Solving problems on concurrent processors. Vol. 1: General techniques and regular problems
Solving problems on concurrent processors. Vol. 1: General techniques and regular problems
Hypercube algorithms: with applications to image processing and pattern recognition
Hypercube algorithms: with applications to image processing and pattern recognition
LAPACK: a portable linear algebra library for high-performance computers
Proceedings of the 1990 ACM/IEEE conference on Supercomputing
Optimizing matrix multiply using PHiPAC: a portable, high-performance, ANSI C coding methodology
ICS '97 Proceedings of the 11th international conference on Supercomputing
ScaLAPACK user's guide
Parallel programming: techniques and applications using networked workstations and parallel computers
Automatically tuned linear algebra software
SC '98 Proceedings of the 1998 ACM/IEEE conference on Supercomputing
A New Parallel Matrix Multiplication Algorithm on Distributed-Memory Concurrent Computers
HPC-ASIA '97 Proceedings of the High-Performance Computing on the Information Superhighway, HPC-Asia '97
Heterogeneous Networks of Workstations and SPMD Scientific Computing
ICPP '99 Proceedings of the 1999 International Workshops on Parallel Processing
LAPACK Working Note 96: Scalable Universal Matrix Multiplication Algorithm
LAPACK Working Note 96: Scalable Universal Matrix Multiplication Algorithm
A cellular computer to implement the kalman filter algorithm
A cellular computer to implement the kalman filter algorithm
Architectures for an Efficient Application Execution in a Collection of HNOWS
Proceedings of the 9th European PVM/MPI Users' Group Meeting on Recent Advances in Parallel Virtual Machine and Message Passing Interface
Performance analysis of overheads for matrix – vector multiplication in cluster environment
PCI'05 Proceedings of the 10th Panhellenic conference on Advances in Informatics
Hi-index | 0.00 |
This paper outlines the general considerations to be taken into account when a network of heterogeneous workstations is used for scientific parallel computing. Special emphasis is made on already installed networks of workstations, which provide a "zero cost" parallel computer at least in hardware. Existing matrix multiplication algorithms are analyzed, taking them as representative enough for this application area. A new algorithm is proposed in order to take advantage of the specific characteristics of networks of workstations. This parallel multiplication algorithm is presented, and its performance is shown by preliminary experimentation using the PVM library to construct a parallel (virtual) computer from a network of workstations. Also, new features concerning data communication performance are identified from the execution profile of the experiments.