Resistive Memory for Computing and Security: Algorithms, Architectures, and Platforms

TL;DR

This paper explores the use of resistive RAM (RRAM) in computing and security, proposing new algorithms, architectures, and experimental platforms to leverage its unique properties for logic, multi-valued computing, and security primitives.

Contribution

It introduces novel algorithms and architectures for RRAM-based digital logic, multi-valued computing, and security primitives, supported by experimental studies and a dedicated design automation framework.

Findings

Successful implementation of RRAM-based digital logic

Development of multi-valued computing techniques using RRAM

Design and testing of hardware security primitives with RRAM

Abstract

Resistive random-access memory (RRAM) is gaining popularity due to its ability to offer computing within the memory and its non-volatile nature. The unique properties of RRAM, such as binary switching, multi-state switching, and device variations, can be leveraged to design novel techniques and algorithms. This thesis proposes a technique for utilizing RRAM devices in three major directions: i) digital logic implementation, ii) multi-valued computing, and iii) hardware security primitive design. We proposed new algorithms and architectures and conducted \textit{experimental studies} on each implementation. Moreover, we developed the electronic design automation framework and hardware platforms to facilitate these experiments.