Dense Dynamic Programming on Multi GPU
CNRS; LAAS; 7 avenue du colonel Roche, F-31077 Toulouse, France
19th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), 2011
@inproceedings{boyer2011dense,
title={Dense dynamic programming on multi GPU},
author={Boyer, V. and El Baz, D. and Elkihel, M.},
booktitle={Parallel, Distributed and Network-Based Processing (PDP), 2011 19th Euromicro International Conference on},
pages={545–551},
year={2011},
organization={IEEE}
}
The implementation via CUDA of a hybrid dense dynamic programming method for knapsack problems on amulti-GPU architecture is considered. Tests are carried out on a Bull cluster with Tesla S1070 computing systems. A first series of computational results shows substantial speedup. The speedup factor is close to 28 with two GPUs.
October 26, 2011 by hgpu
