Acceleration of recovery simulation on big model using GPU
Kazakh-British Technical University, Almaty 050000, Kazakhstan
AWERProcedia Information Technology & Computer Science, Vol. 04, 857-864, 2013
@article{bekibayev2013acceleration,
title={Acceleration of recovery simulation on big model using GPU},
author={Bekibayev, TT and Assilbekov, BK and Zhapbasbayev, UK},
journal={AWERProcedia Information Technology and Computer Science},
volume={4},
number={2},
year={2013}
}
Software that calculate different scenarios of field development play important role in petroleum industry. Increasing number of cells in the simulation grid significantly slows down the calculations. In order to obtain accuracy results it is necessary to spend a lot of time for the simulations (days or weeks) or use expensive high-performance systems or supercomputers. This paper reviews the parallel computing of hydrodynamics on Graphical Processing Unit and realization using CUDA. Most time-consuming parts of code, escpecially solution of Poisson’s equation by SOR method were adapted for GPU implementation. The factors affecting speed-up on GPU were described. Results of calculation accelerations on video cards GeForce GTX 560 Ti are presented. The maximum achieved acceleration is about 90 times.
September 18, 2013 by hgpu
