PARALLEL COMPUTING MODEL WITH CONTINUOUS TIME

Abstract

The aim of this work is to construct a numerical-analytical method of designing efficient algorithms for solution of tasks having the parabolic type. Using a priori information about the smoothness of solutions, great attention is paid to the construction of solutions of high -order accuracy. Creation of parallel computing systems required the development of mathematical concepts for constructing parallel algorithms, i.e. algorithms adapted for implementation in these systems. As the basis for constructing the parallel algorithm we can take both: a sequential algorithm and the task itself as well. The most sensible at parallelization of sequential algorithm is pragmatic approach; actually sequential algorithms detect common elements which further are transformed to a parallel form. It is shown, that the algorithm of numerical - analytical vectorization has the maximal parallel form and, hence, minimally possible time for realization on parallel computing devices.