Coarse-Grained Loop Parallelization: Iteration Space Slicing vs Affine Transformations - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2009

Coarse-Grained Loop Parallelization: Iteration Space Slicing vs Affine Transformations

Abstract

Automatic coarse-grained parallelization of pro- gram loops is of great importance for multi-core computing systems. This paper presents a comparison of Iteration Space Slicing and Affine Transformation Framework algorithms aimed at extracting coarse-grained parallelism available in arbitrarily nested parameterized affine loops. We demonstrate that Iteration Space Slicing permits for extracting more coarse-grained paral- lelism in comparison to the Affine Transformation Framework. Experimental results show that by means of Iteration Space Slicing algorithms, we are able to extract coarse-grained paral- lelism for most loops of the NAS and UTDSP benchmarks, and that there is a strong need in devising advanced algorithms for calculating the exact transitive closure of dependence relations in order to increase the applicability of that framework.
Fichier principal
Vignette du fichier
ISPDC_2009.pdf (221.71 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00645329 , version 1 (27-11-2011)

Identifiers

  • HAL Id : hal-00645329 , version 1

Cite

Anna Beletska, Wlodzirmierz Bielecki, Albert Cohen, Marek Palkowski, Krzysztof Siedlecki. Coarse-Grained Loop Parallelization: Iteration Space Slicing vs Affine Transformations. The 11th International Symposium on Parallel and Distributed Computing, Jul 2009, Munich, Germany. ⟨hal-00645329⟩
236 View
496 Download

Share

Gmail Facebook X LinkedIn More