Branch Strategies to Optimize Decision Trees for Wide-Issue Architectures - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2004

Branch Strategies to Optimize Decision Trees for Wide-Issue Architectures

Résumé

Branch predictors are associated with critical design issues for nowadays instruction greedy processors. We study two important domains where the optimization of decision trees — implemented through switch - case or nested if - then - else constructs — makes the precise modeling of these hardware mechanisms determining for performance: compute-intensive libraries with versioning and cloning, and high-performance interpreters. Against common belief, the complexity of recent microarchitectures does not necessarily hamper the design of accurate cost models, in the special case of decision trees. We build a simple model that illustrates the reasons for which decision tree performance is predictable. Based on this model, we compare the most significant code generation strategies on the Itanium2 processor. We show that no strategy dominates in all cases, and although they used to be penalized by traditional superscalar processors, indirect branches regain a lot of interest in the context of predicated execution and delayed branches. We validate our study with an improvement from 15% to 40% over Intel ICC compiler for a Daxpy code focused on short vectors.
Fichier principal
Vignette du fichier
paper31.pdf (204.78 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01257303 , version 1 (17-01-2016)

Identifiants

  • HAL Id : hal-01257303 , version 1

Citer

Patrick Carribault, Christophe Lemuet, Jean-Thomas Acquaviva, Albert Cohen, William Jalby. Branch Strategies to Optimize Decision Trees for Wide-Issue Architectures. Languages and Compilers for Parallel Computing (LCPC), Sep 2004, West Lafayette, Indiana, United States. ⟨hal-01257303⟩

Collections

CNRS UVSQ
33 Consultations
144 Téléchargements

Partager

Gmail Facebook X LinkedIn More