Optimization of HEP codes on GPUs
GSI, Planckstrasse 1, 64291 Darmstadt, Germany
The European Physical Journal Plus, Volume 126, Number 1, 1-9
@article{springerlink:10.1140/epjp/i2011-11001-5,
author={Al-Turany, M.},
affiliation={GSI, Planckstrasse 1, 64291 Darmstadt, Germany},
title={Optimization of HEP codes on GPUs},
journal={The European Physical Journal Plus},
publisher={Springer Berlin / Heidelberg},
issn={},
keyword={Condensed Matter Physics},
pages={1-9},
volume={126},
issue={1},
url={http://dx.doi.org/10.1140/epjp/i2011-11001-5},
note={10.1140/epjp/i2011-11001-5},
year={2011}
}
The graphics processor units (GPUs) have evolved into high-performance co-processors that can be easily programmed with common high-level language such as C, Fortran and C++. Today’s GPUs greatly outpace CPUs in arithmetic performance and memory bandwidth, making them the ideal coprocessor to accelerate a variety of data parallel applications. Here, we shall describe the application of the data parallelism model supported in CUDA and GPUs with some example usage in high-energy physics software.
February 18, 2011 by hgpu
