TFETI coarse problem massively parallel implementation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F12%3A86084416" target="_blank" >RIV/61989100:27240/12:86084416 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/61989100:27740/12:86084416

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

TFETI coarse problem massively parallel implementation

Popis výsledku v původním jazyce

Most of computations (subdomains problems) appearing in FETI-type methods are purely local and therefore parallelizable without any data transfers. However, if we want to accelerate also dual actions, some communication is needed due to primal-dual transition. Distribution of primal matrices is quite straightforward. Each of cores works with local part associated with its subdomains. Natural effort using the massively parallel computers is to maximize number of subdomains so that sizes of subdomain stiffness matrices are reduced which accelerates their factorization and subsequent pseudoinverse application, which belong to the most time consuming actions. On the other hand, negative effect of that is an increase of null space dimension and number of Lagrange multipliers on subdomains interfaces, i.e. dual dimension, so that the bottleneck of the TFETI method is the application of the projector, especially its part - so called coarse problem, which can be hardly solved sequentially on t

Název v anglickém jazyce

TFETI coarse problem massively parallel implementation

Popis výsledku anglicky

Most of computations (subdomains problems) appearing in FETI-type methods are purely local and therefore parallelizable without any data transfers. However, if we want to accelerate also dual actions, some communication is needed due to primal-dual transition. Distribution of primal matrices is quite straightforward. Each of cores works with local part associated with its subdomains. Natural effort using the massively parallel computers is to maximize number of subdomains so that sizes of subdomain stiffness matrices are reduced which accelerates their factorization and subsequent pseudoinverse application, which belong to the most time consuming actions. On the other hand, negative effect of that is an increase of null space dimension and number of Lagrange multipliers on subdomains interfaces, i.e. dual dimension, so that the bottleneck of the TFETI method is the application of the projector, especially its part - so called coarse problem, which can be hardly solved sequentially on t

Druh

D - Stať ve sborníku

CEP obor

BA - Obecná matematika

OECD FORD obor

—

Projekt

<a href="/cs/project/ED1.1.00%2F02.0070" target="_blank" >ED1.1.00/02.0070: Centrum excelence IT4Innovations</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2012

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

ECCOMAS 2012 - European Congress on Computational Methods in Applied Sciences and Engineering, e-Book Full Papers

ISBN

978-3-9503537-0-9

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

8260-8267

Název nakladatele

Vienna University of Technology

Místo vydání

Vienna

Místo konání akce

Vídeň

Datum konání akce

10. 9. 2012

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—