Recent Progress on Signal Integrity Modeling of Neuromorphic Chips by the PEEC Method

Hanzhi Ma, Tuomin Tao, Quankun Chen, Da Li, Jose Schutt-Aine, Andreas Cangellaris, Er Ping Li

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

Abstract

With the rapid advances of artificial intelligence and its applications, the design of memristor-based neuromorphic chips inspired by the human brain has become an important area of research. Signal integrity issues, such as crosstalk and IR drop, affect the performance of these chips and necessitate the use of signal integrity modeling and analysis methods during the early stages of chips design. In this mini review, we summarize recent progress on the application of the Partial Element Equivalent Circuit (PEEC) method to the signal integrity modeling of neuromorphic chips.

Original languageEnglish (US)
Title of host publicationEPEPS 2023 - IEEE 32nd Conference on Electrical Performance of Electronic Packaging and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350317985
DOIs
StatePublished - 2018
Event32nd IEEE Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2023 - Milpitas, United States
Duration: Oct 15 2023Oct 18 2023

Publication series

NameEPEPS 2023 - IEEE 32nd Conference on Electrical Performance of Electronic Packaging and Systems

Conference

Conference32nd IEEE Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2023
Country/TerritoryUnited States
CityMilpitas
Period10/15/2310/18/23

Keywords

  • Neuromorphic chips
  • partial element equivalent circuit
  • signal integrity

ASJC Scopus subject areas

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

Fingerprint

Dive into the research topics of 'Recent Progress on Signal Integrity Modeling of Neuromorphic Chips by the PEEC Method'. Together they form a unique fingerprint.

Cite this