Improvement of the fused CUDA kernels performance prediction
Fakulta Informatiky, Masarykova Univerzita
Masarykova Univerzita, 2013
@article{novak2013improvement,
title={Improvement of the fused CUDA kernels performance prediction},
author={Nov{‘a}k, Peter},
year={2013}
}
In this thesis a tool for improving the performance prediction of a source-to-source compiler of mapped functions developed on the Faculty of Informatics is presented. This tool integrates the modification of the original compiler and static and dynamic data gathering to provide as much data about the fusions as possible in order to analyze them. These data were then analyzed using the R statistic environment and the analysis results and suggestions for prediction improvements are presented.
January 25, 2014 by hgpu
