Implementation of algorithms with a fine-grained parallelism on GPUs
Institute of Computational Mathematics and Mathematical Geophysics (Computing Center), Siberian Branch of the Russian Academy of Sciences, Novosibirsk
Numerical Analysis and Applications, Vol. 4, No. 1. (1 January 2011), pp. 46-55.
The efficiency of implementations of algorithms with a fine-grained parallelism on GPUs that support the CUDA architecture is studied. Cellular automata and difference schemes are used for testing. Several versions of implementations are proposed and their efficiency is analyzed. An example of GPU application for modeling the process of carbon dioxide oxidation on the catalyst surface is given.
March 17, 2011 by hgpu