Understanding the Performances of SMVP on Multiprocessor Platform - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Understanding the Performances of SMVP on Multiprocessor Platform

Résumé

Sparse Matrix Vector Product (SMVP) is an important kernel in many scientific applications. In this paper we study the performances of this kernel on multiprocessor platform using four different compression format (CSR, CSC, ELL and COO). Our aim is to extract runtime environment parameters, matrix characteristics and algorithm parameters that impact performances. This work is in the context of implementing an auto-tuner system for Optimal sparse Compression Format (OCF) selection.
Fichier non déposé

Dates et versions

hal-01863729 , version 1 (29-08-2018)

Identifiants

  • HAL Id : hal-01863729 , version 1

Citer

Ichrak Mehrez, Olfa Hamdi-Larbi, Thomas Dufaud, Nahid Emad. Understanding the Performances of SMVP on Multiprocessor Platform. The 2018 International Conference on Parallel and Distributed Processing Techniques & Applications PDPTA'18, Jul 2018, Las Vegas, United States. ⟨hal-01863729⟩
85 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More