SYSTEM-LEVEL SYNTHESIS USING EVOLUTIONARY ALGORITHMS

In this paper, we consider system-level synthesis;Is the problem of op timally mapping a task-level specification onto a heterogeneous hardwa re/software architecture. This problem requires (1) the selection of t he architecture (allocation) including general purpose and dedicated p rocessors, ASICs, busses and memories, (2) the mapping of the specific ation onto the selected architecture in space (binding) and time (sche duling), and (3) the design space exploration with the goal to find a set of implementations that satisfy a number of constraints on cost an d performance. Existing methodologies often consider a fixed architect ure, perform the binding only, do not reflect the tight interdependenc y between binding and scheduling, do not consider communication (tasks and resources), or require long run-times preventing design space exp loration, or yield only one implementation with optimal cost. Here, a model is introduced that handles all mentioned requirements and allows the task of system-synthesis to be specified as an optimization probl em. The application and adaptation of an-Evolutionary Algorithm to sol ve the tasks of optimization and design space exploration is described .