泛研网

公众版 查看说明
全球科研项目数据库2026版

EPSCoR Research Fellows:NSF:Memristor Based Computing-in-Memory for Neuromorphic System:Design,Optimization,and Fabrication

项目来源

美国国家科学基金(NSF)

项目主持人

Jinhui Wang

项目受资助机构

GEORGIA INSTITUTE OF TECHNOLOGY

财政年度

2025,2024

立项时间

未公开

项目编号

2428981

研究期限

未知 / 未知

项目级别

国家级

受资助金额

600000.00美元

学科

未公开

学科代码

未公开

基金类别

Standard Grant

关键词

EPSCoR RII:EPSCoR Research Fe ; EXP PROG TO STIM COMP RES

参与者

未公开

参与机构

UNIVERSITY OF SOUTH ALABAMA

项目标书摘要：Generative AI,such as ChatGPT,along with AI image and video generation platforms,have recently taken the world by storm.However,recent studies have revealed that running AI engines consumes a staggering amount of energy.Neuromorphic systems,which utilize memristors and crossbar arrays,leverage Computing-in-Memory(CIM)technology for AI computation,demonstrating significant improvements in energy efficiency.The goal of this project is to investigate memristor-based CIM for neuromorphic systems from the perspectives of design,optimization,and fabrication.This project offers a unique opportunity for the principal investigator(PI)from the Department of Electrical and Computer Engineering(ECE)at the University of South Alabama(USA)to establish a long-term collaboration with the School of ECE at the Georgia Institute of Technology(Georgia Tech),thereby enhancing the PI’s research capabilities.This collaboration will not only broaden the PI’s research scope but also greatly benefit his career trajectory,ultimately contributing significantly to his home institution and jurisdiction during and beyond the two-year award period.This fellowship provides the PI with an excellent opportunity to explore novel AI computing systems from a hardware perspective,thus steering his research toward transformative new directions.It will also significantly contribute to the economic and technological development of this EPSCoR-eligible jurisdiction.The PI will share the knowledge and resources obtained from Georgia Tech with his colleagues and the broader community,thereby raising the overall research and educational capacity and competitiveness of his institution and jurisdiction.Based on the knowledge acquired at Georgia Tech,the PI will also organize workshops and seminars at his home institution and jurisdiction to foster broad collaborations and maximize the benefits of this fellowship.The enhanced knowledge gained through this fellowship will serve as a crucial link,connecting scientific research with practical applications in AI hardware design,and facilitating the development of future novel computing systems.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

人员信息

Jinhui Wang(Principal Investigator)：jwang231@ua.edu；

机构信息

【Georgia Institute of Technology(Performance Institution)】StreetAddress：225 North Avenue,Atlanta,Georgia,United States/ZipCode：303320315；【UNIVERSITY OF SOUTH ALABAMA】StreetAddress：307 UNIVERSITY BLVD,MOBILE,Alabama,United States/PhoneNumber：2514606333/ZipCode：36688；

项目主管部门

Office Of The Director(O/D)-OIA-Office of Integrative Activities(OIA)

项目官员

Jose Colom(Email：jcolom@nsf.gov；Phone：7032927088)

  • 排序方式：
  • 1
  • /

  • 1.Honey-ReRAM Enabled Sustainable Edge AI System for IoT Applications

    • 关键词：
    • Edge AI; Internet of Things; Electrodes; Switches; Accuracy; Indium tinoxide; Immune system; Energy efficiency; Substrates; Quantization(signal); Internet of Things (IoT); natural organic ReRAM; honey-ReRAM;computing in-memory system; edge artificial intelligence (AI); inferenceaccuracy; variation; nonlinearity; sustainable;MEMORY; DEVICE
    • Wang, Jinhui;Zhao, Feng;Rafeeq Khan, Mohammad;Tanim, Md. Mehedi Hasan;Templin, Zoe;Uppaluru, Harshvardhan
    • 《IEEE ACCESS》
    • 2025年
    • 13卷
    • 期刊

    This paper is toward a promising solution to address the environmental sustainability challenge in computing by building brain-inspired and green non-Von Neumann systems with Resistive Random-Access Memory (ReRAM) made from natural organic materials, honey, for energy-efficient operation, renewable material resources, sustainable device manufacturing, and environmentally-friendly disposal. In this paper, honey-ReRAM and its arrays are firstly manufactured and tested. The resistance modulation mechanism of honey-ReRAM is analyzed and investigated. Then a Computing-in-Memory (CIM) architecture based on honey-ReRAM for edge AI and IoT applications is proposed and evaluated. The experimental results indicate that the proposed edge AI systems with the VGG8 and DenseNet-40 models have a high inference accuracy, more than 90%. If device variation and nonlinearity are considered, the VGG8 model is still effective, and the 16-level ReRAM enabled edge AI system has the best performance, including accuracy = 92%, TOPS = 0.864048, FPS = 701.431, energy efficiency = 45.819, and Per(overall) = 558. Furthermore, four conductance drift scenarios and Analog-to-Digital Converter (ADC) quantization effects are also considered to further verify the proposed edge AI systems. It concludes: 1) the system has high immunity to the device drift effect and would be very reliable even with long duration of time; 2) as for the VGG8 models, when the ADC has 5-bit, all accuracies rise to over 90%; 3) as for DenseNet-40 models, a 7-bit ADC can ensure an accuracy of 88%. Finally, the honey-ReRAM enabled sustainable edge AI system is compared to the state-of-the-art and shows great merits.

    ...
  • 排序方式：
  • 1
  • /