Fast Evaluation of GP Trees on GPGPU by Optimizing Hardware Scheduling
LSIIT – UMR 7005, Pole API, Bd Sebastien Brant, 67400 Illkirch – France
Genetic Programming, Lecture Notes in Computer Science, 2010, Volume 6021/2010, 301-312
@article{maitre2010fast,
title={Fast evaluation of GP trees on GPGPU by optimizing hardware scheduling},
author={Maitre, O. and Lachiche, N. and Collet, P.},
journal={Genetic Programming},
pages={301–312},
year={2010},
publisher={Springer}
}
This paper shows that it is possible to use General Purpose Graphic Processing Unit cards for a fast evaluation of different Genetic Programming trees on as few as 32 fitness cases by using the hardware scheduling of NVIDIA cards. Depending on the function set, observed speedup ranges between x50 and x250 on one half of an NVidia GTX295 GPGPU card, vs a single core of an Intel Quad core Q8200.
January 21, 2011 by hgpu
