A hardware/software partitioner using a dynamically determined granularity

Abstract

Computer aided hardware/software partitioning is one of the keychallenges in hardware/software co-design. While previous approacheshave used a fixed granularity, i.e. the size of the partitioningobjects was fixed, we present a partitioning approach thatdynamically determines the partitioning granularity to adapt optimizationsteps to application properties and to intermediate optimizationresults. Experiments with simulated annealing optimizationshow a faster convergence and far better adaptability to costfunction variations than in previous experiments with fixed granularity.