DocumentCode
579033
Title
A GPU Implementation of the SIP Method
Author
Igounet, P. ; Alfaro, P. ; Pedemonte, M. ; Ezzatti, Pablo
Author_Institution
Inst. de Comput., Univ. de la Republica, Montevideo, Uruguay
fYear
2011
fDate
9-11 Nov. 2011
Firstpage
195
Lastpage
201
Abstract
This article presents the implementation of the Strongly Implicit Procedure (SIP) to resolve penta-diagonal linear systems on a GPU in order to improve its computational efficiency. In particular, two different implementations of the SIP method on a GPU are presented and discussed. The experimental evaluation of the proposed methods demonstrates that a significant reduction on the runtime can be attained (acceleration values up to 4x ) when compared with both serial and parallel CPU implementations.
Keywords
digital arithmetic; graphics processing units; linear systems; GPU implementation; SIP method; parallel CPU implementations; penta-diagonal linear systems; serial CPU implementations; strongly implicit procedure; Central Processing Unit; Graphics processing units; Instruction sets; Kernel; Multicore processing; Runtime; GPU; SIP; penta-diagonal linear system solver;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Science Society (SCCC), 2011 30th International Conference of the Chilean
Conference_Location
Curico
ISSN
1522-4902
Print_ISBN
978-1-4673-1364-3
Type
conf
DOI
10.1109/SCCC.2011.26
Filename
6363398
Link To Document