Iterative Krylov Methods for Acoustic Problems on Graphics Processing Unit

Author

Cherik Ahamed, Abal-Kassim ; Magoules, Frederic

Author_Institution

Appl. Math. & Syst. Lab., Ecole Centrale Paris, Paris, France

fYear

2014

fDate

24-27 Nov. 2014

Firstpage

19

Lastpage

23

Abstract

This paper deals with linear algebra operations on Graphics Processing Unit (GPU) with complex number arithmetic using double precision. An analysis of their uses within iterative Krylov methods is presented to solve acoustic problems. Numerical experiments performed on a set of acoustic matrices arising from the modelisation of acoustic phenomena inside a car compartment are collected, and outline the performance, robustness and effectiveness of our algorithms, with a speed-up up to 28x for dot product, 9.8x for sparse matrix-vector product and solvers.

Keywords

acoustic signal processing; computer graphics; graphics processing units; iterative methods; matrix algebra; GPU; acoustic matrices; acoustic phenomena modelisation; acoustic problems; car compartment; complex number arithmetic; dot product; double precision; graphics processing unit; iterative Krylov methods; linear algebra operations; sparse matrix-vector product; Acoustics; Equations; Graphics processing units; Iterative methods; Mathematical model; Sparse matrices; Vectors; Acoustic; CSR matrix; CUDA; GPU; Helmholtz equation; Iterative Krylov methods; Linear algebra; Parallel computing;

fLanguage

English

Publisher

ieee

Conference_Titel

Distributed Computing and Applications to Business, Engineering and Science (DCABES), 2014 13th International Symposium on

Conference_Location

Xian Ning

Print_ISBN

978-1-4799-4170-4

Type

conf

DOI

10.1109/DCABES.2014.7

Filename

6999048