{ This paper describes the use of Unied System Construction tools under development at the University of Southern California. The goal of the project is to automate the construction of heterogeneous, applicationspecic systems. Key elements of the USC system include multiprocessor synthesis, multi-chip datapath synthesis, memory-intensive synthesis, and multi-chip partitioning. The tools were applied to design of an image compression chip set, and results of using these tools are reported on here. Our results are c omparable to manual designs reported in the literature.

No abstract

In this paper, we present a mathematical programming model f o r finding sub-optimal assignment of a given application task onto a heterogeneous suite of computers. The proposed model is based on the Cluster-M heterogeneous programming paradigm. Using Cluster-M, an application task is represented in f o r m of a Cluster-M Specification which indicates all the concurrent and communicating subtasks at every step of computation. These Specifications are then t o be mapped onto the underlying heterogeneous suite of computers represented in a Cluster-M Representation format. To map every step of Cluster-M Specification onto the Cluster-M Representation of the heterogeneous suite, we propose t o use an optimal synthesis technique called SOS. We formulate and solve each of the mapping steps in form of a Mixed Integer Linear Programming model. This leads t o a very fast suboptimal selection and mapping solution.