Parallel Tiled Code for Computing General Linear Recurrence Equations

In this article, we present a technique that allows us to generate parallel tiled code calculate general linear recursion equations (GLRE). That deals with multidimensional data and it is computing-intensive. We demonstrate dependencies available in an original computing GLREs do not allow any because there only one solution the time partition constraints built for program. show how transform another exposes such are two distinct solutions restrictions derived from these dependencies. This 2D GLREs. The wavefront used achieve parallelism, generated conforms OpenMP C/C++ standard. experiments conducted resulting much more efficient than serial Code performance improvement achieved by allowing parallelism better locality of target code.