Abstract
Traditionally, performance evaluation of networks-on-chip (NoC) is largely based on simulation which, besides being extremely slow, provides little insight on how different design parameters can affect the actual network performance. Therefore, it is practically impossible to use simulation for optimization purposes. This chapter presents a mathematical model for on-chip routers and utilize this new model for NoC performance analysis. The model presented in this chapter can be used not only to obtain fast and accurate performance estimates, but also to guide the NoC design process within an optimization loop. The accuracy of our approach and its practical use is illustrated through extensive simulation results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Our assumptions and router model are detailed in Sect. 5.5.
- 2.
The PASTA definition implies that the distribution of packets in the system that is seen by a new (arriving) packet is the same as the long run (time asymptotic) or steady state of the packet distribution. This allows us to relate the mean waiting time a packet in the buffer with the mean number of packets in all the buffers of the router.
- 3.
Equivalently, the eigenvalues of matrices \(T\Uplambda C_{1}\) and \(T \Uplambda C_{1}\) are less than one.
- 4.
Note that, in this chapter, we use A \(\ge \) B to denote the element-wise comparison for two matrices of same dimensions.
- 5.
When \(P = 1 \), this condition reduces to \(\lambda T < 1\) known as the stability condition for a single buffer.
- 6.
Each mapping is simulated 100 times and the average latency over all runs is used for ranking to increase the confidence level of the results. Run-time comparisons against a single simulation run are presented in Sect. 5.6.5.
References
Bertsekas D, Gallager R (1992) Data networks. Prentice Hall, Upper Saddle River
Dally WJ (1990) Performance analysis of k-ary n-cube interconnection networks. IEEE Trans Comput 39(6):775–785
Dielissen J, Radulescu A, Goossens K, Rijpkema E (2003) Concepts and implementation of the Philips network-on-chip. IP-based SoC Design
Draper J, Ghosh J (1994) A comprehensive analytical model for wormhole routing in multicomputer systems. J Parallel Distrib Comput 23(2):202–214
Guan W, Tsai W, Blough D (1993) An analytical model for wormhole routing in multicomputer interconnection networks. In: Proceedings of international parallel processing symposium, April (1993)
Guz Z, Walter I, Bolotin E, Cidon I, Ginosar R, Kolodny A (2006) Efficient link capacity and QoS design for wormhole network-on-chip. In: Proceedings of design, automation and test in Europe conference, March (2006)
Hu P, Kleinrock L (1997) An analytical model for wormhole routing with finite size input buffers. In: 15th international teletraffic congress, June (1997)
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
Hu J, Ogras UY, Marculescu R (2006) System-level buffer allocation for application-specific networks-on-chip router design. IEEE Trans Comput Aided Des Integr Circuits Syst 25(12):2919–2933
Lieverse P, Van Der Wolf P, Vissers K, Deprettere E (2001) A methodology for architecture exploration of heterogeneous signal processing systems. J VLSI Signal Process Syst Signal Image Video Technol 29(3):197–206
Marculescu R, Ogras UY, Peh L, Jerger NE, Hoskote Y (2009) Outstanding research problems in NoC design: system, microarchitecture, and circuit perspectives. IEEE Trans Comput Aided Des Integr Circuits Syst 28(1):3–21
Millberg M, Nilsson E, Thid R, Jantsch A (2004) Guaranteed bandwidth using looped containers in temporally disjoint networks within the Nostrum network on chip. In: Proceedings of design, automation and test in Europe conference, Feb (2004)
Murali S, De Micheli G (2004) Bandwidth-constrained mapping of cores onto NoC architectures. In: Proceedings of design, automation and test in Europe conference, Feb (2004)
Ogras UY, Marculescu R (2006) “It’s a small world after all”: NoC performance optimization via long-range link insertion. IEEE Trans Very Large Scale Integr Syst Special Sect Hardw/Softw Codesign Syst Synth 14(7):693–706
Ogras UY, Bogdan P, Marculescu R (2010) An analytical approach for network-on-chip performance analysis. In: IEEE transaction on computer-aided design of integrated circuits and systems (TCAD), vol 29, Issue 12, Dec (2010)
Ould-Khaoua M, Sarbazi-Azad H (2001) An analytical model of adaptive wormhole routing in hypercubes in the presence of hot spot traffic. IEEE Trans Parallel Distrib Syst 12(3):283–292
Pande PP, Grecu C, Jones M, Ivanov A, Saleh R (2005) Performance evaluation and design trade-offs for network-on-chip interconnect architectures. IEEE Trans Comput 54(8):1025–1040
Ross S (2006) Simulation. Elsevier Academic Press, New York
Strang G (2009) Introduction to linear algebra, 4th edn. Wellesley-Cambridge Press, Welleseley
Varatkar G, Marculescu R (2004) On-chip traffic modeling and synthesis for MPEG-2 video applications. IEEE Trans VLSI 12(1):108–119
Wang H, Zhu X, Peh L, Malik S (2002) Orion: a power-performance simulator for interconnection networks. In: Proceedings of annual international symposium on microarchitecture, Nov (2002)
Worm_Sim: a cycle accurate simulator for Networks-on-Chip. http://www.ece.cmu.edu/~sld/wiki/doku.php?id=shared:worm_sim
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2013 Springer Science+Business Media New York
About this chapter
Cite this chapter
Ogras, U.Y., Marculescu, R. (2013). NoC Performance Analysis. In: Modeling, Analysis and Optimization of Network-on-Chip Communication Architectures. Lecture Notes in Electrical Engineering, vol 184. Springer, Dordrecht. https://doi.org/10.1007/978-94-007-3958-1_5
Download citation
DOI: https://doi.org/10.1007/978-94-007-3958-1_5
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-007-3957-4
Online ISBN: 978-94-007-3958-1
eBook Packages: EngineeringEngineering (R0)