Browsing by Subject "system"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item A Recommendation System for Preconditioned Iterative Solvers(2011-02-22) George, ThomasSolving linear systems of equations is an integral part of most scientific simulations. In recent years, there has been a considerable interest in large scale scientific simulation of complex physical processes. Iterative solvers are usually preferred for solving linear systems of such magnitude due to their lower computational requirements. Currently, computational scientists have access to a multitude of iterative solver options available as "plug-and- play" components in various problem solving environments. Choosing the right solver configuration from the available choices is critical for ensuring convergence and achieving good performance, especially for large complex matrices. However, identifying the "best" preconditioned iterative solver and parameters is challenging even for an expert due to issues such as the lack of a unified theoretical model, complexity of the solver configuration space, and multiple selection criteria. Therefore, it is desirable to have principled practitioner-centric strategies for identifying solver configuration(s) for solving large linear systems. The current dissertation presents a general practitioner-centric framework for (a) problem independent retrospective analysis, and (b) problem-specific predictive modeling of performance data. Our retrospective performance analysis methodology introduces new metrics such as area under performance-profile curve and conditional variance-based finetuning score that facilitate a robust comparative performance evaluation as well as parameter sensitivity analysis. We present results using this analysis approach on a number of popular preconditioned iterative solvers available in packages such as PETSc, Trilinos, Hypre, ILUPACK, and WSMP. The predictive modeling of performance data is an integral part of our multi-stage approach for solver recommendation. The key novelty of our approach lies in our modular learning based formulation that comprises of three sub problems: (a) solvability modeling, (b) performance modeling, and (c) performance optimization, which provides the flexibility to effectively target challenges such as software failure and multiobjective optimization. Our choice of a "solver trial" instance space represented in terms of the characteristics of the corresponding "linear system", "solver configuration" and their interactions, leads to a scalable and elegant formulation. Empirical evaluation of our approach on performance datasets associated with fairly large groups of solver configurations demonstrates that one can obtain high quality recommendations that are close to the ideal choices.Item Development of a comprehensive reporting system for a school reform organization: The Accelerated Schools Project(Texas A&M University, 2006-04-12) Stephens, Jennifer AnneGiven the conflicting research results on the effectiveness of whole-school reform models (Nunnery, 1998; Stringfield & Herman, 1997; American Institutes for Research, 1999; U.S. Department of Education, 2004), there is a need to focus on the evaluation procedures of whole-school reform organizations. Because the ultimate goal is to improve school performance, it should also be a goal of each whole-school reform organization to design a comprehensive data collection system to evaluate each school??s performance. A comprehensive reporting system was developed for a school reform organization, the Accelerated Schools Project (ASP). Using the steps of the research and development process recommended by Borg and Gall (1989), this study: (a) developed a theoretical framework for the reporting system, (b) identified data that should be collected in the reporting system, (c) performed a field test with an expert panel of educational professionals, (d) developed a preliminary form of the reporting system, (e) performed a main field test with principals and coaches in the ASP network, (f) reported field test results, (g) revised the preliminary reporting system, (h) developed a website for the reporting system, and (i) provided recommendations for the completion, dissemination and implementation of the system in accelerated schools across the nation. This study has important implications for both the ASP community and for the entire whole-school reform community. For the ASP community, the reporting system could be used: (a) to collect data in all accelerated schools across the nation (b) as a longitudinal database of information to monitor data on each ASP school, and (c) to generate school summary reports on ASP schools. These data will assist researchers in measuring the effectiveness of the ASP model on student achievement and other important variables. For the whole-school reform community, the method used in this study could be replicated in other school reform organizations to develop a comprehensive reporting system. By providing consistent data for school reform organizations to evaluate the impact of their models on students and schools, educational researchers will be better equipped to understand each model??s impact, and thus will better understand the diverse research results on school reform effectiveness.