Analyzing parallelization performance of Reed-Solomon algorithm

Distributed storage systems allow to solve the strong demand of data storage required by today's society, this is because new challenges arise related to data recovery based on erasure code. This article presents the parallelization of the Reed-Solomon algorithm through threads. The evaluation...

Descripción completa

Detalles Bibliográficos
Autores: Marcillo, Fabricio R., Palacios, Raúl H., Díaz, Antonio F., Herrera, Jefferson R., Camacho, Ronald D.
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2021
País:Ecuador
Institución:Universidad Técnica Estatal de Quevedo
Repositorio:Revista InGenio
Idioma:español
OAI Identifier:oai:revistas.uteq.edu.ec:article/365
Acceso en línea:https://revistas.uteq.edu.ec/index.php/ingenio/article/view/365
Access Level:acceso abierto
Palabra clave:Fiabilidad
tolerancia a los fallos
códigos de control de errores
Reed-Solomon
Reliability
fault tolerance
error control codes
Descripción
Sumario:Distributed storage systems allow to solve the strong demand of data storage required by today's society, this is because new challenges arise related to data recovery based on erasure code. This article presents the parallelization of the Reed-Solomon algorithm through threads. The evaluation was made in a BLADE system, the execution of the algorithm has been done in a configuration of 1, 2, 4 and 8 threads to check the behavior of the algorithm. Regarding the results, it was observed that the times required for processing the algorithms for both encoding and decoding are considerably reduced.