HW/ SW Partitioning Algorithms for Multi-objective Optimization in Embedded Systems

One of the most crucial steps in the design of modern Embedded Systems (ES) is the partitioning the system’s functionalities between the hardware (HW) blocks and the software (SW) blocks. The process of hardware software partitioning (HSP) is driven by several non functional requirements factors. Several works studied the influence of the execution time and the hardware area (cost) factors while dealing with the HSP problem; other works included also the power consumption factor. This article gives a study the HSP problem while considering several factors (ES metrics) and presents two approaches to solve the problem. The first approach has the objective of optimizing simultaneously a number of metrics while respecting a constraint on the global hardware area (cost metric), this approach is implemented using 0-1 Knapsack Problem (KP) algorithm; experimental results show that the algorithm is very fast and gives more reliable solutions comparing to well-known algorithms such as the Genetic Algorithm (GA) and the Simulated Annealing (SA) algorithm. The second approach aims to optimize the hardware cost while respecting given constraints on the other metrics; the proposed approach is based on Balas method.