Performance Prediction Model and Analysis for Compute-Intensive Tasks on GPUs

Abstract : Using Graphics Processing Units (GPUs) to solve general purpose problems has received significant attention both in academia and industry. Harnessing the power of these devices however requires knowledge of the underlying architecture and the programming model. In this paper, we develop analytical models to predict the performance of GPUs for computationally intensive tasks. Our models are based on varying the relevant parameters - including total number of threads, number of blocks, and number of streaming multi-processors - and predicting the performance of a program for a specified instance of these parameters. The approach can be used in the context of heterogeneous environments where distinct types of GPU devices with different hardware configurations are employed.
Type de document :
Communication dans un congrès
Ching-Hsien Hsu; Xuanhua Shi; Valentina Salapura. 11th IFIP International Conference on Network and Parallel Computing (NPC), Sep 2014, Ilan, Taiwan. Springer, Lecture Notes in Computer Science, LNCS-8707, pp.612-617, 2014, Network and Parallel Computing. 〈10.1007/978-3-662-44917-2_65〉
Liste complète des métadonnées

Littérature citée [8 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01403164
Contributeur : Hal Ifip <>
Soumis le : vendredi 25 novembre 2016 - 14:52:03
Dernière modification le : vendredi 1 décembre 2017 - 01:10:10
Document(s) archivé(s) le : mardi 21 mars 2017 - 11:55:04

Fichier

978-3-662-44917-2_65_Chapter.p...
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Khondker Hasan, Amlan Chatterjee, Sridhar Radhakrishnan, John Antonio. Performance Prediction Model and Analysis for Compute-Intensive Tasks on GPUs. Ching-Hsien Hsu; Xuanhua Shi; Valentina Salapura. 11th IFIP International Conference on Network and Parallel Computing (NPC), Sep 2014, Ilan, Taiwan. Springer, Lecture Notes in Computer Science, LNCS-8707, pp.612-617, 2014, Network and Parallel Computing. 〈10.1007/978-3-662-44917-2_65〉. 〈hal-01403164〉

Partager

Métriques

Consultations de la notice

209

Téléchargements de fichiers

47