Similar articles

Abstract: As technology scales down, the reliability issues are becoming more crucial, especially for networks-on-chip (NoCs) that provide the communication requirements of multi-processor systems-on-chip. Reliability evaluation based on analytical models is a precise method for dependability analysis before and after designing the fault-tolerant systems. In this paper, we accurately formulate the inherent reliability and vulnerability of some popular NoC architectures against permanent faults, also depending on the employed routing algorithm and traffic model. Based on this analysis, effects of failures in the links, switches and network interfaces on the packet delivery of NoCs are determined. Besides, some extensions to evaluate a fault-tolerant method and some routing algorithms are described. The analyses are validated through appropriate simulations. The results thus obtained are exactly the same as or very close to the analytical ones.

[1] Abachi, H., Walker, A.J., 1997. Reliability Analysis of Tree, Torus and Hypercube Message Passing Architectures. Proc. 29th Southeastern Symp. on System Theory, p.44-48.

[2] Chang, C., Mohapatra, P., 1998. An efficient method for approximating submesh reliability of two-dimensional meshes. IEEE Trans. Parall. Distr. Syst., 9(11):1115-1124.

[3] Dalirsani, A., Hosseinabady, M., Navabi, Z., 2007. An Analytical Model for Reliability Evaluation of NoC Architectures. Proc. 13th IEEE Int. On-line Testing Symp., p.49-56.

[4] Dally, W.J., Seitz, C.L., 1986. The Torus Routing Chip. Technical Report, No. 5208:TR:86, Computer Science Department, California Institute of Technology, Pasadena, California, USA, p.1-19.

[5] Dally, W.J., Towles, B., 2001. Route Packets, Not Wires: On-chip Interconnection Networks. Proc. ACM/IEEE Design Automation Conf., p.684-689.

[6] Dumitras, T., Marculescu, R., 2003. On-chip Stochastic Communication. Proc. Design, Automation and Test in Europe, p.790-795.

[7] Fazino, F., Palesi, M., Patti, D., 2008. Noxim: Network-on-Chip Simulator. Available from http://sourceforge.net/projects/noxim [Accessed on Sept. 2008].

[8] Glass, C.J., Ni, L.M., 1994. The turn model for adaptive routing. J. ACM, 41(5):874-902.

[9] Greenfield, D., Banerjee, A., Lee, J.G., Moore, S., 2007. Implications of Rent’s Rule for NoC Design and Its Fault-tolerance. Proc. 1st Int. Symp. on Networks-on-Chip, p.283-294.

[10] Kim, J., Das, C.R., Lin, W., Feng, T., 1989. Reliability evaluation of hypercube multicomputers. IEEE Trans. Rel., 38(1):121-129.

[11] Kim, J., Nicopoulos, C., Park, D., Narayanan, V., Yousif, M.S., Das, C.R., 2006. A Gracefully Degrading and Energy-efficient Modular Router Architecture for On-chip Networks. Proc. 33rd Int. Symp. on Computer Architecture, p.4-15.

[12] Koren, I., Krishna, C.M., 2007. Fault Tolerant Systems. Morgan Kaufmann Publishers, San Francisco, CA, p.11-15.

[13] Lehtonen, T., Liljeberg, P., Plosila, J., 2007. Fault Tolerance Analysis of NoC Architectures. IEEE Int. Symp. on Circuits and Systems, p.361-364.

[14] Mohapatra, P., Das, C.R., 1995. On dependability evaluation of mesh connected processors. IEEE Trans. Comput., 44(9):1073-1084.

[15] Mondal, M., Wu, X., Aziz, A., Massoud, Y., 2006. Reliability Analysis for On-chip Networks under RC Interconnect Delay Variation. First Int. Conf. on Nano-networks and Workshops, p.1-5.

[16] Schonwald, T., Zimmermann, J., Bringmann, O., Rosenstiel, W., 2007. Fully Adaptive Fault-tolerant Routing Algorithm for Network-on-Chip Architectures. Proc. 10th Euromicro Conf. on Digital System Design Architectures, Methods and Tools, p.527-534.

[17] Wang, G., Chen, J., Wang, G., Chen, S., 2003. Probability Model for Faults in Large-scale Multicomputer Systems. Proc. 12th Asian Test Symp., p.452-457.