Slot-Based Transmission Protocol for Real-Time NoCs - SBT-NoC

Authors Borislav Nikolić, Robin Hofmann, Rolf Ernst



PDF
Thumbnail PDF

File

LIPIcs.ECRTS.2019.26.pdf
  • Filesize: 2.39 MB
  • 22 pages

Document Identifiers

Author Details

Borislav Nikolić
  • Institute of Computer and Network Engineering, TU Braunschweig, Germany
Robin Hofmann
  • Institute of Computer and Network Engineering, TU Braunschweig, Germany
Rolf Ernst
  • Institute of Computer and Network Engineering, TU Braunschweig, Germany

Cite AsGet BibTex

Borislav Nikolić, Robin Hofmann, and Rolf Ernst. Slot-Based Transmission Protocol for Real-Time NoCs - SBT-NoC. In 31st Euromicro Conference on Real-Time Systems (ECRTS 2019). Leibniz International Proceedings in Informatics (LIPIcs), Volume 133, pp. 26:1-26:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)
https://doi.org/10.4230/LIPIcs.ECRTS.2019.26

Abstract

Network on Chip (NoC) interconnects are some of the most challenging-to-analyse components of multiprocessor platforms. This is primarily due to the following two reasons: (i) NoCs contain numerous shared resources (e.g. routers, links), and (ii) the network traffic often concurrently traverses multiple of those resources. Consequently, complex contention scenarios among traffic flows might occur, some of the important implications being significant performance limitations, and difficulties when performing the real-time analysis. In this work, we propose a slot-based transmission protocol for NoCs (called SBT-NoC), and an accompanying analysis method for deriving worst-case traffic latencies. The cornerstone of SBT-NoC is a contention-less slot-based transmission, arbitrated via a protocol running on a dedicated network medium. The main advantage of SBT-NoC is that, while not requiring any sophisticated hardware support (e.g. virtual channels, a flit-level arbitration), it makes NoCs amenable to real-time analysis and guarantees bounded low latencies of high-priority time-critical flows, which is a sine qua non for the inclusion of NoCs, and multiprocessors in general, in the real-time domain. The experimental evaluation, including both synthetic workloads and a use-case of an autonomous driving vehicle application, reveals that SBT-NoC offers a plethora of configuration opportunities, which makes it applicable to a wide range of diverse traffic workloads.

Subject Classification

ACM Subject Classification
  • Computer systems organization → Real-time systems
  • Computer systems organization → Embedded systems
Keywords
  • Real-Time Systems
  • Embedded Systems
  • Network-on-Chip
  • Protocols

