Algorithm for Parallelization of Cubic Spline Computational Processes in Distributed Computing Systems
Main Article Content
Abstract
The article is devoted to the creation of an algorithm for the parallelization of cubic-spline computational processes in distributed computing systems. The article considers the creation of an algorithm or parallelization of cubic-spline computational processes using MPI (Message Passing Technology) technology, studying the problems of parallel streams in a distributed computing system and parallel transmission and reception of messages in real-time on networked computers. Spline coefficients were calculated using point formulas that fully satisfy the parallelization requirements. Point formulas allow the implementation of time-consuming computational processes in parallel, as they do not require the solution of a system of equations. The acceleration coefficient and efficiency of the proposed parallel algorithm are calculated and presented in the form of a comparative table relative to the computational processes on several computers. A large number of geographic signals were selected as the incoming signal.