Evolutionary optimization techniques and reconfigurable hardware.

摘要

An optimization scheme for embedded system design using hardware and software components is presented. The goal of suitably partitioning the system into hardware and software is achieved using Genetic Algorithms (GA). The optimization objective is to reduce the time taken and the power consumed during task execution. The suitability of introducing a reconfigurable hardware resource over preconfigured hardware is explored for the same objectives. Further, the procedure to allocate optimal number of resources based on the design objective is proposed. A test environment is developed using randomly generated task graphs.; In applying evolutionary optimization techniques to reconfigurable architectures, the design of a run time reconfigurable Fuzzy Logic Controller (FLC) is presented. Four design strategies of implementing the FLC are presented, which includes a feasibility analysis for the maximum design size. Further, an implementation framework for hardware-software co-design and a self-reconfiguring Fuzzy Logic Controller is proposed.