Umeå universitets logga

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
General framework for re-assuring numerical reliability in parallel Krylov solvers: a case of bi-conjugate gradient stabilized methods
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Uppsala University, Uppsala, Sweden.
Sorbonne Université, CNRS, LIP6, Paris, France.
Universitat Jaime I, Castellón de la Plana, Spain.
2023 (Engelska)Ingår i: The international journal of high performance computing applications, ISSN 1094-3420, E-ISSN 1741-2846Artikel i tidskrift (Refereegranskat) Epub ahead of print
Abstract [en]

Parallel implementations of Krylov subspace methods often help to accelerate the procedure of finding an approximate solution of a linear system. However, such parallelization coupled with asynchronous and out-of-order execution often makes more visible the non-associativity impact in floating-point operations. These problems are even amplified when communication-hiding pipelined algorithms are used to improve the parallelization of Krylov subspace methods. Introducing reproducibility in the implementations avoids these problems by getting more robust and correct solutions. This paper proposes a general framework for deriving reproducible and accurate variants of Krylov subspace methods. The proposed algorithmic strategies are reinforced by programmability suggestions to assure deterministic and accurate executions. The framework is illustrated on the preconditioned BiCGStab method and its pipelined modification, which in fact is a distinctive method from the Krylov subspace family, for the solution of non-symmetric linear systems with message-passing. Finally, we verify the numerical behavior of the two reproducible variants of BiCGStab on a set of matrices from the SuiteSparse Matrix Collection and a 3D Poisson’s equation.

Ort, förlag, år, upplaga, sidor
Sage Publications, 2023.
Nyckelord [en]
accuracy, ExBLAS, HPC, Numerical reliability, PBiCGStab, pipelined PBiCGStab, reproducibility
Nationell ämneskategori
Beräkningsmatematik
Identifikatorer
URN: urn:nbn:se:umu:diva-216137DOI: 10.1177/10943420231207642Scopus ID: 2-s2.0-85174938956OAI: oai:DiVA.org:umu-216137DiVA, id: diva2:1809293
Tillgänglig från: 2023-11-02 Skapad: 2023-11-02 Senast uppdaterad: 2023-11-02

Open Access i DiVA

fulltext(6289 kB)22 nedladdningar
Filinformation
Filnamn FULLTEXT01.pdfFilstorlek 6289 kBChecksumma SHA-512
9afe48ac44912c2531ed4aeb83ce8e452f66bdd0532b4f9c102188cbce1724983952c4228264f57711927aa164bac9a2c9d5a276aeadfbe922ffcb2ff5a43ac5
Typ fulltextMimetyp application/pdf

Övriga länkar

Förlagets fulltextScopus

Person

Iakymchuk, Roman

Sök vidare i DiVA

Av författaren/redaktören
Iakymchuk, Roman
Av organisationen
Institutionen för datavetenskap
I samma tidskrift
The international journal of high performance computing applications
Beräkningsmatematik

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 22 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 76 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