The Open Cybernetics & Systemics Journal

2015, 9 : 1155-1164
Published online 2015 September 10. DOI: 10.2174/1874110X01509011155
Publisher ID: TOCSJ-9-1155

An Improved Algorithm for 3D NoC Floorplanning Based on Particle Swarm Optimization of Nesting Simulated Annealing

Song Guozhi , Zhang Dakun , Huang Cui and Wang Lianlian
School of Computer Science and Software Engineering, Tianjin Polytechnic University, Tianjin300387, China.

ABSTRACT

In this paper, an improved floorplanning algorithm, named the floorplanning algorithm based on particle swarm optimization algorithm nesting simulated annealing to optimize the floorplans (PSO-SA-NoC), has been proposed with simulations conducted to verify this algorithm. The simulation results are compared with the original Simulated Annealing- NoC. The results show that the CPU’s process time of the PSO-SA-NoC algorithm decreased by 35.39%. The packet transmission latency reduces 4.05% in the average case and 83.3% in the best case respectively. The throughput improves 1.72% in the average case and 10.57% in the best case respectively.

Keywords:

3D NoC, floorplanning algorithm, heterogeneous floorplans, PSO, SA.