Reducing code size in scheduling synchronous dataflow graphs on multicore systems

A Synchronous Dataflow Graph (SDFG) is a widely used abstraction to capture the characteristics of a number of applications often running on embedded systems. When scheduling/mapping an SDFG on a multicore embedded system, the code of tasks may have to be duplicated onto multiple cores to fully utilize the parallelism of the multicore system. However, such an approach may increase the overall code size in the system, which may not be desirable. This paper proposes a code-size-aware scheduling heuristic, which decreases code duplication of SDFGs on multicore systems, hence minimizing overall code size while not affecting throughput. In experiments, the proposed heuristic achieves significant code size reduction for all the tested SDFGs compared with a state-of-art recently proposed scheduling algorithm.