Polyhedral-Model Guided Loop-Nest Auto-Vectorization

Konrad Trifunović 1 Dorit Nuzman 2 Albert Cohen 1 Ayal Zaks 2 Ira Rosen 2
1 ALCHEMY - Architectures, Languages and Compilers to Harness the End of Moore Years
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France
Abstract : Optimizing compilers apply numerous inter- dependent optimizations, leading to the notoriously difficult phase-ordering problem -- that of deciding which trans- formations to apply and in which order. Fortunately, new infrastructures such as the polyhedral compilation framework host a variety of transformations, facilitating the efficient explo- ration and configuration of multiple transformation sequences. Many powerful optimizations, however, remain external to the polyhedral framework, including vectorization. The low-level, target-specific aspects of vectorization for fine-grain SIMD has so far excluded it from being part of the polyhedral framework. In this paper we examine the interactions between loop transformations of the polyhedral framework and subsequent vectorization. We model the performance impact of the dif- ferent loop transformations and vectorization strategies, and then show how this cost model can be integrated seamlessly into the polyhedral representation. This predictive modelling facilitates efficient exploration and educated decision making to best apply various polyhedral loop transformations while considering the subsequent effects of different vectorization schemes. Our work demonstrates the feasibility and benefit of tuning the polyhedral model in the context of vectorization. Experimental results confirm that our model has accurate predictions, providing speedups of over 2.0x on average over traditional innermost-loop vectorization on PowerPC970 and Cell-SPU SIMD platforms.
Type de document :
Communication dans un congrès
The 18th International Conference on Parallel Architectures and Compilation Techniques, Sep 2009, Raleigh, United States. 2009
Liste complète des métadonnées

Littérature citée [21 références]  Voir  Masquer  Télécharger

Contributeur : Albert Cohen <>
Soumis le : dimanche 27 novembre 2011 - 21:16:02
Dernière modification le : jeudi 11 janvier 2018 - 06:22:13
Document(s) archivé(s) le : vendredi 16 novembre 2012 - 12:10:09


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-00645325, version 1



Konrad Trifunović, Dorit Nuzman, Albert Cohen, Ayal Zaks, Ira Rosen. Polyhedral-Model Guided Loop-Nest Auto-Vectorization. The 18th International Conference on Parallel Architectures and Compilation Techniques, Sep 2009, Raleigh, United States. 2009. 〈hal-00645325〉



Consultations de la notice


Téléchargements de fichiers