Vector Nonlinear Time-Series Analysis of Gamma-Ray Burst Datasets on Heterogeneous Clusters

Vector Nonlinear Time-Series Analysis of Gamma-Ray Burst Datasets on Heterogeneous Clusters

The simultaneous analysis of a number of related datasets using a single statistical model is an important problem in statistical computing. A parameterized statistical model is to be fitted on multiple datasets and tested for goodness of fit within a fixed analytical framework. Definitive conclusio...

Full description

Bibliographic Details
Main Authors: Ioana Banicescu, Ricolindo L. Cariño, Jane L. Harvill, John Patrick Lestrade
Format: Article
Language:English
Published: Hindawi Limited 2005-01-01
Series:Scientific Programming
Online Access:http://dx.doi.org/10.1155/2005/674158
id doaj-6889e5e4414d4dc1a3cf3ddd1d4f93dc
record_format Article
spelling doaj-6889e5e4414d4dc1a3cf3ddd1d4f93dc2021-07-02T01:06:45ZengHindawi LimitedScientific Programming1058-92441875-919X2005-01-01132677710.1155/2005/674158Vector Nonlinear Time-Series Analysis of Gamma-Ray Burst Datasets on Heterogeneous ClustersIoana Banicescu0Ricolindo L. Cariño1Jane L. Harvill2John Patrick Lestrade3Department of Computer Science and Engineering, PO Box 9637, Mississippi State University, Mississippi State MS 39762, USACenter for Computational Sciences ERC, Mississippi State University, PO Box 9627, Mississippi State University, Mississippi State MS 39762, USACenter for Computational Sciences ERC, Mississippi State University, PO Box 9627, Mississippi State University, Mississippi State MS 39762, USADepartment of Physics and Astronomy, Mississippi State University, PO Box 5167, Mississippi State University, Mississippi State MS 39762, USAThe simultaneous analysis of a number of related datasets using a single statistical model is an important problem in statistical computing. A parameterized statistical model is to be fitted on multiple datasets and tested for goodness of fit within a fixed analytical framework. Definitive conclusions are hopefully achieved by analyzing the datasets together. This paper proposes a strategy for the efficient execution of this type of analysis on heterogeneous clusters. Based on partitioning processors into groups for efficient communications and a dynamic loop scheduling approach for load balancing, the strategy addresses the variability of the computational loads of the datasets, as well as the unpredictable irregularities of the cluster environment. Results from preliminary tests of using this strategy to fit gamma-ray burst time profiles with vector functional coefficient autoregressive models on 64 processors of a general purpose Linux cluster demonstrate the effectiveness of the strategy.http://dx.doi.org/10.1155/2005/674158
collection DOAJ
language English
format Article
sources DOAJ
author Ioana Banicescu
Ricolindo L. Cariño
Jane L. Harvill
John Patrick Lestrade
spellingShingle Ioana Banicescu
Ricolindo L. Cariño
Jane L. Harvill
John Patrick Lestrade
Vector Nonlinear Time-Series Analysis of Gamma-Ray Burst Datasets on Heterogeneous Clusters
Scientific Programming
author_facet Ioana Banicescu
Ricolindo L. Cariño
Jane L. Harvill
John Patrick Lestrade
author_sort Ioana Banicescu
title Vector Nonlinear Time-Series Analysis of Gamma-Ray Burst Datasets on Heterogeneous Clusters
title_short Vector Nonlinear Time-Series Analysis of Gamma-Ray Burst Datasets on Heterogeneous Clusters
title_full Vector Nonlinear Time-Series Analysis of Gamma-Ray Burst Datasets on Heterogeneous Clusters
title_fullStr Vector Nonlinear Time-Series Analysis of Gamma-Ray Burst Datasets on Heterogeneous Clusters
title_full_unstemmed Vector Nonlinear Time-Series Analysis of Gamma-Ray Burst Datasets on Heterogeneous Clusters
title_sort vector nonlinear time-series analysis of gamma-ray burst datasets on heterogeneous clusters
publisher Hindawi Limited
series Scientific Programming
issn 1058-9244
1875-919X
publishDate 2005-01-01
description The simultaneous analysis of a number of related datasets using a single statistical model is an important problem in statistical computing. A parameterized statistical model is to be fitted on multiple datasets and tested for goodness of fit within a fixed analytical framework. Definitive conclusions are hopefully achieved by analyzing the datasets together. This paper proposes a strategy for the efficient execution of this type of analysis on heterogeneous clusters. Based on partitioning processors into groups for efficient communications and a dynamic loop scheduling approach for load balancing, the strategy addresses the variability of the computational loads of the datasets, as well as the unpredictable irregularities of the cluster environment. Results from preliminary tests of using this strategy to fit gamma-ray burst time profiles with vector functional coefficient autoregressive models on 64 processors of a general purpose Linux cluster demonstrate the effectiveness of the strategy.
url http://dx.doi.org/10.1155/2005/674158
work_keys_str_mv AT ioanabanicescu vectornonlineartimeseriesanalysisofgammarayburstdatasetsonheterogeneousclusters
AT ricolindolcarino vectornonlineartimeseriesanalysisofgammarayburstdatasetsonheterogeneousclusters
AT janelharvill vectornonlineartimeseriesanalysisofgammarayburstdatasetsonheterogeneousclusters
AT johnpatricklestrade vectornonlineartimeseriesanalysisofgammarayburstdatasetsonheterogeneousclusters
_version_ 1721345430469476352

Similar Items