Normal view MARC view ISBD view

Parallelization analysis on clusters of multicore nodes using shared distributed memory parallel computing models

By:

Tinetti, Fernando Gustavo

Contributor(s):

Wolfmann, Aaron Gustavo Horacio

Material type: Article

ArticleDescription: Datos electrónicos (1 archivo: 298 KB)Subject(s):

CLUSTERS

Online resources:

Click here to access online

Summary: This paper presents alternatives performance results obtained by analyzing parallelization on a cluster of multicore nodes. The ultimate goal is to if both shared distributed memory parallel processing models need to be taken into account independently, if one affects the other both must be considered simultaneosly. The application used as a testbed is classical in the context of highperformance computing: matrix multiplication. Results are shown in terms of the conditions under which performance is optimized to focus the parallelization efforts on clusters with nodes with multiple cores, based on experiments combining both kinds of parallel models. In any case, processing units should be effectively used in order to optimize the performance of parallel applications.

Average rating: 0.0 (0 votes)

Holdings ( 1 )
Title notes ( 3 )

Holdings
Item type	Home library	Call number	Status	Date due	Barcode
Capítulo de libro	Biblioteca de la Facultad de Informática	A0232 (Browse shelf(Opens below))	No corresponde

Browsing Biblioteca de la Facultad de Informática shelves Close shelf browser (Hides shelf browser)

Previous								Next
Previous	A0229 Obtaining a Fuzzy Classification Rule System a Non-Supervised Clustering	A0230 Mapping tasks to processors in heterogeneous multiprocessor architectures : the MATEHa algorithm	A0231 Thinking semantic wikis as learning object repositories	A0232 Parallelization analysis on clusters of multicore nodes using shared distributed memory parallel computing models	A0233 Embedding security patterns into a domain model	A0234 AMTHA : an algorithm for automatically mapping tasks to processors in heterogeneous multiprocessor architectures	A0235 Clock synchronization in clusters for performance evaluation : numeric/scientific computing	Next

Formato de archivo: PDF. -- Este documento es producción intelectual de la Facultad de Informática-UNLP (Colección BIPA / Biblioteca.) -- Disponible también en línea (Cons. 03/05/2011)

This paper presents alternatives performance results obtained by analyzing parallelization on a cluster of multicore nodes. The ultimate goal is to if both shared distributed memory parallel processing models need to be taken into account independently, if one affects the other both must be considered simultaneosly. The application used as a testbed is classical in the context of highperformance computing: matrix multiplication. Results are shown in terms of the conditions under which performance is optimized to focus the parallelization efforts on clusters with nodes with multiple cores, based on experiments combining both kinds of parallel models. In any case, processing units should be effectively used in order to optimize the performance of parallel applications.

2009 World Congress on Computer Science Information Engineering ISBN 978-0-7695-3507-4. Pág. 466 - 470. 2009