Virginia Tech - Wake Forest University School of Biomedical Engineering & Sciences
Computer Science Technical Reports @Virginia TechNot a member yet
997 research outputs found
Sort by
Design and Implementation of a Massively Parallel Version of DIRECT
Get PDFThis paper describes several massively parallel implementations for a global search algorithm DIRECT.
Two parallel schemes take different approaches to address DIRECT's design challenges imposed by memory requirements
and data dependency. Three design aspects in topology, data structures, and task allocation are compared in
detail. The goal is to analytically investigate the strengths and weaknesses of these parallel schemes, identify several
key sources of inefficiency, and experimentally evaluate a number of improvements in the latest parallel DIRECT
implementation. The performance studies demonstrate improved data structure efficiency and load balancing on a
2200 processor cluster
Literature Survey on Interaction Techniques for Large Displays
Get PDFWhen designing for large screen displays, designers are forced to deal with cursor tracking issues, interacting over distances, and space management issues. Because of the large visual angle of the user that the screen can cover, it may be hard for users to begin and complete search tasks for basic items such as cursors or icons. In addition, maneuvering over long distances and acquiring small targets understandably takes more time than the same interactions on normally sized screen systems. To deal with these issues, large display researchers have developed more and more unconventional devices, methods and widgets for interaction, and systems for space and task management.
For tracking cursors there are techniques that deal with the size and shape of the cursor, as well as the “density†of the cursor. There are other techniques that help direct the attention of the user to the cursor.
For target acquisition on large screens, many researchers saw fit to try to augment existing 2D GUI metaphors. They try to optimize Fitts’ law to accomplish this. Some techniques sought to enlarge targets while others sought to enlarge the cursor itself. Even other techniques developed ways of closing the distances on large screen displays. However, many researchers feel that existing 2D metaphors do not and will not work for large screens. They feel that the community should move to more unconventional devices and metaphors. These unconventional means include use of eye-tracking, laser-pointing, hand-tracking, two-handed touchscreen techniques, and other high-DOF devices.
In the end, many of these developed techniques do provide effective means for interaction on large displays. However, we need to quantify the benefits of these methods and understand them better. The more we understand the advantages and disadvantages of these techniques, the easier it will be to employ them in working large screen systems. We also need to put into place a kind of interaction standard for these large screen systems. This could mean simply supporting desktop events such as pointing and clicking. It may also mean that we need to identify the needs of each domain that large screens are used for and tailor the interaction techniques for the domain
Dynamic Multigrain Parallelization on the Cell Broadband Engine
Get PDFThis paper addresses the problem of orchestrating and scheduling
parallelism at multiple levels of granularity on heterogeneous
multicore processors. We present policies and mechanisms for adaptive
exploitation and scheduling of multiple layers of parallelism on the
Cell Broadband Engine. Our policies combine event-driven task
scheduling with malleable loop-level parallelism, which is exposed
from the runtime system whenever task-level parallelism leaves cores
idle. We present a runtime system for scheduling applications with
layered parallelism on Cell and investigate its potential with RAxML,
a computational biology application which infers large phylogenetic
trees, using the Maximum Likelihood (ML) method. Our experiments show
that the Cell benefits significantly from dynamic parallelization
methods, that selectively exploit the layers of parallelism in the
system, in response to workload characteristics. Our runtime
environment outperforms naive parallelization and scheduling based on
MPI and Linux by up to a factor of 2.6. We are able to execute RAxML
on one Cell four times faster than on a dual-processor system with
Hyperthreaded Xeon processors, and 5--10\% faster than on a
single-processor system with a dual-core, quad-thread IBM Power5
processor
A Special Topics Course on Personal Information Management
Get PDFPersonal Information Management (PIM) is an important emerg- ing area of study in Computer Science and Information Systems. During the Spring of 2006, we offered a special topics course in PIM at Virginia Tech. This paper presents some motivation of why studying PIM is important, the goals for the course, some sam- ple material from the course, and a few student evaluations. The paper presents in detail an activity called “Day in the Life of My Information†that resulted in an interesting experience from both, educational and research points of view
Proceedings of the First Annual Virginia Tech Center for Human-Computer Interaction Research Experience for Undergraduates (REU) Symposium
