Reducing Memory Requirements of Stream Programs by Graph Transformations

Pablo de Oliveira Castro (1) , Stéphane Louise (1) , Denis Barthou (2, 3)

1 LIST (CEA) - Laboratoire d'Intégration des Systèmes et des Technologies
2 LaBRI - Laboratoire Bordelais de Recherche en Informatique
3 RUNTIME - Efficient runtime systems for parallel architectures

Stream languages explicitly describe fork-join parallelism and pipelines, offering a powerful programming model for many-core Multi-Processor Systems on Chip (MPSoC). In an embedded resource-constrained system, adapting stream programs to fit memory requirements is particularly important. In this paper we present a new approach to re- duce the memory footprint required to run stream programs on MPSoC. Through an exploration of equivalent program variants, the method selects parallel code minimizing mem- ory consumption. For large program instances, a heuristic accelerating the exploration phase is proposed and evalu- ated. We demonstrate the interest of our method on a panel of ten significant benchmarks. Using a multi-core modulo scheduling technique, our approach lowers considerably the minimal amount of memory required to run seven of these benchmarks while preserving throughput.

Mots clés: Graph Transformations; Stream Languages; Data Flow; Mem- ory; Graph Transformations.

Domaines: Calcul parallèle, distribué et partagé [cs.DC]

Pablo de Oliveira Castro, Stéphane Louise, Denis Barthou. Reducing Memory Requirements of Stream Programs by Graph Transformations. International IEEE Conference on High Performance Computing and Simulation, Jun 2011, Caen, France. p171-180, ⟨10.1109/HPCS.2010.5547134⟩. ⟨hal-00551584⟩