,
ICPM'2011

Experimental grid for numerical linear algebra
Author: Ivan Šimeček, Filip Šimek
Keywords

grid, GPGPU, numerical linear algebra


Abstract

Plenty of numerical algebra libraries have been developed in recent years. These libraries are tuned for the given CPU and its memory architecture, fully utilize its memory hierarchy and inner pipelines and achieve impressive computation power. There is also a new trend in the high-performance computing: GPU computing. This paper describes a new concept of the new heterogeneous grid for the numerical linear algebra computing with maximal ratio between prize and computational power. It allows a parallelization of scientific codes with minimal programming effort.

 

Download:
final version (in .PDF format)

BibTex entry:
@inproceedings{JA_ICPM11a,
author = {{\v S}ime{\v c}ek, I. and {\v S}imek, F.},
title = {{GPU cluster for acceleration of computations}},
booktitle = {{Proceedings of International Conference PRESENTATION of MATHEMATICS '11}},
publisher = {Technical University},
address = {Liberec},
year = {2011},
pages = {125--130},
ISBN = {978-80-7372-773-4},
language = {English}
}

BACK