Enhancing the Performance of Conjugate Gradient Solvers on Graphic Processing Units

Author

Dehnavi, Maryam Mehri ; Fernández, David M. ; Giannacopoulos, Dennis

Author_Institution

Electr. & Comput. Eng. Dept., McGill Univ. Montreal, Montreal, QC, Canada

Volume

47

Issue

5

fYear

2011

fDate

5/1/2011 12:00:00 AM

Firstpage

1162

Lastpage

1165

Abstract

A study of the fundamental obstacles to accelerate the preconditioned conjugate gradient (PCG) method on modern graphic processing units (GPUs) is presented and several techniques are proposed to enhance its performance over previous work independent of the GPU generation and the matrix sparsity pattern. The proposed enhancements increase the performance of PCG up to 23 times compared to vector optimized PCG results on modern CPUs and up to 3.4 times compared to previous GPU results.

Keywords

computer graphic equipment; conjugate gradient methods; coprocessors; parallel processing; sparse matrices; CPU; GPU generation; fundamental obstacle; graphic processing unit; matrix sparsity pattern; preconditioned conjugate gradient method; vector optimized PCG; Acceleration; Computer architecture; Graphics processing unit; Instruction sets; Kernel; Optimization; Sparse matrices; Computer architecture; conjugate gradients (CGs); graphic processing units (GPUs); parallel processing;

fLanguage

English

Journal_Title

Magnetics, IEEE Transactions on

Publisher

ieee

ISSN

0018-9464

Type

jour

DOI

10.1109/TMAG.2010.2081662

Filename

5754727