High-Level Modeling Approach for Analyzing the Effects of Traffic Models on Power and Throughput in Mesh-Based NoCs

Traffic models exert different message flows in a network and have a considerable effect on power consumption through different applications. So a good power analysis should consider traffic models. In this paper we present power and throughput models in terms of traffic rate parameters for the most popular traffic models, i e. Uniform, local, HotSpot and First Matrix Transpose (FMT) as a permutational traffic model. We also select Mesh topology as the most prominent NoC topology and validate the presented models by comparing our results against simulation results from Synopsys Power Compiler and Modelsim. From the comparison, we show that our modeling approach leads to average error of 2% for power and 2.8% for throughput modeling.

[1]  Li-Shiuan Peh,et al.  High-level power analysis for on-chip networks , 2004, CASES '04.

[2]  Luca Benini,et al.  Networks on chip: a new paradigm for systems on chip design , 2002, Proceedings 2002 Design, Automation and Test in Europe Conference and Exhibition.

[3]  Luca Benini,et al.  Networks on Chips : A New SoC Paradigm , 2022 .

[4]  P. Marwedel,et al.  Design, Design Automation, And Test In Europe , 1997, IEEE Design & Test of Computers.

[5]  Kai Hwang,et al.  Advanced computer architecture - parallelism, scalability, programmability , 1992 .

[6]  Mary K. Vernon,et al.  Performance Analysis of Mesh Interconnection Networks with Deterministic Routing , 1994, IEEE Trans. Parallel Distributed Syst..

[7]  Partha Pratim Pande,et al.  Performance evaluation and design trade-offs for network-on-chip interconnect architectures , 2005, IEEE Transactions on Computers.

[8]  Anant Agarwal,et al.  Limits on Interconnection Network Performance , 1991, IEEE Trans. Parallel Distributed Syst..

[9]  William J. Dally,et al.  Performance Analysis of k-Ary n-Cube Interconnection Networks , 1987, IEEE Trans. Computers.