umu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
A novel parallel QR algorithm for hybrid distributed memory HPC systems
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. (eSSENCE, UMIT, Parallel and Scientific Computing, HPC2N)
2010 (Engelska)Ingår i: SIAM Journal on Scientific Computing, ISSN 1064-8275, E-ISSN 1095-7197, Vol. 32, nr 4, s. 2345-2378Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

A novel variant of the parallel QR algorithm for solving dense nonsymmetric eigenvalue problems on hybrid distributed high performance computing systems is presented. For this purpose, we introduce the concept of multiwindow bulge chain chasing and parallelize aggressive early deflation. The multiwindow approach ensures that most computations when chasing chains of bulges are performed in level 3 BLAS operations, while the aim of aggressive early deflation is to speed up the convergence of the QR algorithm. Mixed MPI-OpenMP coding techniques are utilized for porting the codes to distributed memory platforms with multithreaded nodes, such as multicore processors. Numerous numerical experiments confirm the superior performance of our parallel QR algorithm in comparison with the existing ScaLAPACK code, leading to an implementation that is one to two orders of magnitude faster for sufficiently large problems, including a number of examples from applications.

Ort, förlag, år, upplaga, sidor
Society for industrial and applied mathematics (SIAM) , 2010. Vol. 32, nr 4, s. 2345-2378
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
URN: urn:nbn:se:umu:diva-50997DOI: 10.1137/090756934ISI: 000280771100030OAI: oai:DiVA.org:umu-50997DiVA, id: diva2:472934
Tillgänglig från: 2012-01-04 Skapad: 2012-01-04 Senast uppdaterad: 2018-06-08Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltext

Personposter BETA

Kågström, Bo

Sök vidare i DiVA

Av författaren/redaktören
Kågström, Bo
Av organisationen
Institutionen för datavetenskap
I samma tidskrift
SIAM Journal on Scientific Computing
Datavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 272 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf