Automated development of applications for graphical processing units using rewriting rules

Abstract

Recently there was an active development of parallel programming methods concerning implementation of general-purpose algorithms on graphical processing units (GPUs). Using this specialized hardware allows increasing performance significantly, but requires low-level programming and understanding details of underlying hardware and software platform. Therefore there is a need for automating development process. This paper presents a technique for automating GPU application development, based on rewriting rules approach. An example is given demonstrating the possibilities of our approach when migrating from sequential C# program to its parallel analog running on GPU, as well as optimization of parallel applications. Using our approach we obtained performance speedup of 25X, while preserving the benefits of Microsoft .NET platform.