Adaptive Scalable SVD Unit for Fast Processing of Large LSE Problems


Autoria(s): Bildosola Agirregomezkorta, Iñaki; Martínez Corral, Unai; Basterrechea Oyarzabal, Koldobika
Data(s)

16/09/2014

08/10/2014

16/09/2014

08/10/2014

18/06/2014

Resumo

Singular Value Decomposition (SVD) is a key linear algebraic operation in many scientific and engineering applications. In particular, many computational intelligence systems rely on machine learning methods involving high dimensionality datasets that have to be fast processed for real-time adaptability. In this paper we describe a practical FPGA (Field Programmable Gate Array) implementation of a SVD processor for accelerating the solution of large LSE problems. The design approach has been comprehensive, from the algorithmic refinement to the numerical analysis to the customization for an efficient hardware realization. The processing scheme rests on an adaptive vector rotation evaluator for error regularization that enhances convergence speed with no penalty on the solution accuracy. The proposed architecture, which follows a data transfer scheme, is scalable and based on the interconnection of simple rotations units, which allows for a trade-off between occupied area and processing acceleration in the final implementation. This permits the SVD processor to be implemented both on low-cost and highend FPGAs, according to the final application requirements.

Identificador

25th International Conference on Application-specific Systems, Architectures and Processors (ASAP 2014, Zurich

http://hdl.handle.net/10810/13397

10.1109/ASAP.2014.6868625

Idioma(s)

eng

Publicador

Institute of Electrical and Electronic Engineers (IEEE)

Relação

http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6868625

Direitos

(c) 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.

info:eu-repo/semantics/openAccess

Palavras-Chave #Singular Value Decomposition (SVD) #adaptive threshold #selectable accuracy #scalable architecture #Field Programmable Gate Array (FPGA) #error regularization #high dimensionality datasets #linear algebraic operation
Tipo

info:eu-repo/semantics/article