Mapping linear algebra algorithms into array processors: a case study

Abstract

A general methodology, based on the concept of folding, for mapping wavefront algorithms into processor square meshes of fixed size has been implemented on a mesh of INMOS transputers, programmed in OCCAM, for the multiplication of matrices of arbitrary size. Different implementations of the code are considered and compared. The computational costs are analyzed in detail. The method and the performances of the system used are compared with other more standard solutions.<>