Fundamental Limits on the Computational Accuracy of Resistive Crossbar-based In-memory Architectures

Saion K. Roy, Ameya Patil, Naresh R. Shanbhag

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

Abstract

In-memory computing (IMC) architectures exhibit an intrinsic trade-off between computational accuracy and energy efficiency. This paper determines the fundamental limits on the compute SNR of MRAM-, ReRAM-, and FeFET-based crossbars by employing statistical signal and noise models. For a specific dot-product dimension N, the maximum compute SNR (SNRmax) is shown to occur at an optimum value of sensing resistance R-{s} {*} where clipping and quantization noise contributions from the analog-to-digital converter (ADC) are balanced out. SNRmax can be further improved by choosing devices with higher resistive contrast Roff/Ron, e.g., FeFET, but only until it attains a value in the range 12-15. Beyond this point, mismatch in the input digital-to-analog converters (DACs) and bitcell variations begin to dominate the compute SNR. Finally, by mapping a ResNet20 (CIFAR-10) network onto resistive crossbars, it is shown that the array-level compute SNR maximizing circuit parameters also maximizes the network-level accuracy.

Original languageEnglish (US)
Title of host publicationIEEE International Symposium on Circuits and Systems, ISCAS 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages384-388
Number of pages5
ISBN (Electronic)9781665484855
DOIs
StatePublished - 2022
Event2022 IEEE International Symposium on Circuits and Systems, ISCAS 2022 - Austin, United States
Duration: May 27 2022Jun 1 2022

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume2022-May
ISSN (Print)0271-4310

Conference

Conference2022 IEEE International Symposium on Circuits and Systems, ISCAS 2022
Country/TerritoryUnited States
CityAustin
Period5/27/226/1/22

Keywords

  • FeFET
  • MRAM
  • ReRAM
  • SNR
  • crossbar
  • eNVM
  • in-memory computing

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Fundamental Limits on the Computational Accuracy of Resistive Crossbar-based In-memory Architectures'. Together they form a unique fingerprint.

Cite this