Distributed Memory Allocation Technique for Synchronous Dataflow Graphs - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

Distributed Memory Allocation Technique for Synchronous Dataflow Graphs


This paper introduces a new distributed memory allocation technique for applications modeled with Synchronous Dataflow (SDF) graphs. This technique builds on a State-of-the-Art shared memory allocation technique based on a weighted graph, called Memory Exclusion Graph (MEG). A MEG captures the memory reuse opportunities between memory objects that must be allocated before the execution of an SDF graph. The algorithms detailed in this paper enable a single MEG to be split into separate MEGs, each of which is associated with a memory bank accessible only by one core of the architecture. The proposed technique is implemented within a rapid prototyping framework and is evaluated by deploying real computer vision applications on a Multiprocessor System-on-Chip (MPSoC). Results show a systematic performance improvement due to better memory usage, with application speedups ranging from 2% up to 380%.
Fichier principal
Vignette du fichier
20161026-SiPS16_Desnos.pdf (436.03 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01390486 , version 1 (02-11-2016)



Karol Desnos, Maxime Pelcat, Jean-François Nezan, Slaheddine Aridhi. Distributed Memory Allocation Technique for Synchronous Dataflow Graphs. 2016 IEEE International Workshop on Signal Processing Systems, IEEE; IEEE Signal Processing Society; IEEE CAS, Oct 2016, Dallas, TX, United States. ⟨10.1109/SiPS.2016.16⟩. ⟨hal-01390486⟩
193 View
275 Download



Gmail Facebook Twitter LinkedIn More