LASCA: Featured Projects

Computer network emulation, Srinidhi Varadarajan, Computer Science.
The continuing exponential growth of the Internet has resulted in rapid proliferation of new network protocols. Protocol interactions have become vastly more complex and it is no longer possible to analyze their runtime behavior in small experimental testbeds. Furthermore, critical network protocols are highly distributed in nature. The complexity of router software, the backbone of Internet communication, requires large-scale testbeds to verify scalability and validate correctness. The reseach goal of this project is to enable the systematic study of network applications and protocols through the development of a scalable network emulation testbed. To achieve this goal, we are building a new network emulation system called the Open Network Emulator (ONE), based on a novel compiler directed framework that supports both simulation and direct code execution paradigms. This integration of paradigms, which often have opposing requirements, enables a new dimension in verification and validation of network protocols. Event-driven simulation models can now be validated through their interaction with real-world code counterparts. Our compiler directed strategy provides a modular framework that includes support for automatic checkpointing and recovery, without application support. Our compiler directed strategy for generating composable code objects also enables existing non-OO codes to use the power of grid computing environments. Support for transparent checkpointing and recovery enables large scientific simulation codes to use optimistic parallel discrete event simulation (PDES) algorithms without modification. Support for runtime code migration enables new dynamic load balancing algorithms that are of use to large-scale parallel computation. For more information, visit the Computing Systems Research Lab.

Grid computing, Dennis Kafura and Cal Ribbens, Computer Science.
The goal of this project is to establish a campus-wide computational grid at Virginia Tech. The group is working with LASCA affiliates with large-scale computing needs to access a variety of computing resources from around the university---in some cases leveraging unused cycles on workstations, in other cases combining multiple clusters and SMPs in order to run extremely large parallel codes. Research projects pursued by this group include privilege management and authorization, scheduling, runtime algorithm selection, automatic job checkpointing and migration, and configurable resource brokering. For more information, visit the Grid-Computing Research Group.

Molecular electronics, Massimiliano Di Ventra, Physics.
Prof. Di Ventra's research focuses on using first-principles atomistic calculations to predict the electronic, optical and transport properties of materials. He is a pioneer of transport calculations in molecular devices from first principles. This includes the investigation of fundamental phenomena at the atomic level, e.g., electromigration and temperature effects. His recent work also includes the study of the transport properties of nanotubes, their metal contacts and field-effect behavior, thin-film oxidation of wide-gap materials like SiC, and the improvement of the SiC-SiO2 interface via NO annealing.

Molecular modeling---protein structure and function, David Bevan, Biochemistry.
Prof. Bevan is working to isolate and characterize proteins with the ultimate goal of modeling the dynamics and interactions of the proteins that serve as the basis of their function. For example, his group has isolated a protein from cyanobacteria that is called cyanoglobin. It is a heme-containing protein that binds oxygen reversibly, and it functions in some capacity in nitrogen fixation. The kinetics of ligand binding to cyanoglobin have been defined, and a three-dimensional model of the structure of the protein has recently been developed. Other topics of interest include a study of the beta-glucosidases and the application of molecular modeling to the study of endocrine disruptors and to an analysis of the structure and dynamics of DNA.

Molecular statics and dynamics, Diana Farkas, Materials Science & Engineering.
Prof. Farkas research concentrates on theoretical studies of extended defect structure in novel ordered intermetallic alloys, with emphasis on predicting mechanical behavior. Using various computer simulation techniques, she studies the atomic structure of grain boundaries and dislocation cores in these materials and the interaction of dislocations and grain boundaries. The goal is to contribute to the understanding of the mechanical behavior of these alloys in both single crystal and polycrystalline form and to be able to suggest ways to improve their ductility. Her research encompasses state-of-the-art work in atomistic micro-mechanical and continuum level computational work in the areas of material deformation and fracture, wave propagation, and visualization.

Seismic modelling --- waves in complex media, Matthias Imhof, Geological Sciences.
Prof. Imhof's work focuses on simulating the propagation of acoustic and elastic waves in complex media and the interpretation of seismic experiments. Computation of synthetic seismograms is essential for designing seismic experiments, data processing tools, and interpretation schemes. Dr. Imhof is developing new simulation algorithms based on the finite-difference and boundary-element methods. A current example is the simulation of elastic waves in media with embedded fractures or cavities. With regard to data interpretation, Dr. Imhof is developing a full-waveform tomographic algorithm to infer the subsurface from both reflected and transmitted seismic signals. In addition to deterministic inversion, he is also working on estimating local second-order statistics of subsurface heterogeneity from seismic data and the construction of compatible heterogeneity models.


Last updated 12/12/02
LASCA Home