Hardware Software Partitioning Problem in Embedded System Design Using Particle Swarm Optimization Algorithm | IEEE Conference Publication | IEEE Xplore

Hardware Software Partitioning Problem in Embedded System Design Using Particle Swarm Optimization Algorithm


Abstract:

Hardware/software partitioning is a crucial problem in embedded system design. In this paper, we provide an alternative approach to solve this problem using particle swar...Show More

Abstract:

Hardware/software partitioning is a crucial problem in embedded system design. In this paper, we provide an alternative approach to solve this problem using particle swarm optimization (PSO) algorithm. Performance analysis of the proposed scheme with integer linear programming, genetic algorithm and ant colony optimization technique has been compared using standard benchmark datasets, and the computer simulations reveal that the proposed approach outperforms all the meta-heuristic based existing techniques with respect to cumulative runtimes for several runs of the same program. The integer linear programming has been found to yield the optimal solutions, and the proposed swarm scheme yields sub-optimal solution, sufficiently close to the reported results obtained for integer programming.
Date of Conference: 04-07 March 2008
Date Added to IEEE Xplore: 22 August 2008
Print ISBN:978-0-7695-3109-0
Conference Location: Barcelona, Spain

1. Introduction

An embedded system is a computing system rather than desktop computers/laptops/palmtops, capable of reacting spontaneously with sensory inputs in real time and designed for dedicated applications. Typical applications that employ embedded systems include fax machines, copiers, printers, scanners, cash registers, alarm systems, card readers, mobile phones, digital cameras, washing machines, DVD players, speech recognizers and many more. Like typical computer systems, embedded systems too include hardware and software components. In other words, it is common to use both application-specific hardware accelerator circuits and general-purpose programmable units with appropriate software for embedded system design. Usually application specific hardware is much faster than software and also more power efficient, but expensive at the some time. Software, on the other hand, is cheaper, but slow and consumes much power when implemented on a general purpose processor. Hence for faster realization or power-critical situations, hardware based systems are preferred, whereas noncritical modules of embedded systems are realized in software. Consequently a trade-off between cost, power and performance needs to be devised to realize an embedded system on a mixed hardware/software platform.

Contact IEEE to Subscribe

References

References is not available for this document.