Multi GPU Implementation of the Simplex Algorithm
CNRS, LAAS, 7 avenue du colonel Roche, F-31077 Toulouse, France
IEEE 13th International Conference on High Performance Computing and Communications (HPCC), 2011
@inproceedings{lalami2011multi,
title={Multi GPU Implementation of the Simplex Algorithm},
author={Lalami, M.E. and El-Baz, D. and Boyer, V.},
booktitle={High Performance Computing and Communications (HPCC), 2011 IEEE 13th International Conference on},
pages={179–186},
year={2011},
organization={IEEE}
}
The Simplex algorithm is a well known method to solve linear programming (LP) problems. In this paper, we propose an implementation via CUDA of the Simplex method on a multi GPU architecture. Computational tests have been carried out on randomly generated instances for non-sparse LP problems. The tests show a maximum speedup of 24:5 with two Tesla C2050 boards.
November 14, 2011 by hgpu
