Survey on Smart Network Interface Card

被引:0
|
作者
Ma X. [1 ,2 ]
Yang F. [1 ]
Wang Z. [1 ]
Yuan G. [1 ]
An X. [1 ,2 ]
机构
[1] High Performance Computer Research Center, Institute of Computing Technology, Chinese Academy of Sciences, Beijing
[2] University of Chinese Academy of Sciences, Beijing
基金
中国国家自然科学基金;
关键词
High performance network; In-network computing; Network offloading; Programmable architecture; Programming framework; Smart network interface card (SmartNIC);
D O I
10.7544/issn1000-1239.20200629
中图分类号
学科分类号
摘要
In the era of the rapid increase in network speed, memory access bottleneck has been a prominent problem, and network processing overhead has been increasing significantly. Ordinary network cards have gradually exposed defects in network protocol processing, data migration, and programmable flexibility in modern applications. As a programmable intelligent network device, the SmartNIC (smart network interface card) has received extensive attention in the fields of data center and scientific computing cluster applications. SmartNIC has become a key technology to solve network bottlenecks. It can bring significant benefits in terms of protocol processing offload, network function virtualization, application-specific acceleration, and other usage scenarios. We survey the basic architecture, programming framework, application direction, and other hot research issues of SmartNIC. We summarize the typical products in the current industry and important achievements in academia. We also clarify the advantages and disadvantages of different design architectures. The application scenarios applicable to different programming frameworks are introduced, and the value of SmartNIC in typical data center applications and scientific computing applications is introduced. After that, we give some efficient suggestions about software and hardware collaborative design of SmartNIC in different application scenarios. Finally, we present the hot issues that still exist in the design and use of SmartNIC, and put forward the important future research points and a universal design solution for SmartNIC. © 2022, Science Press. All right reserved.
引用
收藏
页码:1 / 21
页数:20
相关论文
共 116 条
  • [1] 2020 roadmap
  • [2] Hoefler T, Girolamo S, Taranov K, Et al., sPIN: High-performance streaming processing in the network, Proc of the Int Conf for High Performance Computing, Networking, Storage and Analysis, (2017)
  • [3] Daniel F, Andrew P, Sambhrama M, Et al., Azure accelerated networking: SmartNICs in the public cloud, Proc of the 15th Symp on Networked Systems Design and Implementa-tion, pp. 51-66, (2018)
  • [4] Sean C, Muhammad S, Balaji P, Et al., λ-NIC: Interactive serverless compute on programmable SmartNICs, Proc of the ACM Special Interest Group on Data Communication, pp. 151-152, (2019)
  • [5] Ma Xiaoxiao, Lu Gang, Fu Binzhang, Et al., Implementation method and performance analysis of non-contiguous data communication in network, Chinese Journal of Computers, 43, 6, pp. 1123-1138, (2020)
  • [6] Maroun T, Lina M, Mark S., Lynx: A SmartNIC-driven accelerator-centric architecture for network servers, Proc of the 25th Int Conf on Architectural Support for Programming Languages and Operating Systems, pp. 117-131, (2020)
  • [7] Antoine K, SImon P, Naveen K, Et al., High performance packet processing with FlexNIC, Proc of the 21st Int Conf on Architectural Support for Programming Languages and Operating Systems, pp. 67-81, (2016)
  • [8] Kaushik K R, Jayaram M, Alan L, Et al., SNICh: Efficient last hop networking in the data center, Proc of the 6th ACM/IEEE Symp on Architectures for Networking and Communications Systems, (2010)
  • [9] Li Xiaoyao, Wang Xiuxiu, Liu Fangming, Et al., DHL: Enabling flexible software network functions with FPGA acceleration, Proc of the 38th Int Conf on Distributed Computing Systems, (2018)
  • [10] Alexander R, Muhammad S, Tushar S, Et al., Elastic RSS: Co-Scheduling packets and cores using programmable NICs, Proc of the 3rd Asia-Pacific Workshop on Networking, pp. 71-77, (2019)