Get PDFVirginia Tech's Center for Human-Computer Interaction presents the project abstracts for the REU ’06 symposium. The REU (Research Experience for Undergraduates) program provides undergraduate students from various universities with the opportunity to spend eight weeks at Virginia Tech, working with our faculty and graduate students on research projects using the state-of-the-art technology and laboratories assembled here. The REU program is sponsored by a National Science Foundation grant IIS-0552732
Forward, Tangent Linear, and Adjoint Runge Kutta Methods in KPP–2.2 for Efficient Chemical Kinetic Simulations
Get PDFThe Kinetic PreProcessor (KPP) is a widely used software environment which generates Fortran90, Fortran77, Matlab, or C code for the simulation of chemical kinetic systems. High computational efficiency is attained by exploiting the sparsity pattern of the Jacobian and Hessian. In this paper we report on the implementation of two new families of stiff numerical integrators in the new version 2.2 of KPP. One family is the fully implicit three-stage Runge Kutta methods, and the second family are singly diagonally-implicit Runge Kutta methods. For each family tangent linear models for direct decoupled sensitivity analysis, and adjoint models for adjoint sensitivity analysis of chemical kinetic systems are also implemented. To the best of our knowledge this work brings the first implementation of the direct decoupled sensitivity method and of the discrete adjoint sensitivity method with Runge Kutta methods. Numerical experiments with a chemical system used in atmospheric chemistry illustrate the power of the stiff Runge Kutta integrators and their tangent linear and discrete adjoint models. Through the integration with KPP–2.2. these numerical techniques become easily available to a wide community interested in the simulation of chemical kinetic systems
Architectural Refactoring for Fast and Modular Bioinformatics Sequence Search
Get PDFBioinformaticists use the Basic Local Alignment Search Tool (BLAST) to characterize an unknown sequence by
comparing it against a database of known sequences, thus detecting evolutionary relationships and biological properties. mpiBLAST is a widely-used, high-performance, open-source parallelization of BLAST that runs on a computer cluster delivering super-linear speedups. However, the Achilles heel of mpiBLAST is its lack of modularity, adversely affecting maintainability and extensibility; an effective architectural refactoring will benefit both users and developers.
This paper describes our experiences in the architectural refactoring of mpiBLAST into a modular, high-performance software package. Our evaluation of five component-oriented designs culminated in a design that enables modularity while retaining high-performance. Furthermore, we achieved this refactoring effectively and efficiently using eXtreme Programming techniques. These experiences will be of value to software engineers faced with the challenge of creating maintainable and extensible, high-performance, bioinformatics software
The Cost of Numerical Integration in Statistical Decision-theoretic Methods for Robust Design Optimization
Get PDFThe Bayes principle from statistical decision theory provides a conceptual framework
for quantifying uncertainties that arise in robust design optimization. The difficulty with
exploiting this framework is computational, as it leads to objective and constraint functions that
must be evaluated by numerical integration. Using a prototypical robust design optimization
problem, this study explores the computational cost of multidimensional integration (computing
expectation) and its interplay with optimization algorithms. It concludes that straightforward
application of standard off-the-shelf optimization software to robust design is prohibitively
expensive, necessitating adaptive strategies and the use of surrogates
Proceedings of the Resolve Workshop 2006
Get PDFThe aim of the RESOLVE Workshop 2006 was to bring together researchers and educators interested in: Refining formal approaches to software engineering, especially component-based systems, and introducing them into the classroom. The workshop served as a forum for participants to present and discuss recent advances, trends, and concerns in these areas, as well as formulate a common understanding of emerging research issues and possible solution paths
The Effects of Task, Task Mapping, and Layout Space on User Performance in Information-Rich Virtual Environments
Get PDFHow should abstract information be displayed in Information-Rich Virtual Environments (IRVEs)? There are a variety of techniques available, and it is important to determine which techniques help foster a user’s understanding both within and between abstract and spatial information types. Our evaluation compared two such techniques: Object Space and Display Space. Users strongly prefer Display Space over Object Space, and those who use Display Space may perform better. Display Space was faster and more accurate than Object Space for tasks comparing abstract information. Object Space was more accurate for comparisons of spatial information. These results suggest that for abstract criteria, visibility is a more important requirement than perceptual coupling by depth and association cues. They also support the value of perceptual coupling for tasks with spatial criteria