GPU-based paralelization of the BGP protocol
暂无分享,去创建一个
In order to speed up the choice of the best routes in the BGP protocol, this paper proposes its paralelization using GPU. An additional benefit is the off-load of CPU which can now be fully dedicated to the packet processing and forwarding. The evaluation experiments with real routes carried on the CUDA platform has shown the degree of speedup.
[1] Randy Zhang,et al. BGP Design and Implementation , 2003 .
[2] Jason Sanders,et al. CUDA by example: an introduction to general purpose GPU programming , 2010 .