Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

Trade-offs in the design of a router with both guaranteed and best-effort services for networks on chip

Trade-offs in the design of a router with both guaranteed and best-effort services for networks on chip

For access to this article, please select a purchase option:

Buy article PDF
$19.95
(plus tax if applicable)
Buy Knowledge Pack
10 articles for $120.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IEE Proceedings - Computers and Digital Techniques — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Managing the complexity of designing chips containing billions of transistors requires decoupling computation from communication. For the communication, scalable and compositional interconnects, such as networks on chip (NoC), must be used. It is shown that guaranteed services are essential in achieving this decoupling. Guarantees typically come at the cost of lower resource utilisation. To avoid this, they must be used in combination with best-effort services. The key element of this NoC is a router consisting conceptually of two parts; the so-called guaranteed-throughput (GT) and best-effort (BE) routers. The GT and BE router architectures are combined in an efficient implementation by sharing resources. The trade-offs between hardware complexity and efficiency of the combined router are shown that motivate the choices. The reasoning for the trade-offs is validated with a prototype router implementation. A layout is shown of an input-queued wormhole 5×5 router with an aggregate bandwidth of 80 Gbit/s. It occupies 0.26 mm2 in a 0.13 μm technology. This shows that our router provides high performance at reasonable cost, bringing NoCs one step closer.

References

    1. 1)
      • Mckeown, W.N.: `Scheduling algorithms for input-queued cell switches', 1995, PhD thesis, University of California, Berkeley, CA, USA.
    2. 2)
      • Goossens, K., van Meerbergen, J., Peeters, A., Wielage, P.: `Networks on silicon: Combining best-effort and guaranteed services', Proc. Design Automation and Test in Europe Conf., Paris, March 2002, p. 423–425.
    3. 3)
      • K. Keutzer , S. Malik , A. Richard Newton , J.M. Rabaey , A. Sangiovanni–Vincentelli . System-level design: orthogonalization of concerns and platform-based design. IEEE Trans. Comput.-Aided Des. Integr. Circuits Sys. , 12 , 1523 - 1543
    4. 4)
      • DeHon, A.: ‘Robust, high-speed network design for large-scale multiprocessing’. A.I. Technical report 1445, Massachusetts Institute of Technology, Artificial Intelligence Laboratory, September 1993.
    5. 5)
      • J. Bainbridge , S. Furber . CHAIN: A delay-insensitive chip area interconnect. IEEE Micro , 5 , 16 - 23
    6. 6)
      • A.S. Tanenbaum . (1981) Computer networks.
    7. 7)
    8. 8)
      • Ali, M.K.M., Youssefi, M.: `The performance analysis of an input access scheme in a high-speed packet switch', Proc. Joint Conf. IEEE Computer and Communications Societies. Networking in the 90s., (INFOCOM), Bal Harbour, FL, April 1991, vol. 2, , p. 454–461.
    9. 9)
      • K. Goossens , J. Dielissen , J. van Meerbergen , P. Paplavko , A. Rădulescu , E. Rijpkema , E. Waterlander , P. Wielage , A. Jantsch , H. Tenhunen . (2003) Guaranteeing the quality of services in networks on chip, Networks on chip.
    10. 10)
      • Guerrier, P., Greiner, A.: `A generic architecture for on-chip packet-switched interconnections', Proc. Design Automation and Test in Europe Conf., Paris, 2000, p. 250–256.
    11. 11)
      • M.T. Rose . (1990) The open book: a practical perspective on OSI.
    12. 12)
      • M.J. Karol , M.G. Hluchyj , S.P. Morgan . Input versus output queueing on a space-division packet switch. IEEE Trans. Commun. , 12 , 1347 - 1356
    13. 13)
      • Rexford, J.: `Tailoring router architectures to performance requirements in cut-through networks', 1999, PhD thesis, University of Michigan, Department of Computer Science and Engineering.
    14. 14)
      • L. Benini , G. De Micheli . Networks on chips: A new SoC paradigm. IEEE Comput. , 1 , 70 - 80
    15. 15)
      • Zimmer, H.: `Fault modelling and error-control coding in a network-on-chip. Master's thesis', Laboratory of Electronics and Computer Systems, Royal Institute of Technology (KTH), IMIT/LECS 2002-26, Stockholm, 2002.
    16. 16)
      • Dally, W.J., Towels, B.: `Route packets, not wires: on-chip interconnection networks', Proc. Design Automation Conf., June 2001, p. 684–689.
    17. 17)
      • A. Rădulescu , K. Goossens , S. Bhattacharyya , E. Deprettere , J. Teich . (2003) Communication services for networks on silicon, Domain-specific processors: systems, architectures, modeling and simulation.
    18. 18)
      • L. Benini , G. De Micheli . Powering networks on chips. Proc. Int. Symp. on Systems Synthesis (ISSS) , 33 - 38
    19. 19)
      • Sgroi, M., Sheets, M., Mihal, A., Keutzer, K., Malik, S., Rabaey, J., Sangiovanni-Vincentelli, A.: `Addressing the system-on-a-chip interconnect woes through communication-based design', Proc. Design Automation Conf., Las Vegas, NV, June 2001, p. 667–672.
http://iet.metastore.ingenta.com/content/journals/10.1049/ip-cdt_20030830
Loading

Related content

content/journals/10.1049/ip-cdt_20030830
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address