Identificador persistente para citar o vincular este elemento:
http://hdl.handle.net/10553/73112
Título: | 'Beowulf cluster' for high-performance computing tasks at the university: a very profitable investment | Autores/as: | Galán, M. J. García, F. Álvarez Álvarez, Luis Antonio Ocón Carreras, Antonio Andrés Rubio, E. |
Clasificación UNESCO: | 120317 Informática 330406 Arquitectura de ordenadores 530602 Innovación tecnológica |
Palabras clave: | Cluster Computer commodities High performance computing Linux Oss |
Fecha de publicación: | 2001 | Publicación seriada: | Informatica (Ljubljana) | Resumen: | We describe a high performance/low price "computer cluster" named Beowulf Cluster. This kind of device was initially developed by T. Sterling and D. Becker (N.A.S.A.) and it is a kind of cluster built primarily out of commodity hardware components, running an OSS (Open Source Software) operating system like Linux or FreeBSD, interconnected by a private high-speed network, dedicated to running high-performance computing tasks. We will show several advantages of such a device, among them we can mention very high performance-price ratio, easy scalability, recycling possibilities of the hardware components and guarantee of usability/upgradeability in the medium and long-term future. All these advantage make it specially suitable for the university environment and, thus, we make a description about the implementation of the Beowulf Cluster using commodity equipment dedicated to run high-performance computing tasks at our university focusing on the different areas of application of this device that range from production of high quality multimedia content to applications in numerical simulation in engineering. | URI: | http://hdl.handle.net/10553/73112 | ISSN: | 0350-5596 | Fuente: | Informatica (Ljubljana) [ISSN 0350-5596], v. 25 (2), p. 189-193, (Julio 2001) |
Colección: | Artículos |
Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.