Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/1990
Title: | Ordinary linear model estimation on a massively parallel simd computer | Authors: | Kontoghiorghes, Erricos John | metadata.dc.contributor.other: | Κοντογιώργης, Έρρικος Γιάννης | Major Field of Science: | Social Sciences | Keywords: | Algorithms;Mathematical models;Regression analysis | Issue Date: | 1999 | Source: | Concurrency Practice and Experience, 1999, vol. 11, no. 7, pp. 323-341 | Volume: | 11 | Issue: | 7 | Start page: | 323 | End page: | 341 | Journal: | Concurrency Practice and Experience | Abstract: | Efficient algorithms for estimating the coefficient parameters of the ordinary linear model on a massively parallel SIMD computer are presented. The numerical stability of the algorithms is ensured by using orthogonal transformations in the form of Householder reflections and Givens plane rotations to compute the complete orthogonal decomposition of the coefficient matrix. Algorithms for reconstructing the orthogonal matrices involved in the decompositions are also designed, implemented and analyzed. The implementation of all algorithms on the targeted SIMD array processor is considered in detail. Timing models for predicting the execution time of the implementations are derived using regression modelling methods. The timing models also provide an insight into how the algorithms interact with the parallel computer. The predetermined factors used in the regression fits are derived from the number of memory layers involved in the factorization process of the matrices. Experimental results show the high accuracy and predictive power of the timing models. | URI: | https://hdl.handle.net/20.500.14279/1990 | ISSN: | 10403108 | DOI: | 10.1002/(SICI)1096-9128(199906)11:7<323::AID-CPE425>3.0.CO;2-I | Rights: | © Wiley | Type: | Article | Affiliation : | Université de Neuchâtel |
Appears in Collections: | Άρθρα/Articles |
CORE Recommender
SCOPUSTM
Citations
2
checked on Nov 9, 2023
Page view(s)
569
Last Week
0
0
Last month
4
4
checked on Dec 23, 2024
Google ScholarTM
Check
Altmetric
Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.