PARALLEL MATRIX-MULTIPLICATION ALGORITHM ON NETWORK OF WORKSTATIONS

Abstract

Matrix multiplication is one of the important operations in scientific and engineering application. However, it is also one of
the operations that are time consuming. Continuous researches have been conducted to improve this operation. One of the
alternatives is to have the operation performed in parallel. However, these types of algorithms often carried out on
expensive supercomputers or multiprocessing systems. With the advancement of personal computers and networking, the
use of network of computers has become an advantage to the computing community. Although programming in such
environment is relatively harder compared to that of in shared memory multiprocessing environment, its advantages
outweigh its complexity. In this paper, we introduce the concept of Network of Computers (NOW) or Cluster computing
and present its advantages. We discuss matrix-multiplication algorithm and highlight one of the parallel matrixmultiplication
algorithms. We present the comparison in terms of speed between serial algorithm and the parallel algorithm
when we run them on our cluster. We end our discussion by outlining our future works.