Skip to main content
Erschienen in: SICS Software-Intensive Cyber-Physical Systems 4/2016

15.09.2015 | Special Issue Paper

Characterizing the efficiency of multicore and manycore processors for the solution of sparse linear systems

Erschienen in: SICS Software-Intensive Cyber-Physical Systems | Ausgabe 4/2016

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

We analyze the efficiency of servers equipped with state-of-the-art general-purpose multicore processors as well as platforms based on accelerators such as graphics processing units (GPUs) and the Intel Xeon Phi. Following the proposal recently advocated in the High Performance Conjugate Gradient (HPCG) benchmark, we leverage for this purpose efficient implementations of ILUPACK, a preconditioned solver for sparse linear systems that comprises numerical kernels and data access patterns analogous to those of HPCG. Our study analyzes the (computational) performance and energy efficiency, with two different metrics for each: time/floating-point throughput for the former; and energy/floating-point throughput-per-Watt for the latter.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Computer Science - Research and Development

Computer Science – Research and Development (CSRD), formerly Informatik – Forschung und Entwicklung (IFE), is a quarterly international journal that publishes high-quality research and survey papers from the Software Engineering & Systems area.

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Weitere Produktempfehlungen anzeigen
Literatur
3.
Zurück zum Zitat Golub GH, Loan CFV (1996) Matrix computations, 3rd edn. The Johns Hopkins University Press, BaltimoreMATH Golub GH, Loan CFV (1996) Matrix computations, 3rd edn. The Johns Hopkins University Press, BaltimoreMATH
5.
Zurück zum Zitat Dongarra J, Heroux MA (2013) Toward a new metric for ranking high performance computing systems. Sandia Report SAND2013-4744, Sandia National Laboratory Dongarra J, Heroux MA (2013) Toward a new metric for ranking high performance computing systems. Sandia Report SAND2013-4744, Sandia National Laboratory
6.
Zurück zum Zitat Aliaga JI, Badia RM, Barreda M, Bollhöfer M, Quintana-Ortí ES (2014) Leveraging task-parallelism with OmpSs in ILUPACK’s preconditioned CG method. In: 26th International symposium on computer architecture and high performance computing (SBAC-PAD), pp 262–269 Aliaga JI, Badia RM, Barreda M, Bollhöfer M, Quintana-Ortí ES (2014) Leveraging task-parallelism with OmpSs in ILUPACK’s preconditioned CG method. In: 26th International symposium on computer architecture and high performance computing (SBAC-PAD), pp 262–269
7.
Zurück zum Zitat Aliaga JI, Bollhöfer M, Dufrechou E, Ezzatti P, Quintana-Ortí ES (2014) Leveraging data-parallelism in ILUPACK using graphics processors. In: 13th International symposium parallel distributed computing (ISPDC), pp 119–126 Aliaga JI, Bollhöfer M, Dufrechou E, Ezzatti P, Quintana-Ortí ES (2014) Leveraging data-parallelism in ILUPACK using graphics processors. In: 13th International symposium parallel distributed computing (ISPDC), pp 119–126
8.
Zurück zum Zitat Aliaga JI, Bollhöfer M, Martín AF, Quintana-Ortí ES (2011) Exploiting thread-level parallelism in the iterative solution of sparse linear systems. Parallel Comput 37(3):183–202MathSciNetCrossRefMATH Aliaga JI, Bollhöfer M, Martín AF, Quintana-Ortí ES (2011) Exploiting thread-level parallelism in the iterative solution of sparse linear systems. Parallel Comput 37(3):183–202MathSciNetCrossRefMATH
9.
Zurück zum Zitat Saad Y (2003) Iterative methods for sparse linear systems. 2nd edn. SIAM Saad Y (2003) Iterative methods for sparse linear systems. 2nd edn. SIAM
Metadaten
Titel
Characterizing the efficiency of multicore and manycore processors for the solution of sparse linear systems
Publikationsdatum
15.09.2015
Erschienen in
SICS Software-Intensive Cyber-Physical Systems / Ausgabe 4/2016
Print ISSN: 2524-8510
Elektronische ISSN: 2524-8529
DOI
https://doi.org/10.1007/s00450-015-0299-7

Weitere Artikel der Ausgabe 4/2016

SICS Software-Intensive Cyber-Physical Systems 4/2016 Zur Ausgabe