Accelerating Vector Calculations on GPU
Faculty of Computer Science and Management, Zilina, Slovak Republic
Scientific papers of the University of Pardubice Faculty of Economics and Administration, p.52, 2011
@article{grondzaka2011accelerating,
title={ACCELERATING VECTOR CALCULATIONS ON GPU},
author={Grond{v{z}}{‘a}ka, K. and Martincov{‘a}a, P. and {v{S}}uchb, O.},
journal={Scientific papers of the University of Pardubice Faculty of Economics and Administration},
pages={52},
year={2011}
}
Multicore computational accelerators such as Graphics Processor Units (GPUs) became common for gaining high-performance computing on a larger scale. Programming GPUs requires detailed knowledge of the underlying architecture in order to get maximum performance. In this paper we present solution of vector distance calculation on NVIDIA’s parallel computing architecture CUDA (Common Unified Device Architecture), where we optimize the performance of a parallel algorithm and get significant speedup.
October 1, 2011 by hgpu
