We present a methodology for the exploration of signal processing architect
ures at the system level. The methodology, named SPADE, provides a means to
quickly build models of architectures at an abstract level, to easily map
applications, modeled as Kahn Process Networks, onto these architecture mod
els, and to analyze the performance of the resulting system by simulation.
The methodology distinguishes between applications and architectures, and u
ses a trace-driven simulation technique for co-simulation of application mo
dels and architecture models. As a consequence, architecture models need no
t be functionally complete to be used for performance analysis while data d
ependent behavior is still handled correctly. We have used the methodology
for the exploration of architectures and mappings of an MPEG-2 video decode
r application.