In this paper we present a multi-objective genetic algorithm to solve the problem of mapping a set of task graphs onto a heterogeneous multiprocessor platform. The objective is to meet all real-time deadlines subject to minimizing system cost and power consumption, while staying within bounds on local memory sizes and interface buffer sizes. Our approach allows for mapping onto a fixed platform or onto a flexible platform where architectural changes are explored during the mapping. We demonstrate our approach through an exploration of a smart phone, where five task graphs with a total of 530 tasks after hyper period extension are mapped onto a multiprocessor platform. The results show four non-inferior solutions which tradeoffs the various objectives.
Main Research Area:
Informatics and Mathematical Modelling, Technical University of Denmark, DTU, 2006