Taking advantage of GPU/CPU architectures for sparse Conjugate Gradient solver computation

Solving large sparse linear systems is a time and energy consuming process. This paper presents an efficient exploitation of graphic processing units (GPUs) for accelerating Conjugate Gradient iterative solver (CG). We use the high-level software library PARALUTION for sparse linear algebra on multi...

Full description

Saved in:
Bibliographic Details
Published in2015 Third World Conference on Complex Systems (WCCS) pp. 1 - 5
Main Authors Kasmi, Najlae, Zbakh, Mostapha, Mahmoudi, Sidi Ahmed, Manneback, Pierre
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.11.2015
Subjects
Computer architecture
Conjugate Gradient
CUDA
GPU
Graphics processing units
Hardware
Instruction sets
Kernel
Libraries
Linear systems
OpenCL
PARALUTION
Sparse linear algebra
Online AccessGet full text

Cover

More Information
Summary:Solving large sparse linear systems is a time and energy consuming process. This paper presents an efficient exploitation of graphic processing units (GPUs) for accelerating Conjugate Gradient iterative solver (CG). We use the high-level software library PARALUTION for sparse linear algebra on multi/many-core systems, which supports GPU (with CUDA and OpenCL) and Multi-CPU implementations of CG method using different storage formats. We discuss and compare performance using three platforms.
DOI:10.1109/ICoCS.2015.7483268