Abstract. This paper describes a software architecture that allows image processing researchers to develop parallel applications in a transparent manner. The architecture’s main component is an extensive library of low level image processing operations that can be run on distributed memory MIMD-style parallel hardware. Since the library has an application programming interface identical to that of an existing sequential image library, all parallelism is completely hidden from the user. In this paper we give an overview of all architecture components, and show how issues related to automatic parallelization and optimization are dealt with by the application of domain specific performance models. Results obtained for a realistic application indicate that model-based optimization of a wide range of imaging software indeed is possible.
Frank J. Seinstra, Dennis Koelma, Jan-Mark Geusebr