• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
10.11606/D.55.2018.tde-09032018-135249
Document
Author
Full name
Omar Andrés Carmona Cortés
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 1999
Supervisor
Committee
Santana, Regina Helena Carlucci (President)
Franco, Neide Maria Bertoldi
Méndez, Osvaldo Ronald Saavedra
Title in Portuguese
Desenvolvimento e Avaliação de Algoritmos Numéricos Paralelos
Keywords in Portuguese
Não disponível
Abstract in Portuguese
O objetivo principal deste trabalho é o desenvolvimento e avaliação de algoritmos numéricos paralelos e sua execução em máquinas paralelas (máquinas multiprocessadas, máquinas vetoriais e máquinas paralelas virtuais). Os algoritmos desenvolvidos foram executados em diferentes condições tanto em termos de plataformas utilizadas como em termos de tamanho da aplicação considerada. Os resultados obtidos na implementação dos algoritmos numéricos são analisados baseando-se em algumas métricas (tempo de execução e operações em ponto flutuante) comuns aos resultados apresentados nos principais benchmarks estudados. Através dos resultados obtidos, o desempenho das bibliotecas de passagem de mensagem MPI e PVM, o desempenho das arquiteturas consideradas e da implementação dos algoritmos numéricos são analisados.
Title in English
Not available
Keywords in English
Not available
Abstract in English
The main objective of this dissertation is the development and evaluation of numerical parallel algorithms and their execution on parallel machines (multiprocessor machines, vectorial machines and parallel virtual environments). The algorithms developed have been executed under different conditions both in terms of the hardware plataform adopted and the problem size. The results obtained with the numerical algorithms implementation are all analyzed according to some metrics (execution time and float-point operations) available in the main benchmarks studied. The performance reached with the message passing libraries PVM and MPI together with the performance observed from the different architectures considered and the numerical algorithms implemented are ali analyzed according to the result obtained in this work.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2018-03-09
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2021. All rights reserved.