Using DRBL to Deploy MPICH2 and CUDA on Green Computing
Department of Applied Mathematics, National Chung Hsing University, Taichung City, Taiwan
The First International Conference on Advanced Communications and Computation (INFOCOMP), 2011
@inproceedings{jiun2011using,
title={Using DRBL to Deploy MPICH2 and CUDA on Green Computing},
author={Jiun-Yu, W. and Yao-Tsung, W. and Steven, S. and Hui Ching, W.},
booktitle={INFOCOMP 2011, The First International Conference on Advanced Communications and Computation},
pages={75–79},
year={2011}
}
In this paper, an energy efficient architecture for Build Energy Efficient GPU and CPU Cluster Using DRBL is proposed. This architecture helps administrator not only to quickly deploy and manage GPU and CPU Cluster environment, but also bring benefit of energy efficiency in scientific computing. The experiment simulates 3 cases to prove energy efficiency. We will compare GPU and CPU Cluster Using DRBL with the design without DRBL. According to the experiment results, the architecture provides a way to implement a power economization computing architecture that reduces energy consumption.
November 1, 2011 by hgpu
