Petri Net Based Cyclic Scheduling

Loop scheduling is particularly importantwhendesigning efficient compilers for parallel architectures. In this article a cyclic schedule of nonpreemptive tasks with precedence constraints and no communication delays on an unlimited number of identical processors will be proposed. In addition an attempt is made to minimize the number of processors used without releasing the time-optimality condition. In order to better understand the nature of the problem the terms data parallelism and structural parallelism are clarified first