ffLink

Author:

de la Chevallerie David1,Korinth Jens1,Koch Andreas1

Affiliation:

1. Embedded Systems and Applications Group, Darmstadt, Germany

Abstract

We describe the architecture and implementation of ffLink, a high-performance PCIe Gen3 interface for attaching reconfigurable accelerators on Xilinx Virtex 7 FPGA devices to Linux-based hosts. ffLink encompasses both hardware as well as flexible operating system components that allow a tailoring of the infrastructure to the specific data transfer needs of the application. When configured to use multiple DMA engines to hide transfer latencies, ffLink achieves a throughput of up to 7 GB/s, which is 95% of the maximum throughput of an eight-lane PCIe interface, while requiring just 11% of device area on a mid-size FPGA.

Publisher

Association for Computing Machinery (ACM)

Reference14 articles.

1. Demo Bundle Virtex7 Gen3. http://xillybus.com/pcie-download 2014. Accessed: 02/15. Demo Bundle Virtex7 Gen3. http://xillybus.com/pcie-download 2014. Accessed: 02/15.

2. REPARA - Reengineering and Enabling Performance and poweR of Applications. http://www.repara-project.eu 2014. Accessed: 01/15. REPARA - Reengineering and Enabling Performance and poweR of Applications. http://www.repara-project.eu 2014. Accessed: 01/15.

3. PCI Express Solution. http://nwlogic.com/products/pci-express-solution/ 2015. Accessed: 03/2015. PCI Express Solution. http://nwlogic.com/products/pci-express-solution/ 2015. Accessed: 03/2015.

Cited by 9 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. SoftCache: A Software Cache for PCIe-Attached Hardware Accelerators;Proceedings of the Platform for Advanced Scientific Computing Conference;2024-06-03

2. TaPaS Co-AIE: An Open-Source Framework for Streaming-Based Heterogeneous Acceleration Using AMD AI Engines;2024 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW);2024-05-27

3. Ethernet Emulation over PCIe for RISC-V Software Development Vehicles;2023 38th Conference on Design of Circuits and Integrated Systems (DCIS);2023-11-15

4. Fair DMA Scheduler for Low-Latency Accelerator Offloading;2022 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom);2022-12

5. Portrait: A holistic computation and bandwidth balanced performance evaluation model for heterogeneous systems;Sustainable Computing: Informatics and Systems;2022-09

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