItaly
CityGenoa
Period27/11/1929/11/19

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Optimization
  • Computer Networks and Communications
  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'Energy efficiency optimization of FPGA-based CNN accelerators with full data reuse and VFS'. Together they form a unique fingerprint.

Cite this