FUTURE OF FPGA - ACCELERATING COMPUTATIONS IN DATA PROCESSING CENTERS AND CLOUDS
DOI:
https://doi.org/10.26906/SUNZ.2023.2.106Keywords:
reconfigurable logic, FPGA acceleration, cloud computing, data center, virtualization, taxonomic categories, data classification, machine learning, softwareAbstract
Relevance. Data analysis is often performed using machine learning methods. Often, the algorithms involved need to deal with large datasets, which leads to long execution times. Therefore, research into hardware accelerators based on fieldprogrammable gate arrays (FPGAs) to improve performance is relevant. FPGAs are a promising solution for hardware acceleration, post-production configuration, and reprogramming capabilities. The purpose of this study is to investigate and analyze trends in existing cloud FPGA architectures, which highlight the complex relationship between architectures and system requirements. This allows us to identify new architectures that are likely to offer significant benefits for cloud workloads. The object of the study is the evolution of FPGA accelerators for data center (DC) and cloud computing. The subject of the study is methods and algorithms for researching cloud FPGA architectures based on taxonomic categories. Results. The paper discusses the future use of FPGAs in data centers and clouds. Current architectures are also investigated and scalability and abstractions supported by operating systems, middleware, and virtualization are discussed. Conclusion. A classification of cloud FPGA architectures based on taxonomic categories has been developed. An architectural organization for deploying FPGA applications used in cloud environments and data center environments is considered and proposed.Downloads
References
A. Putnam, A. M. Caulfield, E. S. Chung, D. Chiou, K. Constantinides, J. Demme, H. Esmaeilzadeh, J. Fowers, G. P. Gopal, J. Gray, M. Haselman, S. Hauck, S. Heil, A. Hormati, J. Kim, S. Lanka, J. Larus, E. Peterson, S. Pope, A. Smith, J. Thong, P. Y. Xiao, and D. Burger. 2014. A reconfigurable fabric for accelerating large-scale data center services. In ACM/IEEE 41st International Symposium on Computer Architecture (ISCA). 13–24. DOI:https://doi.org/10.1109/ISCA. 2014.6853195.
A. M. Caulfield, E. S. Chung, A. Putnam, H. Angepat, Jeremy Fowers, Michael Haselman, Stephen Heil, Matt Humphrey, Puneet Kaur, Joo-Young Kim, Daniel Lo, Todd Massengill, Kalin Ovtcharov, Lisa Woods, Sitaram Lanka, Derek Chiou, and Doug Burger. 2016. A cloud-scale acceleration architecture. In 49th IEEE/ACM Int. Symp. on Microarchitecture. 1–13.
J. Fowers, G. Brown, P. Cooke, and G. Stitt, “A performance and energy comparison of FPGAs,GPUs, and multicores for sliding-window applications,” in Proceedings of the ACM/ SIGDA International Symposium on Field Programmable Gate Arrays, pp. 47–56, ACM, Monterey, CA, USA, February 2012.
Chethan Ramesh, Shivukumar B. Patil, Siva Nishok Dhanuskodi, George Provelengios, Sébastien Pillement, Daniel Holcomb, and Russell Tessier. 2018. FPGA side channel attacks without physical access. In IEEE 26th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM). 45–52.
Kasper Rasmussen, Ilias Giechaskiel, and Ken Eguro. 2019. Leakier wires: Exploiting FPGA long wires for covert-and sidechannel attacks. ACM Trans. Reconfig. Technol. Syst. 12, 3 (2019).
Ilias Giechaskiel, Kasper Rasmussen, and Jakub Szefer. 2020. CAPSULe: Cross-FPGA covert-channel attacks through power supply unit leakage. In IEEE Symposium on Security and Privacy. 1728–1741.
George Provelengios, Daniel Holcomb, and Russell Tessier. 2019. Characterizing power distribution attacks in multi-user FPGA environments. In International Conference on Field Programmable Logic and Applications (FPL). 194–201.
Xilinx Case Study. [n.d.]. Xilinx Powers Alibaba Cloud FaaS with AI Acceleration Solution for E-Commerce Business. Retrieved from https://www.xilinx.com/publications/powered-by-xilinx/xilinx-alibaba-case-study.pdf.
Norihisa Fujita, Ryohei Kobayashi, Yoshiki Yamaguchi, and Taisuke Boku. 2019. Parallel processing on FPGA combining computation and communication in OpenCL programming. In IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, 479–488.
Mohamed S Abdelfattah, David Han, Andrew Bitar, Roberto DiCecco, Shane O’Connell, Nitika Shanker, Joseph Chu, Ian Prins, Joshua Fender, Andrew C Ling, et al. Dla: Compiler and fpga overlay for neural network inference acceleration. In 2018 28th International Conference on Field Programmable Logic and Applications (FPL), pages 411–4117. IEEE, 2018.
