Measuring the component of a divide and conquer skeleton

Current performance prediction analytical models try to characterize the performance behavior of actual machines through a small set of parameters. Due to different factors, the predicted times suffer substantial deviations. A natural approach is to associate a different proportionality constant wit...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Printista, Alicia Marcela, Saez, Fernando
Formato: Articulo
Lenguaje:Inglés
Publicado: 2009
Materias:
Ciencias Informáticas
timing model
skeleton
multivariate analysis
Parallel
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/9647
http://journal.info.unlp.edu.ar/wp-content/uploads/JCST-Apr09-5.pdf
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-9647
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
timing model
skeleton
multivariate analysis
Parallel
spellingShingle Ciencias Informáticas
timing model
skeleton
multivariate analysis
Parallel
Printista, Alicia Marcela
Saez, Fernando
Measuring the component of a divide and conquer skeleton
topic_facet Ciencias Informáticas
timing model
skeleton
multivariate analysis
Parallel
description Current performance prediction analytical models try to characterize the performance behavior of actual machines through a small set of parameters. Due to different factors, the predicted times suffer substantial deviations. A natural approach is to associate a different proportionality constant with each basic block of computation. In particular, the paper deals with a skeleton designed for parallel divide and conquer algorithms that provide hypercubical communications among processes. Our proposal is to introduce different kinds of components to the analytical model by associating a performance constant for each conceptual block of a skeleton. The trace files obtained from the execution of the resulting code using the programming skeleton are used by lineal regression techniques giving us, among other information, the values of the parameters of those blocks. The accuracy of the proposed model is analyzed by means of two instances of skeleton.
format Articulo
Articulo
author Printista, Alicia Marcela
Saez, Fernando
author_facet Printista, Alicia Marcela
Saez, Fernando
author_sort Printista, Alicia Marcela
title Measuring the component of a divide and conquer skeleton
title_short Measuring the component of a divide and conquer skeleton
title_full Measuring the component of a divide and conquer skeleton
title_fullStr Measuring the component of a divide and conquer skeleton
title_full_unstemmed Measuring the component of a divide and conquer skeleton
title_sort measuring the component of a divide and conquer skeleton
publishDate 2009
url http://sedici.unlp.edu.ar/handle/10915/9647
http://journal.info.unlp.edu.ar/wp-content/uploads/JCST-Apr09-5.pdf
work_keys_str_mv AT printistaaliciamarcela measuringthecomponentofadivideandconquerskeleton
AT saezfernando measuringthecomponentofadivideandconquerskeleton
bdutipo_str Repositorios
_version_ 1764820492170035202

Ejemplares similares