A fuzzy-based routing scheme for network-on-chip with honeycomb topology

Network-on-chip (NoC) paradigm, which is based on a modular packet-switched mechanism, effectively addresses many of the on-chip communication challenges such as wiring complexity, communication latency, and bandwidth of many-core systems. In designing an efficient NoC, topology and routing algorithm are the most important challenging issues that have significant impact on area, latency and power consumption. The goal of this paper is designing a fuzzy-based routing algorithm for a NoC architecture with honeycomb topology. The proposed algorithm is a livelock and deadlock free routing algorithm based on fuzzy logic for hexagonal zones with flat triple coordinate system. The analysis of simulation results demonstrates that the proposed algorithm, provides higher performance in terms of latency, power consumption, throughput and area than a traditional fuzzy-based routing algorithm for mesh-based NoC architectures. Comparing to a non-fuzzy routing algorithm for honeycomb NoCs, the proposed scheme performs faster with higher throughput with a negligible area and power consumption overhead.

[1]  Xuan-Tu Tran,et al.  Fuzzy-logic based low power solution for Network-on-Chip architectures , 2016, 2016 International Conference on Advanced Technologies for Communications (ATC).

[2]  Hannu Tenhunen,et al.  Memory-Efficient On-Chip Network With Adaptive Interfaces , 2012, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[3]  Konstantinos Tatas,et al.  Hardware implementation of dynamic fuzzy logic based routing in Network-on-Chip , 2017, Microprocess. Microsystems.

[4]  Hannu Tenhunen,et al.  Fuzzy-based Adaptive Routing Algorithm for Networks-on-Chip , 2013, J. Syst. Archit..

[5]  Fahimeh Yazdanpanah,et al.  H2WNoC: A honeycomb hardware-efficient wireless network-on-chip architecture , 2019, Nano Commun. Networks.

[6]  Bevan M. Baas,et al.  A Hexagonal Processor and Interconnect Topology for Many-Core Architecture with Dense On-Chip Networks , 2012, VLSI-SoC.

[7]  H. Tenhunen,et al.  Comparison of mesh and honeycomb network-on-chip architectures , 2012, 2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA).

[8]  Santanu Chattopadhyay,et al.  Network-on-Chip , 2014 .

[9]  Axel Jantsch,et al.  Networks on chip , 2003 .

[10]  Salvatore Monteleone,et al.  Cycle-Accurate Network on Chip Simulation with Noxim , 2016, ACM Trans. Model. Comput. Simul..

[11]  An-Yeu Wu,et al.  Regional ACO-Based Cascaded Adaptive Routing for Traffic Balancing in Mesh-Based Network-on-Chip Systems , 2015, IEEE Transactions on Computers.

[12]  Masoud Daneshtalab,et al.  An energy-efficient partition-based XYZ-planar routing algorithm for a wireless network-on-chip , 2018, The Journal of Supercomputing.

[13]  Masoud Daneshtalab,et al.  HoneyWiN: Novel Honeycomb-Based Wireless NoC Architecture in Many-Core Era , 2018, ARC.

[14]  Nader Bagherzadeh,et al.  AROMa: Aging-Aware Deadlock-Free Adaptive Routing Algorithm and Online Monitoring in 3D NoCs , 2018, IEEE Transactions on Parallel and Distributed Systems.

[15]  Alexander Wei Yin,et al.  Explorations of Honeycomb Topologies for Network-on-Chip , 2009, 2009 Sixth IFIP International Conference on Network and Parallel Computing.