SHF: Small: Novel SW/HW Approximate Computing Methodologies with Case Studies on Biometric Security Systems

SHF：小型：新颖的软件/硬件近似计算方法以及生物识别安全系统的案例研究

• 批准号: 1814920
• 负责人: Sherief Reda
• 金额: $ 31.35万
• 依托单位: Brown University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-07-01 至 2023-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1814920&HistoricalAwards=false
• 关键词: SHF; Small; Novel; SW; HW

Biometric systems are increasingly deployed to meet the security demand of mobile, embedded and internet-of-things devices. The goal of this project is to devise techniques that lead to biometric systems with faster response time, less energy consumption and cost without compromising the accuracy and security. In addition to the main research goal, this project includes a comprehensive education and outreach plan that includes research experience for undergraduate students, interdisciplinary educational courses, outreach to high-school students, and tech transfer to industry. To achieve the goal of this project, new approximate computing techniques will be developed to simplify the hardware of biometric systems with little or no compromise to accuracy. The project investigates new methods for approximate logic circuit synthesis using Boolean matrix factorization, which leads to smooth trade-off between circuit complexity and quality of results. The project also investigates the use of reinforcement-learning techniques to navigate the space of potential approximate designs to identify the best ones. Finally, the proposal investigates the impact of using the proposed methods on case studies of end-to-end biometric systems, including fingerprinting, iris scanning, and 3D facial recognition.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.

生物识别系统越来越多地被部署，以满足移动、嵌入式和物联网设备的安全需求。该项目的目标是设计一种技术，使生物识别系统具有更快的响应时间、更少的能耗和成本，同时又不影响准确性和安全性。除了主要研究目标外，该项目还包括全面的教育和推广计划，其中包括本科生的研究经验、跨学科教育课程、高中生的推广以及向行业的技术转让。为了实现该项目的目标，将开发新的近似计算技术来简化生物识别系统的硬件，而不会影响准确性。该项目研究了使用布尔矩阵分解进行近似逻辑电路综合的新方法，从而实现电路复杂性和结果质量之间的平滑权衡。该项目还研究了如何使用强化学习技术来探索潜在的近似设计空间，以确定最佳设计。最后，该提案调查了使用所提出的方法对端到端生物识别系统案例研究的影响，包括指纹识别、虹膜扫描和 3D 面部识别。该奖项反映了 NSF 的法定使命，并通过评估被认为值得支持利用基金会的智力优势和更广泛的影响审查标准。

项目成果

Approximate Logic Synthesis Using Boolean Matrix Factorization

使用布尔矩阵分解的近似逻辑综合

• DOI: 10.1109/tcad.2021.3054603
• 发表时间: 2021-01-26
• 期刊: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
• 影响因子: 2.9
• 作者: Jingxiao Ma;S. Hashemi;S. Reda
• 通讯作者: S. Reda

Coordinated Batching and DVFS for DNN Inference on GPU Accelerators

GPU 加速器上用于 DNN 推理的协调批处理和 DVFS

• DOI: 10.1109/tpds.2022.3144614
• 发表时间: 2022-10-01
• 期刊: IEEE Transactions on Parallel and Distributed Systems
• 影响因子: 5.3
• 作者: Seyed Morteza Nabavinejad;S. Reda;M. Ebrahimi
• 通讯作者: M. Ebrahimi

AdaSense: Adaptive Low-Power Sensing and Activity Recognition for Wearable Devices

AdaSense：适用于可穿戴设备的自适应低功耗传感和活动识别

• 发表时间: 2020-01
• 期刊: Proceedings of Design Automation Conference
• 作者: M. Neseem; J. Nelson
• 通讯作者: J. Nelson

Approximate Logic Synthesis: A Survey

近似逻辑综合：调查

• DOI: 10.1109/jproc.2020.3014430
• 发表时间: 2020-12-01
• 期刊: Proceedings of the IEEE
• 影响因子: 20.6
• 作者: Ilaria Scarabottolo;G. Ansaloni;G. Constantinides;L. Pozzi;S. Reda
• 通讯作者: S. Reda

Approximate Logic Synthesis Using BLASYS,

使用 BLASYS 进行近似逻辑综合，

• 发表时间: 2019-01
• 期刊: Workshop on Open-Source EDA Technology
• 作者: J. Ma; S. Hashemi
• 通讯作者: S. Hashemi