Evaluation of state-of-the-art polyhedral tools for automatic code generation on GPUs
ArTeCS group, Univ. Complutense de Madrid
XXIII Jornadas de Paralelismo, 2012
@article{juega2012evaluation,
title={Evaluation of state-of-the-art polyhedral tools for automatic code generation on GPUs},
author={Juega, JC and G{‘o}mez, JI and Tenllado, C. and Verdoolaege, S. and Cohen, A. and Catthoor, F.},
year={2012}
}
At present, multi-core and manycore platforms lead the computer industry, forcing software developers to adopt new programming paradigms, in order to fully exploit their computing capabilities. Nowadays, Graphics Processing Units (GPUs) are one of representatives of many-core architectures, and certainly the most widespread. This paper evaluates and compares tool frameworks that automatically generate code for GPUs, saving time and effort to programmers. These frameworks take advantage of Polyhedral Model techniques to exploit parallelism and to satisfy the specific GPU constraints. The paper shows the key features of some of these source-to-source compilers and analyzes the code that they generate. Finally we discuss the importance of some key aspects such as data mapping and code quality.
July 24, 2012 by hgpu
