Please use this identifier to cite or link to this item:
|Title:||Recursive least-squares using a hybrid householder algorithm on massively parallel simd systems||Authors:||Clint, Maurice
Naegeli, H. H.
Kontoghiorghes, Erricos John
|Keywords:||Algorithms;Computer simulation;Recursive functions;Least squares||Issue Date:||1999||Source:||Parallel Computing, 1999, Volume 25, Issue 9, Pages 1147-1159||Abstract:||Within the context of recursive least-squares, the implementation of a Householder algorithm for block updating the QR decomposition, on massively parallel SIMD systems, is considered. Initially, two implementations based on different mapping strategies for distributing the data matrices over the processing elements of the parallel computer are investigated. Timing models show that neither of these implementations is superior in all cases. In order to increase computational speed, a hybrid implementation uses performance models to partition the problem into two subproblems which are then solved using the first and second implementation, respectively.||URI:||http://ktisis.cut.ac.cy/handle/10488/6800||ISSN:||01678191||DOI:||http://dx.doi.org/10.1016/S0167-8191(99)00043-5||Rights:||© 1999 Elsevier Science B.V. All rights reserved.||Type:||Article||Affiliation:||Institut d'Informatique, Université de Neuchâtel, Switzerland|
|Appears in Collections:||Άρθρα/Articles|
checked on Feb 13, 2018
Page view(s) 50220
checked on Sep 26, 2021
Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.