J Sign Process Syst DOI 10.1007/s11265-014-0956-2 Scheduling of Parallelized Synchronous Dataflow Actors for Multicore Signal Processing Zheng Zhou · William Plishker · Shuvra S. Bhattacharyya · Karol Desnos · Maxime Pelcat · Jean-Francois Nezan Received: 10 February 2014 / Revised: 10 August 2014 / Accepted: 16 September 2014 © Springer Science+Business Media New York 2014 Abstract Parallelization of Digital Signal Processing (DSP) software is an important trend in Multiproces- sor System-on-Chip (MPSoC) implementation. The perfor- mance of DSP systems composed of parallelized computa- tions depends on the scheduling technique, which must in general allocate computation and communication resources for competing tasks, and ensure that data dependencies are satisfied. In this paper, we formulate a new type of parallel task scheduling problem called Parallel Actor Schedul- ing (PAS) for MPSoC mapping of DSP systems that are Z. Zhou () Texas Instruments, Germantown, MD, USA e-mail: z-zhou@ti.com W. Plishker · S.S. Bhattacharyya Department of ECE and UMIACS, University of Maryland, Col- lege Park, USA W. Plishker e-mail: plishker@umd.edu S.S. Bhattacharyya e-mail: ssb@umd.edu K. Desnos · M. Pelcat · J.-F. Nezan IETR, INSA Rennes, CNRS UMR 6164, UEB, Rennes, France W. Plishker e-mail: karol.desnos@insa-rennes.fr M. Pelcat e-mail: Maxime.Pelcat@insa-rennes.fr J.-F. Nezan e-mail: jean-francois.nezan@insa-rennes.fr represented as Synchronous Dataflow (SDF) graphs. In contrast to traditional SDF-based scheduling techniques, which focus on exploiting graph level (inter-actor) paral- lelism, the PAS problem targets the integrated exploitation of both intra- and inter-actor parallelism for platforms in which individual actors can be parallelized across multi- ple processing units. We first address a special case of the PAS problem in which all of the actors in the DSP appli- cation or subsystem being optimized are parallel actors (i.e., they can be parallelized to exploit multiple cores). For this special case, we develop and experimentally eval- uate a two-phase scheduling framework with three work flows that involve particle swarm optimization (PSO) — PSO with a mixed integer programming formulation, PSO with simulated annealing, and PSO with a fast heuristic based on list scheduling. Then, we extend our schedul- ing framework to support the general PAS problem, which considers both parallel actors and sequential actors (actors that cannot be parallelized) in an integrated manner. We demonstrate that our PAS-targeted scheduling framework provides a useful range of trade-offs between synthesis time requirements and the quality of the derived solutions. We also demonstrate the performance of our scheduling frame- work from two aspects: simulations on a diverse set of randomly generated SDF graphs, and implementations of an image processing application and a software defined radio benchmark on a state-of-the-art multicore DSP platform. Keywords Multicore processors · Digital signal processors · Synchronous dataflow · Dataflow modeling · Software synthesis