Optimum and heuristic data path scheduling under resource constraints

This paper presents an integer linear programming model for the scheduling problem in high level synthesis under resource constraints. Extensive consideration is given to the following applications: <list><item>Multi-cycle operations with <list><item>non-pipelined function units, </item><item>pipelined function units; </item></list></item><item>Mutually exclusive operations; </item><item>Functional pipelining; </item><item>Loop folding; </item><item>Scheduling under bus constraint. </item></list>Using this model, we are able to solve all the benchmarks in the literature optimally in a few seconds. Besides the model, a new technique, called <italic>Zone Scheduling (ZS)</italic>, is proposed to solve large size problems. ZS partitions the distribution graph into several zones and solves sequentially the problems contained. A novel feature of this technique is that it schedules more than one control step at a time, allowing us to take a more global view of a scheduling problem.