Title :
Linear algebra algorithms in a heterogeneous cluster of personal computers
Author :
Barbosa, J. ; Tavares, J. ; Padilha, A.J.
Author_Institution :
Grupo de Arquitecturas e Sistemas, FEUP-INEB, Porto, Portugal
Abstract :
Cluster computing is presently a major research area, mostly for high performance computing. The work presented refers to the application of cluster computing in a small scale where a virtual machine is composed of a small number of off-the-self-personal computers connected by a low cost network. A methodology to determine the optimal number of processors to be used in a computation is presented as well as the speedup results obtained for the matrix-matrix multiplication and for the symmetric QR algorithm for eigenvector computation which are significant building blocks for applications in the target image processing and analysis domain. The load balancing strategy is also addressed
Keywords :
eigenvalues and eigenfunctions; image processing; matrix multiplication; open systems; parallel algorithms; resource allocation; virtual machines; workstation clusters; cluster computing; eigenvector computation; heterogeneous cluster of personal computers; high performance computing; linear algebra algorithms; load balancing strategy; low cost network; matrix-matrix multiplication; speedup results; symmetric QR algorithm; target image processing; virtual machine; Application software; Clustering algorithms; Computer applications; Computer networks; Costs; High performance computing; Image processing; Linear algebra; Symmetric matrices; Virtual machining;
Conference_Titel :
Heterogeneous Computing Workshop, 2000. (HCW 2000) Proceedings. 9th
Conference_Location :
Cancun
Print_ISBN :
0-7695-0556-2
DOI :
10.1109/HCW.2000.843740
