Accelerating low bit-width deep convolution neural network in MRAM

Zhezhi He, Shaahin Angizi, Deliang Fan

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

5 Scopus citations

Abstract

Deep Convolution Neural Network (CNN) has achieved outstanding performance in image recognition over large scale dataset. However, pursuit of higher inference accuracy leads to CNN architecture with deeper layers and denser connections, which inevitably makes its hardware implementation demand more and more memory and computational resources. It can be interpreted as 'CNN power and memory wall'. Recent research efforts have significantly reduced both model size and computational complexity by using low bit-width weights, activations and gradients, while keeping reasonably good accuracy. In this work, we present different emerging nonvolatile Magnetic Random Access Memory (MRAM) designs that could be leveraged to implement 'bit-wise in-memory convolution engine', which could simultaneously store network parameters and compute low bit-width convolution. Such new computing model leverages the 'in-memory computing' concept to accelerate CNN inference and reduce convolution energy consumption due to intrinsic logic-in-memory design and reduction of data communication.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2018
PublisherIEEE Computer Society
Pages533-538
Number of pages6
ISBN (Print)9781538670996
DOIs
StatePublished - Aug 7 2018
Externally publishedYes
Event17th IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2018 - Hong Kong, Hong Kong
Duration: Jul 9 2018Jul 11 2018

Publication series

NameProceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI
Volume2018-July
ISSN (Print)2159-3469
ISSN (Electronic)2159-3477

Conference

Conference17th IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2018
CountryHong Kong
CityHong Kong
Period7/9/187/11/18

Keywords

  • In-memory computing
  • Magnetic Random Access Memory
  • Neural network acceleration

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Accelerating low bit-width deep convolution neural network in MRAM'. Together they form a unique fingerprint.

Cite this