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads

References

  1. Adapteva. Epiphany Architecture. URL: https://www.adapteva.com/docs/epiphany_arch_ref.pdf.
  2. L. Benini and G. De Micheli. Networks on chips: a new SoC paradigm. The Comp. J., 35(1):70-78, January 2002. Google Scholar
  3. Josef Berwanger, Martin Peller, and Robert Griessbach. byteflight - A new protocol for safety-critical applications. In FISITA World Automotive Congress, 2000. Google Scholar
  4. T. Bjerregaard and J. Sparso. Implementation of guaranteed services in the MANGO clockless network-on-chip. IEE Proc. - Computers &Digital Techniques, 153(4):217-229, July 2006. Google Scholar
  5. W.J. Dally. Virtual-channel flow control. Trans. Parall. &Distr. Syst., 3(2):194-205, March 1992. Google Scholar
  6. W.J. Dally and C.L. Seitz. Deadlock-Free Message Routing in Multiprocessor Interconnection Networks. Trans. Computers, 1987. Google Scholar
  7. Robert I. Davis, Alan Burns, Reinder J. Bril, and Johan J. Lukkien. Controller Area Network (CAN) schedulability analysis: Refuted, revisited and revised. Real-Time Syst. J., 2007. Google Scholar
  8. K. Duraisamy and P. P. Pande. Enabling High-Performance SMART NoC Architectures Using On-Chip Wireless Links. Trans. Very Large Scale Integration Syst., 2017. Google Scholar
  9. K. Goossens, J. Dielissen, and A. Radulescu. AEthereal network on chip: concepts, architectures, and implementations. IEEE Design &Test Computers, 2005. Google Scholar
  10. Tim Harde, Matthias Freier, Georg von der Brüggen, and Jian-Jia Chen. Configurations and Optimizations of TDMA Schedules for Periodic Packet Communication on Networks on Chip. In 26th RTNS, 2018. Google Scholar
  11. Leandro Soares Indrusiak, Alan Burns, and Borislav Nikolić. Buffer-aware bounds to multi-point progressive blocking in priority-preemptive NoCs. In 21st DATE, 2018. Google Scholar
  12. Intel. Single-Chip-Cloud Computer, 2010. URL: https://www.intel.com/content/dam/www/public/us/en/documents/technology-briefs/intel-labs-single-chip-cloud-article.pdf.
  13. E. Kasapaki, M. Schoeberl, R. B. Sørensen, C. Müller, K. Goossens, and J. Sparsø. Argo: A Real-Time Network-on-Chip Architecture With an Efficient GALS Implementation. Trans. Very Large Scale Integration Syst., 2016. Google Scholar
  14. N. K. Kavaldjiev and G. J. M. Smit. A Survey of Efficient On-Chip Communications for SoC. In 4th Symp. Emb. Syst., 2003. Google Scholar
  15. M. Liu, M. Becker, M. Behnam, and T. Nolte. A tighter recursive calculus to compute the worst case traversal time of real-time traffic over NoCs. In 22nd ASPDAC, 2017. Google Scholar
  16. R. Makowitz and C. Temple. Flexray - A communication network for automotive control systems. In Int. WS Factory Comm. Syst., 2006. Google Scholar
  17. Borislav Nikolić, Sebastian Tobuschat, Leandro Soares Indrusiak, Rolf Ernst, and Alan Burns. Real-time analysis of priority-preemptive NoCs with arbitrary buffer sizes and router delays. Real-Time Syst. J., 2018. Google Scholar
  18. C. Paukovits and H. Kopetz. Concepts of Switching in the Time-Triggered Network-on-Chip. In 14th RTCSA, pages 120-129, 2008. Google Scholar
  19. Yue Qian, Zhonghai Lu, and Wenhua Dou. Analysis of worst-case delay bounds for best-effort communication in wormhole networks on chip. In NOCS, 2009. Google Scholar
  20. Martin Schoeberl, Sahar Abbaspour, Benny Akesson, Neil Audsley, Raffaele Capasso, Jamie Garside, Kees Goossens, Sven Goossens, Scott Hansen, Reinhold Heckmann, Stefan Hepp, Benedikt Huber, Alexander Jordan, Evangelia Kasapaki, Jens Knoop, Yonghui Li, Daniel Prokesch, Wolfgang Puffitsch, Peter Puschner, Andrć Rocha, Cláudio Silva, Jens Sparsø, and Alessandro Tocchi. T-CREST: Time-predictable multi-core architecture for embedded systems. J. Syst. Arch., 2015. Google Scholar
  21. Zheng Shi and A. Burns. Real-Time Communication Analysis for On-Chip Networks with Wormhole Switching. In NOCS, 2008. Google Scholar
  22. Zheng Shi, Alan Burns, and Leandro Soares Indrusiak. Schedulability Analysis for Real Time On-Chip Communication with Wormhole Switching. Int. J. Emb. &Real-Time Comm. Syst., 2010. Google Scholar
  23. Hyojeong Song, Boseob Kwon, and Hyunsoo Yoon. Throttle and preempt: a new flow control for real-time communications in wormhole networks. In 1997 Int. Conf. Parall. Processing, August 1997. Google Scholar
  24. S. Tobuschat and R. Ernst. Real-time communication analysis for Networks-on-Chip with backpressure. In 20th DATE, 2017. Google Scholar
  25. D. Wentzlaff, P. Griffin, H. Hoffmann, L. Bao, B. Edwards, C. Ramey, M. Mattina, C. Miao, J. F. Brown III, and A. Agarwal. On-Chip Interconnection Architecture of the Tile Processor. MICRO, 2007. Google Scholar
  26. Q. Xiong, F. Wu, Z. Lu, and C. Xie. Extending Real-Time Analysis for Wormhole NoCs. Trans. Computers, 66(9), 2017. Google Scholar
  27. Qin Xiong, Zhonghai Lu, Fei Wu, and Changsheng Xie. Real-Time Analysis for Wormhole NoC: Revisited and Revised. In 26th ACM Great Lakes Symp. VLSI, 2016. Google Scholar
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail