Back to search

Georgia Institute of Technology

Design of a non-volatile capacitor-based compute-in memory neural network accelerator

Abstract

dc:description.abstract

To avoid growing challenges with existing neural network accelerators which have sig- nificant energy requirements, the design for a compute-in-memory (CIM) chip is presented and demonstrated in simulation. The CIM aspect is based off a ferroelectric memory de- vice which allows for both storing and performing operations on neural network weights, which bypasses the need for a conventional Von-Neumann based load-store architecture. The focus in this thesis will be on the digital aspect of the accelerator, including inter-chip communication interfaces, the clock networks, and analog-digital interfaces.

Degree

thesis:*
Level thesis:degree_level
Masters
Department dc:contributor.department
Electrical and Computer Engineering
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Mufti, Saad
Advisor dc:contributor.advisor
  • Yu, Shimeng
Committee members dc:contributor.committeemember
  • Doolittle, William A.
  • Hao, Callie

Subjects

dc:subject × 3

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/81544

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Mufti, Saad. Design of a non-volatile capacitor-based compute-in memory neural network accelerator. Masters thesis, Georgia Institute of Technology, 2025. https://hdl.handle.net/1853/81544