Iterative sparse matrix-vector multiplication for accelerating the block Wiedemann algorithm over GF(2) on multi-graphics processing unit systems

Publikationstyp:
Zeitschriftenaufsatz
Metadaten:
Autoren
Autoren-URL
https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=fis-test-1&SrcAuth=WosAPI&KeyUT=WOS:000316230900013&DestLinkType=FullRecord&DestApp=WOS_CPL
DOI
10.1002/cpe.2896
eISSN
1532-0634
Externe Identifier
  • Clarivate Analytics Document Solution ID: 107PQ
ISSN
1532-0626
Ausgabe der Veröffentlichung
4
Zeitschrift
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
Schlüsselwörter
  • SpMV
  • CUDA
  • block Wiedemann
  • RSA
  • number field sieve
  • factorization
Paginierung
586 - 603
Datum der Veröffentlichung
2013
Status
Published
Titel
Iterative sparse matrix-vector multiplication for accelerating the block Wiedemann algorithm over GF(2) on multi-graphics processing unit systems
Sub types
  • Article
Ausgabe der Zeitschrift
25

Datenquelle: Web of Science (Lite)

Andere Metadatenquellen:
Abstract
<jats:title>SUMMARY</jats:title><jats:p>The block Wiedemann (BW) algorithm is frequently used to solve sparse linear systems over GF(2). Iterative sparse matrix–vector multiplication is the most time‐consuming operation. The necessity to accelerate this step is motivated by the application of BW to very large matrices used in the linear algebra step of the number field sieve (NFS) for integer factorization. In this paper, we derive an efficient CUDA implementation of this operation by using a newly designed hybrid sparse matrix format. This leads to speedups between 4 and 8 on a single graphics processing unit (GPU) for a number of tested NFS matrices compared with an optimized multicore implementation. We further present a GPU cluster implementation of the full BW for NFS matrices. A small‐sized GPU cluster is able to outperform CPU clusters of larger size for large matrices such as the one obtained from the Kilobit special NFS factorization. Copyright © 2012 John Wiley &amp; Sons, Ltd.</jats:p>
Autoren
DOI
10.1002/cpe.2896
eISSN
1532-0634
ISSN
1532-0626
Ausgabe der Veröffentlichung
4
Zeitschrift
Concurrency and Computation: Practice and Experience
Sprache
en
Online publication date
2012
Paginierung
586 - 603
Datum der Veröffentlichung
2013
Status
Published
Herausgeber
Wiley
Herausgeber URL
http://dx.doi.org/10.1002/cpe.2896
Datum der Datenerfassung
2023
Titel
Iterative sparse matrix–vector multiplication for accelerating the block Wiedemann algorithm over GF(2) on multi‐graphics processing unit systems
Ausgabe der Zeitschrift
25

Datenquelle: Crossref

Autoren
Zeitschrift
Concurr. Comput. Pract. Exp.
Artikelnummer
4
Paginierung
586 - 603
Datum der Veröffentlichung
2013
Titel
Iterative sparse matrix-vector multiplication for accelerating the block Wiedemann algorithm over GF(2) on multi-graphics processing unit systems.
Ausgabe der Zeitschrift
25

Datenquelle: DBLP

Beziehungen:
Eigentum von

Werkzeuge