A Reconfigurable Streaming Deep Convolutional Neural Network Accelerator for Internet of Things

Li Du*, Yuan Du, Yilei Li, Junjie Su, Yen-Cheng Kuan, Chun Chen Liu, Mau-Chung Chang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

60 Scopus citations

Abstract

Convolutional neural network (CNN) offers significant accuracy in image detection. To implement image detection using CNN in the Internet of Things (IoT) devices, a streaming hardware accelerator is proposed. The proposed accelerator optimizes the energy efficiency by avoiding unnecessary data movement. With unique filter decomposition technique, the accelerator can support arbitrary convolution window size. In addition, max-pooling function can be computed in parallel with convolution by using separate pooling unit, thus achieving throughput improvement. A prototype accelerator was implemented in TSMC 65-nm technology with a core size of 5 mm2. The accelerator can support major CNNs and achieve 152GOPS peak throughput and 434GOPS/W energy efficiency at 350 mW, making it a promising hardware accelerator for intelligent IoT devices.

Original languageEnglish
Article number8011462
Pages (from-to)198-208
Number of pages11
JournalIEEE Transactions on Circuits and Systems I: Regular Papers
Volume65
Issue number1
DOIs
StatePublished - 1 Jan 2018

Keywords

  • Convolution neural network
  • deep learning
  • hardware accelerator
  • IoT

Fingerprint Dive into the research topics of 'A Reconfigurable Streaming Deep Convolutional Neural Network Accelerator for Internet of Things'. Together they form a unique fingerprint.

Cite this