About speedup improvement of classical genetic algorithms using cuda environment

Due to the increasing computational cost required for the numerical solution of evolutionary systems and problems based on topological design, in the last years, many parallel algorithms have been developed in order to improve its performance. Perhaps, the main numerical tool used to solve heuris...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Mroginski, Javier Luis, Castro, Hugo Guillermo
Formato: Artículo
Lenguaje:Español
Publicado: Asociación Argentina de Mecánica Computacional 2023
Materias:
Metaheuristic optimization
CUDA
C++
HPC
Genetic algorithm
Acceso en línea:http://repositorio.unne.edu.ar/handle/123456789/51806
Aporte de:
RIUNNE - Repositorio Institucional de la Universidad Nacional del Nordeste (UNNE) de Universidad Nacional del Nordeste
id I48-R184-123456789-51806
record_format dspace
spelling I48-R184-123456789-518062023-07-04T23:03:46Z About speedup improvement of classical genetic algorithms using cuda environment Mroginski, Javier Luis Castro, Hugo Guillermo Metaheuristic optimization CUDA C++ HPC Genetic algorithm Due to the increasing computational cost required for the numerical solution of evolutionary systems and problems based on topological design, in the last years, many parallel algorithms have been developed in order to improve its performance. Perhaps, the main numerical tool used to solve heuristic problems is known as Genetic Algorithm (GA), deriving its name from the similarity to the evolutionary theory of Darwing. During the last decade, Graphic Processing Unit (GPU) has been used for computing acceleration due to the intrinsic vector-oriented design of the chip set. This gave race to a new programming paradigm: the General Purpose Computing on Graphics Processing Units (GPGPU). Which was replaced then by the Compute Unified Device Architecture (CUDA) environment in 2007. CUDA environment is probably the parallel computing platform and programming model that more heyday has had in recent years, mainly due to the low acquisition cost of the graphics processing units (GPUs) compared to a cluster with similar functional characteristics. Consequently, the number of GPU-CUDAs present in the top 500 fastest supercomputers in the world is constantly growing. In this work, a numerical algorithm developed in the NVIDIA CUDA platform capable of solving classical optimization functions usually employed as benchmarks (De Jong, Rastring and Ackley functions) is presented. The obtained results using a GeForce GTX 750 Ti GPU shown that the proposed code is a valuable tool for acceleration of GAs, improving its speedup in about 130%. 2023-07-04T10:32:09Z 2023-07-04T10:32:09Z 2016 Artículo Mroginski, Javier Luis y Castro, Hugo Guillermo, 2016. About speedup improvement of classical genetic algorithms using cuda environment. Mecánica Computacional. Santa Fe: Asociación Argentina de Mecánica Computacional, vol. 34, p. 3295-3295. E-ISSN 2591-3522. http://repositorio.unne.edu.ar/handle/123456789/51806 spa openAccess http://creativecommons.org/licenses/by-nc-nd/2.5/ar/ application/pdf p. 3295-3295 application/pdf Asociación Argentina de Mecánica Computacional Mecánica Computacional, 2016, vol. 34, p. 3295-3295.
institution Universidad Nacional del Nordeste
institution_str I-48
repository_str R-184
collection RIUNNE - Repositorio Institucional de la Universidad Nacional del Nordeste (UNNE)
language Español
topic Metaheuristic optimization
CUDA
C++
HPC
Genetic algorithm
spellingShingle Metaheuristic optimization
CUDA
C++
HPC
Genetic algorithm
Mroginski, Javier Luis
Castro, Hugo Guillermo
About speedup improvement of classical genetic algorithms using cuda environment
topic_facet Metaheuristic optimization
CUDA
C++
HPC
Genetic algorithm
description Due to the increasing computational cost required for the numerical solution of evolutionary systems and problems based on topological design, in the last years, many parallel algorithms have been developed in order to improve its performance. Perhaps, the main numerical tool used to solve heuristic problems is known as Genetic Algorithm (GA), deriving its name from the similarity to the evolutionary theory of Darwing. During the last decade, Graphic Processing Unit (GPU) has been used for computing acceleration due to the intrinsic vector-oriented design of the chip set. This gave race to a new programming paradigm: the General Purpose Computing on Graphics Processing Units (GPGPU). Which was replaced then by the Compute Unified Device Architecture (CUDA) environment in 2007. CUDA environment is probably the parallel computing platform and programming model that more heyday has had in recent years, mainly due to the low acquisition cost of the graphics processing units (GPUs) compared to a cluster with similar functional characteristics. Consequently, the number of GPU-CUDAs present in the top 500 fastest supercomputers in the world is constantly growing. In this work, a numerical algorithm developed in the NVIDIA CUDA platform capable of solving classical optimization functions usually employed as benchmarks (De Jong, Rastring and Ackley functions) is presented. The obtained results using a GeForce GTX 750 Ti GPU shown that the proposed code is a valuable tool for acceleration of GAs, improving its speedup in about 130%.
format Artículo
author Mroginski, Javier Luis
Castro, Hugo Guillermo
author_facet Mroginski, Javier Luis
Castro, Hugo Guillermo
author_sort Mroginski, Javier Luis
title About speedup improvement of classical genetic algorithms using cuda environment
title_short About speedup improvement of classical genetic algorithms using cuda environment
title_full About speedup improvement of classical genetic algorithms using cuda environment
title_fullStr About speedup improvement of classical genetic algorithms using cuda environment
title_full_unstemmed About speedup improvement of classical genetic algorithms using cuda environment
title_sort about speedup improvement of classical genetic algorithms using cuda environment
publisher Asociación Argentina de Mecánica Computacional
publishDate 2023
url http://repositorio.unne.edu.ar/handle/123456789/51806
work_keys_str_mv AT mroginskijavierluis aboutspeedupimprovementofclassicalgeneticalgorithmsusingcudaenvironment
AT castrohugoguillermo aboutspeedupimprovementofclassicalgeneticalgorithmsusingcudaenvironment
_version_ 1808038716209364992

Ejemplares similares