Skip to Main Content
This paper investigates the effectiveness of genetic algorithms (GAs) for static task scheduling in wormhole Network-on-Chip-based systems. The overall objective was to get the application model mapped onto the architecture so that all tasks and communication meet their deadlines. Inter-task communication is accounted for by using analytical methods. The GA explores both the mapping of tasks as well as the priority ordering of the task set. A novel fitness function was developed and found to perform better than existing functions.