Hardware Acceleration

Author:

Mahmoud Dina

Abstract

AbstractWith Moore’s law and Dennard’s scaling no longer fueling the improvement in computing performance, new avenues for increasing performance are needed. Hardware acceleration is one avenue where many researchers and industrial parties are working and investing. Accelerators can allow for high levels of parallelism not supported by general-purpose central processing units. These high levels of parallelism are particularly well-suited for many modern applications. Therefore, research on the use of hardware acceleration is expected to continue in the near future. However, various parties should consider a variety of aspects when deciding whether to invest in hardware acceleration by making their own accelerators or by buying them from a third party. This factsheet presents an analysis of hardware acceleration and the trends until 2025. It also discusses the aspects and how specific considerations are more important for some actors.

Funder

armasuisse

Publisher

Springer Nature Switzerland

Reference6 articles.

1. Wen-mei Hwu and Sanjay Patel. Accelerator Architectures – A Ten-Year Retrospective. IEEE Micro, 38(6):56–62, November 2018. Conference Name: IEEE Micro.

2. IRDS$${ }^{\text{TM}}$$ 2021: Executive Summary - IEEE IRDS$${ }^{\text{TM}}$$. https://irds.ieee.org/editions/2021/executive-summary, August 2022.

3. Mohamed Gafsi, Mohamed Ali Hajjaji, Jihene Malek, and Abdellatif Mtibaa. FPGA hardware acceleration of an improved chaos-based cryptosystem for real-time image encryption and decryption. Journal of Ambient Intelligence and Humanized Computing, October 2021.

4. Apple unleashes M1, November 2020. Apple Newsroom.

5. Arm Ltd. Security algorithm accelerators. https://developer.arm.com/downloads/-/security-algorithm-accelerators.

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Privacy Preserving Provable Data Possession: A FHE-based Hash Approach;2023 18th Asia Joint Conference on Information Security (AsiaJCIS);2023-08-15

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3