Paralelização de aplicações na plataforma R
Ano de defesa: | 2013 |
---|---|
Autor(a) principal: | |
Orientador(a): | |
Banca de defesa: | |
Tipo de documento: | Dissertação |
Tipo de acesso: | Acesso aberto |
Idioma: | por |
Instituição de defesa: |
Universidade Estadual de Maringá
Brasil Departamento de Informática Programa de Pós-Graduação em Ciência da Computação UEM Maringá, PR Centro de Tecnologia |
Programa de Pós-Graduação: |
Não Informado pela instituição
|
Departamento: |
Não Informado pela instituição
|
País: |
Não Informado pela instituição
|
Palavras-chave em Português: | |
Link de acesso: | http://repositorio.uem.br:8080/jspui/handle/1/2544 |
Resumo: | With the new technologies advent, the parallel programming is being increasingly employed in various areas with the main objective of enhancing the application performance being developed. Areas such as Physics, Biology, Chemistry, Statistics, Geography, and others, have applications that manipulate large amounts of data or perform exhaustive operations on them, requiring high processing time, hindering research in their respective areas. These applications parallelization involves several decisions in design and development, decisions such as the computing parallel model will be employed, which parallelization techniques can be experienced, which best programming language fits the problem, which architecture will be used, among others. Applications in several areas use statistical calculations and in this sense, one of the most widely used development platform is the R, which offers packages that implement several statistical programming functions, including parallelization isolated resources. However, the R platform has been extended openly, by the own scientific community and interested users, without a standardized methodology, computationally certified and well documented, so that there is difficulty in knowledge and their facilities use. This present work presents a applications parallelization methodology in the R platform, with the objective to facilitate the R programmers work, and as a case study, the methodology was used in the geoComp applications parallelization, that was developed to support the bivariate geostatistical model for compositional data structures. The parallel versions obtained were executed, analyzed and evaluated permitting validate the developed methodology and proving their importance. |