Relaxed Subgraph Execution Model for the Throughput Evaluation of IBSDF Graphs

Hamza Deroui (1) , Karol Desnos (1) , Jean-François Nezan (1) , Alix Munier-Kordon (2)

1 IETR - Institut d'Électronique et des Technologies du numéRique
2 ALSOC - Architecture et Logiciels pour Systèmes Embarqués sur Puce

The Interface-Based Synchronous Dataflow (IBSDF) Model of Computation (MoC) is a hierarchical extension of the well-known Synchronous Dataflow (SDF) MoC. The IBSDF model extends the semantics of the SDF model by introducing a graph composition mechanism based on hierarchical interfaces. The IBSDF model introduces also execution rules to ease the analysis of the IBSDF graph such as evaluating the throughput; an essential key performance to evaluate when designing Digital Signal Processing (DSP) systems. However, respecting the execution rules may slow down the execution of IBSDF graphs, and so stop the applications to reach their maximum throughput. This article presents first how to speed-up the execution of an IBSDF graph by relaxing the execution rules. Second, a new method to compute the throughput of IBSDF graphs under a relaxed execution. Finally, a performance comparison between the proposed method and basic methods that rely on a transformation of the IBSDF graph to an equivalent non-hierarchical graph of potentially exponential size. The proposed method outperforms basic methods and makes it possible to evaluate the maximum throughput of large IBSDF graphs in less than 2 seconds.

Mots clés: Throughput evaluation; Interface-Based Synchronous Data Flow; Synchronous data flow; Throughput analysis; Scheduling Algorithm

Domaines: Systèmes embarqués; Calcul parallèle, distribué et partagé [cs.DC]; Performance et fiabilité [cs.PF]; Traitement du signal et de l'image [eess.SP]; Modélisation et simulation

Hamza Deroui, Karol Desnos, Jean-François Nezan, Alix Munier-Kordon. Relaxed Subgraph Execution Model for the Throughput Evaluation of IBSDF Graphs. International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS), Jul 2017, SAMOS, Greece. ⟨10.1109/SAMOS.2017.8344630⟩. ⟨hal-01569593⟩