Design of a Current-Mode Linear-Sum-Based Bitcounting Circuit with an MTJ-Based Compensator for Binarized Neural Networks

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

2 Citations (Scopus)

Abstract

A bitcounting operation, which counts l's/0's in input values and decides the output depending on their majority, is one of the important operations in binarized neural networks (BNNs). In this paper, we propose a bitcounting circuit for compact and low-power BNN hardware. This circuit performs the bitcounting operation by utilizing current-mode linear summation, which achieves a high-speed and low-power operation as well as a compact circuit. In order to guarantee a reliable analog operation of the circuit under possible process variation conditions, magnetic tunnel junction (MTJ) devices integrated with the bitcounting circuit can adjust its operating point and keep this adjustment information in a nonvolatile manner. Through an experimental-data-based evaluation of a 25-input bitcounting circuit under a 40-nm MOS/MTJ-hybrid process, we show that this circuit reduces the power-delay product and circuit area by 92% and 93%, respectively, compared to a conventional accumulation-tree-based one, while guaranteeing the correct operation under the process variation condition assumed on the target fabrication process technology.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE 49th International Symposium on Multiple-Valued Logic, ISMVL 2019
PublisherIEEE Computer Society
Pages91-96
Number of pages6
ISBN (Electronic)9781728100913
DOIs
Publication statusPublished - 2019 May
Event49th IEEE International Symposium on Multiple-Valued Logic, ISMVL 2019 - Fredericton, Canada
Duration: 2019 May 212019 May 23

Publication series

NameProceedings of The International Symposium on Multiple-Valued Logic
Volume2019-May
ISSN (Print)0195-623X

Conference

Conference49th IEEE International Symposium on Multiple-Valued Logic, ISMVL 2019
Country/TerritoryCanada
CityFredericton
Period19/5/2119/5/23

Keywords

  • binarized neural network
  • bitcounting
  • nonvolatile memory
  • variation compensation

ASJC Scopus subject areas

  • Computer Science(all)
  • Mathematics(all)

Fingerprint

Dive into the research topics of 'Design of a Current-Mode Linear-Sum-Based Bitcounting Circuit with an MTJ-Based Compensator for Binarized Neural Networks'. Together they form a unique fingerprint.

Cite this