A genetic algorithm based optimization method for low vertical link density 3-dimensional Networks-on-Chip many core systems

The advantages of moving from 2-Dimensional Networks-on-Chip (NoCs) to 3-Dimensional NoCs for any application must be justified by the improvements in performance, power, latency and the overall system costs, especially the cost of Through-Silicon-Via (TSV). The trade-off between the number of TSVs and the 3D NoCs system performance becomes one of the most critical design issues. In this paper, we demonstrate a genetic algorithm (GA) based system optimization method, which can deliver the advanced system design setup through topology, routing algorithm, task mapping and tile placement. In comparison to the simulated annealing (SA) based design optimization method, our GA based method can achieve significant advantages. All the experiments have been done in GSNOC framework (written in SystemC-RTL), which can achieve the cycle accuracy and good flexibility.

[1]  Klaus Hofmann,et al.  A simulation framework for 3-dimension Networks-on-chip with different vertical channel density configurations , 2012, 2012 IEEE 15th International Symposium on Design and Diagnostics of Electronic Circuits & Systems (DDECS).

[2]  Takahiro Watanabe,et al.  An efficient 3D NoC synthesis by using genetic algorithms , 2010, TENCON 2010 - 2010 IEEE Region 10 Conference.

[3]  TingTing Hwang,et al.  TSV redundancy: Architecture and design issues in 3D IC , 2010, 2010 Design, Automation & Test in Europe Conference & Exhibition (DATE 2010).

[4]  Vijay Laxmi,et al.  GA Based Congestion Aware Topology Generation for Application Specific NoC , 2011, 2011 Sixth IEEE International Symposium on Electronic Design, Test and Application.

[5]  Peter Ramm,et al.  Handbook of 3D integration : technology and applications of 3D integrated circuits , 2012 .

[6]  Makoto Motoyoshi,et al.  Through-Silicon Via (TSV) , 2009, Proceedings of the IEEE.

[7]  Zhigang Mao,et al.  Efficient temporal task partition for coarse-grain reconfigurable systems based on Simulated Annealing Genetic Algorithm , 2011, 2011 9th IEEE International Conference on ASIC.

[8]  Klaus Hofmann,et al.  Deadlock-free routing algorithms for 3-dimension Networks-on-Chip with reduced vertical channel density topologies , 2012, 2012 International Conference on High Performance Computing & Simulation (HPCS).

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

[10]  Oliver Diessel,et al.  Optimization of placement of dynamic network-on-chip cores using simulated annealing , 2011, IECON 2011 - 37th Annual Conference of the IEEE Industrial Electronics Society.