Performance of scientific processing in networks of workstations : matrix multiplication example

Detalles Bibliográficos
Autor Principal: Tinetti, Fernando Gustavo
Formato: Capítulo de libro
Lengua:inglés
Temas:
Acceso en línea:http://goo.gl/lFRbj9
Consultar en el Cátalogo
Resumen:Parallel computing on networks of workstations are intensively used in some application areas such as linear algebra operations. Topics such as processing as well as communication hardware heterogeneity are considered solved by the use of parallel processing libraries, but experimentation about performance under these circumstances seems to be necessary. Also, installed networks of workstations are specially attractive due to its extremely low cost for parallel processing as well as its great availability given the number of installed local area networks. The performance of such networks of workstations is fully analyzed by means of a simple application: matrix multiplication. A parallel algorithm is proposed for matrix multiplication derived from two main sources: a) previous proposed algorithms for this task in traditional parallel computers, and b) the bus based interconnection network of workstations. This parallel algorithm is analyzed experimentally in terms of workstations workload and data communication, two main factors in overall parallel computing performance.
Notas:Formato de archivo: PDF. -- Este documento es producción intelectual de la Facultad de Informática - UNLP (Colección BIPA/Biblioteca)
Descripción Física:1 archivo (39,2 KB)

MARC

LEADER 00000naa a2200000 a 4500
003 AR-LpUFIB
005 20250403180515.0
008 230201s2001 xx o 000 0 eng d
024 8 |a DIF-M6851 
040 |a AR-LpUFIB  |b spa  |c AR-LpUFIB 
100 1 |a Tinetti, Fernando Gustavo 
245 1 0 |a Performance of scientific processing in networks of workstations :  |b matrix multiplication example 
300 |a 1 archivo (39,2 KB) 
500 |a Formato de archivo: PDF. -- Este documento es producción intelectual de la Facultad de Informática - UNLP (Colección BIPA/Biblioteca) 
520 |a Parallel computing on networks of workstations are intensively used in some application areas such as linear algebra operations. Topics such as processing as well as communication hardware heterogeneity are considered solved by the use of parallel processing libraries, but experimentation about performance under these circumstances seems to be necessary. Also, installed networks of workstations are specially attractive due to its extremely low cost for parallel processing as well as its great availability given the number of installed local area networks. The performance of such networks of workstations is fully analyzed by means of a simple application: matrix multiplication. A parallel algorithm is proposed for matrix multiplication derived from two main sources: a) previous proposed algorithms for this task in traditional parallel computers, and b) the bus based interconnection network of workstations. This parallel algorithm is analyzed experimentally in terms of workstations workload and data communication, two main factors in overall parallel computing performance. 
534 |a Journal of Computer Science & Technology, 1(4) 
650 4 |a COMPUTACIÓN PARALELA 
650 4 |a ESTACIONES DE TRABAJO 
650 4 |a INTERFAZ DE TRANSFERENCIA DE MENSAJES - MPI 
856 4 0 |u http://goo.gl/lFRbj9 
942 |c CP  |2 udc 
952 |0 0  |1 0  |4 0  |6 A0591  |7 3  |8 BD  |9 81217  |a DIF  |b DIF  |d 2025-03-11  |l 0  |o A0591  |r 2025-03-11 17:04:25  |u http://catalogo.info.unlp.edu.ar/meran/getDocument.pl?id=885  |w 2025-03-11  |y CP 
999 |c 56037  |d 56037