Deutsch
 
Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
  Lokale TagsFreigabegeschichteDetailsÜbersicht

Freigegeben
Bericht

Structuring distributed relation-based computations with SCDRC

Urheber*innen

Botta,  N.
Potsdam Institute for Climate Impact Research and Cooperation Partners;

Ionescu,  C.
Potsdam Institute for Climate Impact Research and Cooperation Partners;

Linstead,  C.
Potsdam Institute for Climate Impact Research and Cooperation Partners;

Klein,  R.
Potsdam Institute for Climate Impact Research and Cooperation Partners;

Externe Ressourcen

https://www.pik-potsdam.de/en/output/publications/pikreports
(Verlagsversion)

Volltexte (beschränkter Zugriff)
Für Ihren IP-Bereich sind aktuell keine Volltexte freigegeben.
Volltexte (frei zugänglich)

botta1.pdf
(beliebiger Volltext), 967KB

Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Botta, N., Ionescu, C., Linstead, C., Klein, R. (2006): Structuring distributed relation-based computations with SCDRC, (PIK Report ; 103), Potsdam : Potsdam-Institut für Klimafolgenforschung, 61 p.


Zitierlink: https://publications.pik-potsdam.de/pubman/item/item_13823
Zusammenfassung
In this report we present a set of software components for distributed relation-based computations (SCDRC). We explain how SCDRC can be used to structure parallel computations in a single-program multiple-data computational environment.

First, we introduce relation-based algorithms and relation-based computations as generic patterns in scientific computing. We then discuss the problems that have to be solved to parallelize such patterns and propose a high-level formalism for specifying these problems.

This formalism is then applied to derive parallel distributed relation-based computations. These are implemented in the C++ library SCDRC. We present language independent elements of SCDRC and discuss C++ specific aspects of its design and architecture.

Finally, we discuss how to use SCDRC in a simple application and provide preliminary performance figures.