Area-Efficient and Variation-Tolerant In-Memory BNN Computing using 6T SRAM Array

  • Jinseok Kim
  • , Jongeun Koo
  • , Taesu Kim
  • , Yulhwa Kim
  • , Hyungjun Kim
  • , Seunghyun Yoo
  • , Jae Joon Kim

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

89 Scopus citations

Abstract

We introduce a SRAM-based binary neural network (BNN) hardware which uses a single 6T SRAM cell for XNOR operation for the first time. The cell is 45% smaller than the previous 8T bitcell for XNOR operation. We also propose an in-memory calibration and batch normalization to achieve more reliable operation under the presence of process variation.

Original languageEnglish
Title of host publication2019 Symposium on VLSI Circuits, VLSI Circuits 2019 - Digest of Technical Papers
PublisherInstitute of Electrical and Electronics Engineers Inc.
PagesC118-C119
ISBN (Electronic)9784863487185
DOIs
StatePublished - Jun 2019
Externally publishedYes
Event33rd Symposium on VLSI Circuits, VLSI Circuits 2019 - Kyoto, Japan
Duration: 9 Jun 201914 Jun 2019

Publication series

NameIEEE Symposium on VLSI Circuits, Digest of Technical Papers
Volume2019-June

Conference

Conference33rd Symposium on VLSI Circuits, VLSI Circuits 2019
Country/TerritoryJapan
CityKyoto
Period9/06/1914/06/19

Fingerprint

Dive into the research topics of 'Area-Efficient and Variation-Tolerant In-Memory BNN Computing using 6T SRAM Array'. Together they form a unique fingerprint.

Cite this