Algebraic Multigrid on GPU
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21340%2F13%3A00210924" target="_blank" >RIV/68407700:21340/13:00210924 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Algebraic Multigrid on GPU
Original language description
This article deals with the method of algebraic multigrid and its parallelization on GPU. Algebraic multigrid is a sparse matrix iterative solver, which finds the solution by solving also restricted versions of the original problem. The main difference from more widely known geometric multigrid is that it can create the restricted problems without any knowledge about the matrix origin and therefore it can be used for larger range of problems. The article farther presents possibilities how to parallelizethis algorithm on multicore CPU architecture and on GPU. Finally it also shows speedup obtained by the GPU parallelization.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Doktorandské dny 2013
ISBN
978-80-01-05379-9
ISSN
—
e-ISSN
—
Number of pages
10
Pages from-to
123-132
Publisher name
Česká technika - nakladatelství ČVUT
Place of publication
Praha
Event location
Praha
Event date
Nov 15, 2013
Type of event by nationality
CST - Celostátní akce
UT code for WoS article
—