About: TFETI coarse problem massively parallel implementation     Goto   Sponge   NotDistinct   Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

AttributesValues
rdf:type
Description
  • 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 the master core for large scale problems. In this paper, we compare main strategies focusing on process of TFETI massively parallel implementation of the coarse problem and discuss some details of our FLLOP (Feti Light Layer on Petsc) implementation concerning computational and programming effectiveness for more complex engineering problems.
  • 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 the master core for large scale problems. In this paper, we compare main strategies focusing on process of TFETI massively parallel implementation of the coarse problem and discuss some details of our FLLOP (Feti Light Layer on Petsc) implementation concerning computational and programming effectiveness for more complex engineering problems. (en)
Title
  • TFETI coarse problem massively parallel implementation
  • TFETI coarse problem massively parallel implementation (en)
skos:prefLabel
  • TFETI coarse problem massively parallel implementation
  • TFETI coarse problem massively parallel implementation (en)
skos:notation
  • RIV/61989100:27740/12:86084416!RIV13-MSM-27740___
http://linked.open...avai/riv/aktivita
http://linked.open...avai/riv/aktivity
  • P(ED1.1.00/02.0070), S
http://linked.open...vai/riv/dodaniDat
http://linked.open...aciTvurceVysledku
http://linked.open.../riv/druhVysledku
http://linked.open...iv/duvernostUdaju
http://linked.open...titaPredkladatele
http://linked.open...dnocenehoVysledku
  • 174168
http://linked.open...ai/riv/idVysledku
  • RIV/61989100:27740/12:86084416
http://linked.open...riv/jazykVysledku
http://linked.open.../riv/klicovaSlova
  • TFETI; Natural coarse space matrix; FETI; Domain decomposition; Coarse problem (en)
http://linked.open.../riv/klicoveSlovo
http://linked.open...ontrolniKodProRIV
  • [DEDD7DD3337E]
http://linked.open...v/mistoKonaniAkce
  • Vídeň
http://linked.open...i/riv/mistoVydani
  • Vienna
http://linked.open...i/riv/nazevZdroje
  • ECCOMAS 2012 - European Congress on Computational Methods in Applied Sciences and Engineering, e-Book Full Papers
http://linked.open...in/vavai/riv/obor
http://linked.open...ichTvurcuVysledku
http://linked.open...cetTvurcuVysledku
http://linked.open...vavai/riv/projekt
http://linked.open...UplatneniVysledku
http://linked.open...iv/tvurceVysledku
  • Horák, David
  • Hapla, Václav
http://linked.open...vavai/riv/typAkce
http://linked.open.../riv/zahajeniAkce
number of pages
http://purl.org/ne...btex#hasPublisher
  • Vienna University of Technology
https://schema.org/isbn
  • 978-3-9503537-0-9
http://localhost/t...ganizacniJednotka
  • 27740
Faceted Search & Find service v1.16.118 as of Jun 21 2024


Alternative Linked Data Documents: ODE     Content Formats:   [cxml] [csv]     RDF   [text] [turtle] [ld+json] [rdf+json] [rdf+xml]     ODATA   [atom+xml] [odata+json]     Microdata   [microdata+json] [html]    About   
This material is Open Knowledge   W3C Semantic Web Technology [RDF Data] Valid XHTML + RDFa
OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 82 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software