Latency Insertion Method for Accelerated Simulation of Memristor Crossbar Array in Neuromorphic Chip

Yi Zhou, Hanzhi Ma, Junwei Yu, Tahsin Shameem, Zohreh Salehi, Shaloo Rakheja, Erping Li, José E. Schutt-Ainé

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

Abstract

Neuromorphic chips constructed by memristor crossbar array have been introduced to realize in-memory computation. The simulations are usually conducted by full-wave simulation or SPICE-like simulations, which can still be time-consuming for large-scale examples. This work proposed a new method based on the Latency Insertion Method (LIM) that can be orders of magnitude faster than commercial software on memristor crossbar array simulations.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE 74th Electronic Components and Technology Conference, ECTC 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2200-2204
Number of pages5
ISBN (Electronic)9798350375985
DOIs
StatePublished - 2024
Event74th IEEE Electronic Components and Technology Conference, ECTC 2024 - Denver, United States
Duration: May 28 2024May 31 2024

Publication series

NameProceedings - Electronic Components and Technology Conference
ISSN (Print)0569-5503

Conference

Conference74th IEEE Electronic Components and Technology Conference, ECTC 2024
Country/TerritoryUnited States
CityDenver
Period5/28/245/31/24

Keywords

  • circuit simulation
  • latency insertion method (LIM)
  • memristor crossbar
  • neuromorphic computing

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Latency Insertion Method for Accelerated Simulation of Memristor Crossbar Array in Neuromorphic Chip'. Together they form a unique fingerprint.

Cite this