Matrix inversion on CPU-GPU platforms with applications in control theory / Peter Benner, Pablo Ezzatti, Enrique S. Quintana-Ortí, Alfredo Remón
Anzeigen / Download258.79 KB
Discovery
870315951
URN
urn:nbn:de:gbv:3:2-63936
DOI
ISBN
ISSN
Beiträger
Erschienen
Magdeburg : Max Planck Institute for Dynamics of Complex Technical Systems, February 1, 2012
Umfang
1 Online-Ressource (18 Seiten = 0,25 MB) : Diagramme
Ausgabevermerk
Sprache
eng
Anmerkungen
Inhaltliche Zusammenfassung
Abstract: In this paper we tackle the inversion of large-scale dense matrices via conventional matrix factorizations (LU, Cholesky, LDLT ) and the Gauss-Jordan method on hybrid platforms consisting of a multi-core CPU and a many-core graphics processor (GPU). Specifically, we introduce the different matrix inversion algorithms using a unified framework based on the notation from the FLAME project; we develop hybrid implementations for those matrix operations underlying the algorithms, alternative to those in existing libraries for single-GPU systems; and we perform an extensive experimental study on a platform equipped with state-of-the-art general-purpose architectures from Intel and a “Fermi” GPU from NVIDIA that exposes the efficiency of the different inversion approaches. Our study and experimental results show the simplicity and performance advantage of the GJE-based inversion methods, and the difficulties associated with the symmetric indefinite case.
Schriftenreihe
Max Planck Institute Magdeburg Preprints ; 12-02 ppn:870173030