Persistent Link:
http://hdl.handle.net/10150/195294
Title:
Physics Aware Programming Paradigm and Runtime Manager
Author:
Zhang, Yeliang
Issue Date:
2007
Publisher:
The University of Arizona.
Rights:
Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
Abstract:
The overarching goal of this dissertation research is to realize a virtual collaboratory for the investigation of large-scale scientific computing applications which generally experience different execution phases at runtime and each phase has different computational, communication and storage requirements as well as different physical characteristics. Consequently, an optimal solution or numerical scheme for one execution phase might not be appropriate for the next phase of the application execution. Choosing the ideal numerical algorithms and solutions for all application runtime phases remains an active research area. In this dissertation, we present Physics Aware Programming (PAP) paradigm that enables programmers to identify the appropriate solution methods to exploit the heterogeneity and the dynamism of the application execution states. We implement a Physics Aware Runtime Manager (PARM) to exploit the PAP paradigm. PARM periodically monitors and analyzes the runtime characteristics of the application to identify its current execution phase (state). For each change in the application execution phase, PARM will adaptively exploit the spatial and temporal attributes of the application in the current state to identify the ideal numerical algorithms/solvers that optimize its performance. We have evaluated our approach using a real world application (Variable Saturated Aquifer Flow and Transport (VSAFT2D)) commonly used in subsurface modeling, diffusion problem kernel and seismic problem kernel. We evaluated the performance gain of the PAP paradigm with up to 2,000,000 nodes in the computation domain implemented on 32 processors. Our experimental results show that by exploiting the application physics characteristics at runtime and applying the appropriate numerical scheme with adapted spatial and temporal attributes, a significant speedup can be achieved (around 80%) and the overhead injected by PAP is negligible (less than 2%). We also show that the results using PAP is as accurate as the numerical solutions that use fine grid resolution.
Type:
text; Electronic Dissertation
Keywords:
distributed systems; simulation; application-transparent adaptation; numerical algorithm and problems; error analysis
Degree Name:
PhD
Degree Level:
doctoral
Degree Program:
Electrical & Computer Engineering; Graduate College
Degree Grantor:
University of Arizona
Advisor:
Hariri, Salim
Committee Chair:
Hariri, Salim

Full metadata record

DC FieldValue Language
dc.language.isoENen_US
dc.titlePhysics Aware Programming Paradigm and Runtime Manageren_US
dc.creatorZhang, Yeliangen_US
dc.contributor.authorZhang, Yeliangen_US
dc.date.issued2007en_US
dc.publisherThe University of Arizona.en_US
dc.rightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.en_US
dc.description.abstractThe overarching goal of this dissertation research is to realize a virtual collaboratory for the investigation of large-scale scientific computing applications which generally experience different execution phases at runtime and each phase has different computational, communication and storage requirements as well as different physical characteristics. Consequently, an optimal solution or numerical scheme for one execution phase might not be appropriate for the next phase of the application execution. Choosing the ideal numerical algorithms and solutions for all application runtime phases remains an active research area. In this dissertation, we present Physics Aware Programming (PAP) paradigm that enables programmers to identify the appropriate solution methods to exploit the heterogeneity and the dynamism of the application execution states. We implement a Physics Aware Runtime Manager (PARM) to exploit the PAP paradigm. PARM periodically monitors and analyzes the runtime characteristics of the application to identify its current execution phase (state). For each change in the application execution phase, PARM will adaptively exploit the spatial and temporal attributes of the application in the current state to identify the ideal numerical algorithms/solvers that optimize its performance. We have evaluated our approach using a real world application (Variable Saturated Aquifer Flow and Transport (VSAFT2D)) commonly used in subsurface modeling, diffusion problem kernel and seismic problem kernel. We evaluated the performance gain of the PAP paradigm with up to 2,000,000 nodes in the computation domain implemented on 32 processors. Our experimental results show that by exploiting the application physics characteristics at runtime and applying the appropriate numerical scheme with adapted spatial and temporal attributes, a significant speedup can be achieved (around 80%) and the overhead injected by PAP is negligible (less than 2%). We also show that the results using PAP is as accurate as the numerical solutions that use fine grid resolution.en_US
dc.typetexten_US
dc.typeElectronic Dissertationen_US
dc.subjectdistributed systemsen_US
dc.subjectsimulationen_US
dc.subjectapplication-transparent adaptationen_US
dc.subjectnumerical algorithm and problemsen_US
dc.subjecterror analysisen_US
thesis.degree.namePhDen_US
thesis.degree.leveldoctoralen_US
thesis.degree.disciplineElectrical & Computer Engineeringen_US
thesis.degree.disciplineGraduate Collegeen_US
thesis.degree.grantorUniversity of Arizonaen_US
dc.contributor.advisorHariri, Salimen_US
dc.contributor.chairHariri, Salimen_US
dc.contributor.committeememberKrunz, Marwanen_US
dc.contributor.committeememberRozenblit, Jerzy W.en_US
dc.identifier.proquest2253en_US
dc.identifier.oclc659748093en_US
All Items in UA Campus Repository are protected by copyright, with all rights reserved, unless otherwise indicated.