An openMP+/MPI recursive least squares pipelined parallel algorithm based on the square root and extended version information filter for heterogeneous parallel systems

Authors:
F. J. Martínez Zaldívar;A. M. Vidal Maciáa;A. González Salvador
Affiliations:
Departamento de Comunicaciones, Universidad Politécnica de Valencia, Valencia, Spain;Departamento de Sistemas Informáticos y Computación, Universidad Politécnica de Valencia, Valencia, Spain;Departamento de Comunicaciones, Universidad Politécnica de Valencia, Valencia, Spain
Venue:
MATH'05 Proceedings of the 8th WSEAS International Conference on Applied Mathematics
Year:
2005

Citing 1
Cited 0

A fully pipelined RLS-based array for channel equalization

Journal of VLSI Signal Processing Systems - Special issue on array optimization and adaptive tracking algorithms

Quantified Score

Hi-index	0.00

Visualization

Abstract

This article describes a parallel OpenMP and/or MPI implementation of an algorithm for solving the Recursive Least Squares (RLS) problem, suitable for heterogeneous parallel systems. A model for automatic/adaptive load balancing is proposed for either homogeneous or heterogeneous parallel systems. The algorithm is based on a variant of the Kalman Filter named the square root and extended version Information Filter and is oriented to be used in real time applications.