2024-03-29T04:48:10Zhttps://repositori.uji.es/oai/requestoai:repositori.uji.es:10234/615642023-07-21T09:33:13Zcom_10234_7036com_10234_9col_10234_61544
00925njm 22002777a 4500
dc
Benner, Peter
author
Ezzatti, Pablo
author
Kressner, Daniel
author
Quintana-Orti, Enrique S.
author
Remón Gómez, Alfredo
author
2012
Model order reduction of a dynamical linear time-invariant system appears in many applications from science and engineering. Numerically reliable SVD-based methods for this task require in general O(n3) floating-point arithmetic operations, with n being in the range 103 − 105 for many practical applications. In this paper we investigate the use of graphics processors (GPUs) to accelerate model reduction of large-scale linear systems by off-loading the computationally intensive tasks to this device. Experiments on a hybrid platform consisting of state-of-the-art general-purpose multi-core processors and a GPU illustrate the potential of this approach.
Benner, Peter; Ezzatti, Pablo; Kressner, Daniel; Quintana-Ortí, Enrique S.; Remón, Alfredo " Accelerating Model Reduction of Large Linear Systems with Graphics Processors". En: Applied Parallel and Scientific Computing– 10th International Conference, PARA 2010, Reykjavík, Iceland, June 6-9, 2010, Revised Selected Papers, Part II / Jónasson, Kristen [et al.] (Eds.). Berlin : Springer, 2012. (Lecture Notes in Computer Science; 7134) . ISBN 978-3-642-28144-0, pp. 88-97
978-3-642-28144-0
0302-9743
1611-3349
http://hdl.handle.net/10234/61564
http://dx.doi.org/10.1007/978-3-642-28145-7_9
Model reduction
Dynamical linear systems
Lyapunov equations
SVD-based methods
GPUs
Accelerating Model Reduction of Large Linear Systems with Graphics Processors