DEMCMC-GPU: An Efficient Multi-Objective Optimization Method with GPU Acceleration on the Fermi Architecture
Department of Industrial Engineering, Lamar University, 211 Redbird Ln, P.O. Box 10032, Beaumont, TX 77710, USA
New Generation Computing, Vol. 29, No. 2. (1 April 2011), pp. 163-184.
@article{zhu2011demcmc,
title={DEMCMC-GPU: An Efficient Multi-Objective Optimization Method with GPU Acceleration on the Fermi Architecture},
author={Zhu, W. and Yaseen, A. and Li, Y.},
journal={New Generation Computing},
volume={29},
number={2},
pages={163–184},
year={2011},
publisher={Springer}
}
In this paper, we present an efficient method implemented on Graphics Processing Unit (GPU), DEMCMC-GPU, for multi-objective continuous optimization problems. The DEMCMC-GPU kernel is the DEMCMC algorithm, which combines the attractive features of Differential Evolution (DE) and Markov Chain Monte Carlo (MCMC) to evolve a population of Markov chains toward a diversified set of solutions at the Pareto optimal front in the multi-objective search space. With parallel evolution of a population of Markov chains, the DEMCMC algorithm is a natural fit for the GPU architecture. The implementation of DEMCMC-GPU on the pre-Fermi architecture can lead to a ~25 speedup on a set of multi-objective benchmark function problems, compare to the CPU-only implementation of DEMCMC. By taking advantage of new cache mechanism in the emerging NVIDIA Fermi GPU architecture, efficient sorting algorithm on GPU, and efficient parallel pseudorandom number generators, the speedup of DEMCMC-GPU can be aggressively improved to ~100.
June 7, 2011 by hgpu
