Skip to main content

Advertisement

Log in

Energy-aware partitioning of fault-tolerant irregular topologies for 3D network-on-chips

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Irregular topologies have become more attractive choice than their regular counterparts for network-on-chip (NoC) designs since they have lower power consumptions, higher throughputs, and lower latencies. These topologies use the minimum required network resources to minimize some design objectives such as energy and performance. Hence, they are designed to guarantee only one way between application nodes. Therefore, a single permanent link failure may cause a complete breakdown for the designed chip. Previous studies presented an irregular topology design method that adds extra routers and links to have alternative paths between nodes. These topologies use the main routing table if there is no failure on the design. It stores the alternative routing options on routing tables, which can be activated by the external pins of the chip when there is a fault on a link. However, the alternative routings increase the energy consumption and latency of the packets. One solution to mitigate the energy and latency increase can be implementing the design as a 3D NoC, which utilizes faster and less energy consuming through silicon vias between different layers. In this study, we present a method that generates irregular fault-tolerant topology and routing for 3D NoCs. We compare the proposed method with its 2D counterpart on three benchmarks from literature based on energy consumption and chip area. The results show that 3D-based method brings significant energy improvements, especially in alternative routings. Additionally, we observed that employing 3D structure reduces the area proportional to the number of 3D layers, which makes the 3D design a perfect choice for the designed fault-tolerant system.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Dally WJ, Towles B (2001) Route packets, not wires: on-chip interconnection networks. In: Design Automation Conference, 2001. Proceedings. IEEE, pp 684–689

  2. International Technology Roadmap for semiconductors (2015) http://public.itrs.net/

  3. Mark W (2009) A study of nanometer semiconductor scaling effects on microelectronics reliability. PhD Thesis, University of Maryland

  4. Chang Y-C et al (2011) On the design and analysis of fault tolerant NoC architecture using spare routers. In: Proceedings of the 16th Asia and South Pacific Design Automation Conference. IEEE Press

  5. Arabnia HR, Bhandarkar SM (1996) Parallel stereocorrelation on a reconfigurable multi-ring network. J supercomput 10(3):243–269

    Article  MATH  Google Scholar 

  6. Touzene A, Day K (2015) All-to-all broadcasting in torus network on chip. J Supercomput 71(7):2585–2596

    Article  Google Scholar 

  7. Ren Y et al (2013) A fault tolerant NoC architecture using quad-spare mesh topology and dynamic reconfiguration. J Syst Architect 59(7):482–491

    Article  Google Scholar 

  8. Safaei F, ValadBeigi M (2012) An efficient routing methodology to tolerate static and dynamic faults in 2-D mesh networks-on-chip. Microprocess Microsyst 36(7):531–542

    Article  Google Scholar 

  9. Srinivasan K, Chatha KS, Konjevod G (2006) Linear-programming-based techniques for synthesis of network-on-chip architectures. IEEE Trans Very Large Scale Integr (VLSI) Syst 14(4):407–420

    Article  Google Scholar 

  10. Dumitriu V, Khan GN (2009) Throughput-oriented NoC topology generation and analysis for high performance SoCs. IEEE Trans Very Large Scale Integr VLSI Syst 17(10):1433–1446

    Article  Google Scholar 

  11. Siewiorek D, Swarz R (2017) Reliable computer systems: design and evaluatuion. Digital Press, Butterworth

    MATH  Google Scholar 

  12. Tosun S, Ajabshir VB, Mercanoglu O, Ozturk O (2015) Fault-tolerant topology generation method for application-specific network-on-chips. IEEE Trans Comput-Aided Des Integr Circuit Syst 34(9):1495–1508

    Article  Google Scholar 

  13. Ajabshir VB, Tosun S (2014) Fault-tolerant routing for irregular-topology-based network-on-chips. In: Second International Symposium on Computing and Networking, IEEE, 2014, pp 123–129

  14. Koyanagi M, Nakamura T, Yamada Y, Kikuchi H, Fukushima T, Tanaka T, Kurino H (2006) Three-dimensional integration technology based on wafer bonding with vertical buried interconnections. IEEE Trans Electron Dev 53(11):27992808

    Article  Google Scholar 

  15. Van der Plas G et al (2011) Design issues and considerations for low-cost 3-D TSV IC technology. IEEE J Solid-State Circuits 46(1):293–307

    Article  Google Scholar 

  16. Karypis G, Kumar V (1998) A fast and high quality multilevel scheme for partitioning irregular graphs. SIAM J Sci Comput 20(1):359–392

    Article  MathSciNet  MATH  Google Scholar 

  17. Kirkpatrick S, Gelatt CD, Vecchi MP (1983) Optimization by simulated annealing. Science 220(4598):671–680

    Article  MathSciNet  MATH  Google Scholar 

  18. Marcon CAM, Moreno EI, Calazans NLV, Moraes FG (2008) Comparison of network-on-chip mapping algorithms targeting low energy consumption. Comput Dig Tech IET 2(6):471–482

    Article  Google Scholar 

  19. Cormen TH, Leiserson CE, Rivest RL, Stein C (2001) Introduction to algorithms. MIT Press, Cambridge

    MATH  Google Scholar 

  20. Kim DH, Mukhopadhyay S, Lim SK (2009) TSV-aware interconnect length and power prediction for 3D stacked ICs. Proceedings of the 2009 IEEE International Interconnect Technology Conference, IITC 2009, pp 26–28

  21. Lee K, Nakamura T, Ono T, Yamada Y, Mizukusa T, Hashimoto H, Park K, Kurino H, Koyanagi M (2000) Three-dimensional shared memory fabricated using wafer stacking technology. In: Electron Devices Meeting, 2000 IEDM’00. Technical Digest. International. IEEE 2000, pp 165–168

  22. http://glaros.dtc.umn.edu/gkhome/views/metis

  23. Pothen A, Simon HD, Liou K-P (1990) Partitioning sparse matrices with eigenvectors of graphs. SIAM J Matrix Anal Appl 11(3):430–452

    Article  MathSciNet  MATH  Google Scholar 

  24. Fiduccia CM, Mattheyses RM (1988) A linear-time heuristic for improving network partitions. Papers on twenty-five years of electronic design automation. ACM

  25. Kernighan BW, Lin S (1970) An efficient heuristic procedure for partitioning graphs. Bell Syst Tech J 49(2):291–307

    Article  MATH  Google Scholar 

  26. Hu J, Marculescu R (2005) Energy-and performance-aware mapping for regular NoC architectures. IEEE Trans Comput Aided Des Integr Circuits Syst 24(4):551–562

    Article  Google Scholar 

  27. Kim H, Ghoshal P, Grot B, Gratz PV, Jiménez DA (2011) Reducing network-on-chip energy consumption through spatial locality speculation. In: Proceedings of the Fifth ACM/IEEE International Symposium on Networks-on-Chip. ACM, pp 233–240

Download references

Acknowledgements

This work was supported by The Scientific and Technological Research Council of Turkey (TÜBITAK) under Grant No. 117E130.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Suleyman Tosun.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tosun, S., Ajabshir, V.B. Energy-aware partitioning of fault-tolerant irregular topologies for 3D network-on-chips. J Supercomput 74, 4842–4863 (2018). https://doi.org/10.1007/s11227-018-2491-6

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-018-2491-6

Keywords

Navigation