XOR-CiM: An Efficient Computing-in-SOT-MRAM Design for Binary Neural Network Acceleration

Mehrdad Morsali, Ranyang Zhou, Sepehr Tabrizchi, Arman Roohi, Shaahin Angizi

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

1 Scopus citations

Abstract

In this work, we leverage the uni-polar switching behavior of Spin-Orbit Torque Magnetic Random Access Memory (SOT-MRAM) to develop an efficient digital Computing-in-Memory (CiM) platform named XOR-CiM. XOR-CiM converts typical MRAM sub-arrays to massively parallel computational cores with ultra-high bandwidth, greatly reducing energy consumption dealing with convolutional layers and accelerating X(N)OR-intensive Binary Neural Networks (BNNs) inference. With a similar inference accuracy to digital CiMs, XOR-CiM achieves ∼4.5× and 1.8× higher energy-efficiency and speed-up compared to the recent MRAM-based CiM platforms.

Original languageEnglish (US)
Title of host publicationProceedings of the 24th International Symposium on Quality Electronic Design, ISQED 2023
PublisherIEEE Computer Society
ISBN (Electronic)9798350334753
DOIs
StatePublished - 2023
Event24th International Symposium on Quality Electronic Design, ISQED 2023 - San Francisco, United States
Duration: Apr 5 2023Apr 7 2023

Publication series

NameProceedings - International Symposium on Quality Electronic Design, ISQED
Volume2023-April
ISSN (Print)1948-3287
ISSN (Electronic)1948-3295

Conference

Conference24th International Symposium on Quality Electronic Design, ISQED 2023
Country/TerritoryUnited States
CitySan Francisco
Period4/5/234/7/23

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Electrical and Electronic Engineering
  • Safety, Risk, Reliability and Quality

Keywords

  • SOT-MRAM
  • binary neural networks
  • computing-in-memory

Fingerprint

Dive into the research topics of 'XOR-CiM: An Efficient Computing-in-SOT-MRAM Design for Binary Neural Network Acceleration'. Together they form a unique fingerprint.

Cite this