The popularity of GPGPUs in high performance platforms for scientific computing in recent times has renewed interest in approximate inverse preconditioners for Krylov methods. We have recently introduced some new algorithmic variants [6] of popular approximate inverse methods. We now report on the behaviour of these variations in high performance multilevel preconditioning frameworks, and we present the software framework that enables

Bertaccini, D., Filippone, S. (2014). Approximate Inverse Preconditioners for Krylov Methods on Heterogeneous Parallel Computers. In A.B. M. Bader (a cura di), Parallel Computing: Accelerating Computational Science and Engineering (CSE). ADVANCES IN PARALLEL COMPUTING (pp. 183-192). IOS Press [10.3233/978-1-61499-381-0-183].

Approximate Inverse Preconditioners for Krylov Methods on Heterogeneous Parallel Computers

BERTACCINI, DANIELE;FILIPPONE, SALVATORE
2014-01-01

Abstract

The popularity of GPGPUs in high performance platforms for scientific computing in recent times has renewed interest in approximate inverse preconditioners for Krylov methods. We have recently introduced some new algorithmic variants [6] of popular approximate inverse methods. We now report on the behaviour of these variations in high performance multilevel preconditioning frameworks, and we present the software framework that enables
2014
Settore MAT/08 - ANALISI NUMERICA
English
Rilevanza internazionale
Capitolo o saggio
Sparse Matrix Computations, Krylov subspace methods, Approximate inversese, preconditioners, Object-oriented programming, Design patterns.
Referee anonimi; anonymous referees
http://www.ebooks.iospress.nl/volumearticle/35880
Bertaccini, D., Filippone, S. (2014). Approximate Inverse Preconditioners for Krylov Methods on Heterogeneous Parallel Computers. In A.B. M. Bader (a cura di), Parallel Computing: Accelerating Computational Science and Engineering (CSE). ADVANCES IN PARALLEL COMPUTING (pp. 183-192). IOS Press [10.3233/978-1-61499-381-0-183].
Bertaccini, D; Filippone, S
Contributo in libro
File in questo prodotto:
File Dimensione Formato  
PArCO2013 - mlainv-hyb.pdf

solo utenti autorizzati

Descrizione: Authors' final version
Licenza: Copyright dell'editore
Dimensione 123.66 kB
Formato Adobe PDF
123.66 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2108/96771
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 5
social impact