A Flexible DNN Accelerator Design with Layer Pipeline for FPGAs

Weijie You, Deming Chen, Chang Wu

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

Abstract

Deep Neural Networks (DNNs) are very effective for image recognition, object detection and tracking. To meet the need of deployment of DNNs, accelerator designs have been proposed, especially for implementation on FPGAs. Layer pipeline is a new technology to improve computation efficiency by reducing latency between layers. In this paper, we propose a group-based DNN pipeline accelerator design for FPGAs. An entire DNN is partitioned into layer groups with pipeline computation within every group. A configurable logic is used to switch between groups instantaneously. Thus, our design can handle any size DNNs on a single FPGA chip. We evaluate our accelerator for Alexnet and VGG16 on a Xilinx ZC706 board. Our experimental results show that we can increase the throughput by 19% and 42% when compared with layer-based accelerators in [1] and [16].

Original languageEnglish (US)
Title of host publicationProceedings - 2019 6th International Conference on Information Science and Control Engineering, ICISCE 2019
EditorsShaozi Li, Yun Cheng, Ying Dai, Jianwei Ma
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages959-962
Number of pages4
ISBN (Electronic)9781728157122
DOIs
StatePublished - Dec 2019
Event6th International Conference on Information Science and Control Engineering, ICISCE 2019 - Shanghai, China
Duration: Dec 20 2019Dec 22 2019

Publication series

NameProceedings - 2019 6th International Conference on Information Science and Control Engineering, ICISCE 2019

Conference

Conference6th International Conference on Information Science and Control Engineering, ICISCE 2019
CountryChina
CityShanghai
Period12/20/1912/22/19

Keywords

  • Deep Neural Network
  • FPGA
  • Layer Pipeline

ASJC Scopus subject areas

  • Information Systems
  • Information Systems and Management
  • Control and Systems Engineering
  • Control and Optimization

Fingerprint Dive into the research topics of 'A Flexible DNN Accelerator Design with Layer Pipeline for FPGAs'. Together they form a unique fingerprint.

Cite this