Advertisement

Source Hotspot Management in a Mesh Network on Chip

  • Ajay S
  • Satya Sai Krishna Mohan G
  • Shashank S Rao
  • Sujay B ShaunakEmail author
  • Krutthika H K
  • Ananda Y R
  • John Jose
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 892)

Abstract

Network-on-Chip helps to accomplish greater throughput in multi-core chips. In a multi-core chip, each core parallelly processes multiple applications thereby increasing the overall processing capability of the chip. One of the major concern in this field is managing congestion on the network. There are many reasons for congestion, one of them is hotspots, which has been considered in this paper. The applications on a multi-core architecture that operates on large amount of data and computation may create hotspots. These hotspots introduce congestion on the network and increase the latency of packets that pass through them. Our solution to hotspots, identify the source hotspots and decrease inflow of packets into the hotspots, thereby reducing the network pressure where hotspots are present. The congestion control scheme is a threshold based approach that dynamically evaluates the presence of hotspots on the network and a routing algorithm to effectively route the packets away from the hotspots. Our experimental results show that the packets are routed away from the source hotspots and the packet latency of the network is effectively reduced.

Keywords

Congestion management Odd-Even routing Threshold 

Notes

Acknowledgement

This work is supported in part by a grant from DST Government of India, SERB-ECR scheme (project number ECR/2016/212).

References

  1. 1.
    Wang, C., Hu, W., Bagherzadeh, N.: Scalable load balancing congestion-aware network-on-chip router architecture. J. Comput. Syst. Sci. 79(4), 421–439 (2013)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Reshma Raj, R.S., Das, A., Jose, J.: Implementation and analysis of hotspot mitigation in mesh NoCs by cost-effective deflection routing technique. In: IFIP/IEEE International Conference on Very Large Scale Integration (VLSI-SoC), Abu Dhabi, pp. 1–6 (2017)Google Scholar
  3. 3.
    Link, G.M., Vijaykrishnan, N.: Hotspot prevention through runtime reconfiguration in network-on-chip. In: Design, Automation and Test in Europe (DATE), pp. 648–649 (2005)Google Scholar
  4. 4.
    Huang, W., et al.: HotSpot: a compact thermal modeling methodology for early-stage VLSI design. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 14(5), 501–513 (2006)CrossRefGoogle Scholar
  5. 5.
    Gindin, R., et al.: NoC-based FPGA: architecture and routing. In: International Symposium on Networks-on-Chip (NOCS), pp. 253–264 (2007)Google Scholar
  6. 6.
    Kakoulli, E., et al.: HPRA: a pro-active hotspot-preventive high-performance routing algorithm for networks-on-chips. In: International Conference on Computer Design (ICCD), pp. 249–255 (2012)Google Scholar
  7. 7.
    Kakoulli, E., et al.: Intelligent hotspot prediction for network-on-chip based multicore systems. IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst. 31(3), 418–431 (2012)CrossRefGoogle Scholar
  8. 8.
    Gupte, A., Jones, P.: Hotspot mitigation using dynamic partial reconfiguration for improved performance. In: International Conference on Reconfigurable Computing and FPGAs (ReConFig), pp. 89–94 (2009)Google Scholar
  9. 9.
    Alfaraj, N., et al.: HOPE: hotspot congestion control for Clos network on chip. In: International Symposium on Networks-on-Chip (NOCS), pp. 17–24 (2011)Google Scholar
  10. 10.
    Tang, M., Lin, X., Palesi, M.: The repetitive turn model for adaptive routing. IEEE Trans. Comput. 66(1), 138–146 (2017)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Tsai, W.-C., Chu, K.-C., Hu, Y.-H., Chen, S.-J.: Non-minimal, turn-model based NoC routing. Microprocess. Microsyst. 37(8, Part B), 899–914 (2013). ISSN 0141–9331CrossRefGoogle Scholar
  12. 12.
    Benini, L., De Micheli, G.: Networks on chips: a new SoC paradigm. Computer 35, 70–78 (2002)CrossRefGoogle Scholar
  13. 13.
    Tatas, K., Siozios, K., Soudris, D., Jantsch, A.: Designing 2D and 3D Network on-Chip Architectures, 1st edn, p. 265. Springer, New York (2014).  https://doi.org/10.1007/978-1-4614-4274-5CrossRefGoogle Scholar
  14. 14.
    Jiang, N., et al.: A detailed and flexible cycle-accurate network-on-chip simulator. In: International Symposium on Performance Analysis of Systems and Software (ISPASS), pp. 86–96 (2013)Google Scholar
  15. 15.
    Binkert, N., et al.: The gem5 simulator. ACM SIGARCH Comput. Arch. News 39(2), 1 (2011)CrossRefGoogle Scholar
  16. 16.
  17. 17.

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Ajay S
    • 1
  • Satya Sai Krishna Mohan G
    • 1
  • Shashank S Rao
    • 1
  • Sujay B Shaunak
    • 1
    Email author
  • Krutthika H K
    • 1
  • Ananda Y R
    • 2
  • John Jose
    • 2
  1. 1.Department of ECEDayananda Sagar College of EngineeringBengaluruIndia
  2. 2.MARS Lab, Department of CSEIndian Institute of Technology GuwahatiGuwahatiIndia

Personalised recommendations