Massively Parallel Computing Systems with Real Time Constraints the \algorithm Architecture Adequation" Methodology

Massively Parallel Computing Systems (MPCS) provide high performance computing generally used to accelerate numerical computation applications. We present a methodology called \Algorithm Architecture Adequation" used to take advantage of the computation power of these systems in the case of real-time applications. With this methodology, application algorithm as well as MPCS are speciied with graphs, then the implementation of an algorithm on a MPCS in respect with real-time constraints may be formalized in terms of graphs transformations. This allows to optimize, taking into account inter-processor communications which are critical, the real-time performances of the implementation. As a result, real-time distributed executives are produced automatically without deadlock and with minimum overhead. This reduces drastically the development cycle of real-time applications running on MPCS.