Toward an automatic mapping of DSP algorithms onto parallel processors

With ever increasing computational requirements of complex DSP algorithms and applications, implementation on multiprocessor platforms becomes a necessity. The main problem is lack of necessary software tools for multiprocessor mapping. We present the main features of a prototype design environment which allows direct mapping of complex DSP applications, designed for implementation on a single processor, onto a multiprocessor platform. We currently use a configurable network of MIMD machines but essentially any platform and interconnection topology can be specified by the user. Experimental results are presented and discussed for automatic mapping of an adaptive differential pulse code modulation (ADPCM) system to a multiprocessor platform with different number of processors and interconnection topologies.