MD -- A molecular dynamics application
MD is a complete high-performance parallel molecular dynamics
system. It offers abstractions with which programmers can implement efficient
strategies for managing the control and dataflow required for the basic
molecular dynamics calculations as well as for global statistics and
scientific visualization. In addition, MD is designed to support
experimentation with alternative methods of domain decomposition and of thread
synchronization, and with alternative approaches to exploiting molecular
locality.
A compressed tar file containing the MD source code and
sample data can be fetched by clicking here. (This file is approx 0.9 Mbyte. It was
compressed with Unix "compress". Your Web browser may automatically
decompress the file on fetch. In this case, simply save the file locally,
untar and follow README directions to build the application.)
Related Projects
- Cthreads -- A user-level threads
library for parallel programming. Cthreads is required to build
MD.
- Falcon -- A monitoring and steering
system for parallel programs. Falcon has been used to diagnose and control MD
during parallel execution.
Related Publications
- Design and Analysis of a Parallel Molecular Dynamics
Application, Greg Eisenhauer and Karsten Schwan, in Journal of Parallel
and Distributed Computing, Volume 35, Number 1, pp.76-90, May 25, 1996.
- Opportunities
and Tools for Highly Interactive Distributed and Parallel Computing,
Greg Eisenhauer, Weiming Gu, Thomas Kindler, Karsten Schwan, Dilma Silva
and Jeffrey Vetter, chapter in Parallel Computer Systems: Performance
Instrumentation and Visualization, Rebecca Koskela and Margaret Simmons,
editors, ACM Press, 1996.
pport
-
MD -- A Flexible Framework
for High-Speed Parallel Molecular Dynamics, Greg Eisenhauer and Karsten Schwan, In High Performance
Computing, Proceedings of the 1994 SCS Simulation Multiconference, pages
70-75, April 1994, Society for Computer Simulation.
- Falcon -- Toward Interactive Parallel Programs: The On-line
Steering of a Molecular Dynamics Application, Greg Eisenhauer,
Weiming Gu, Karsten Schwan and Niru Mallavarupu, In Proceedings of The
Third International Symposium on High-Performance Distributed Computing
(HPDC-3), San Francisco, August 1994. IEEE Computer Society. Also
available as tech report GIT-CC-94-08,
College of Computing, Georgia Institute
of Technology, Atlanta, GA 30332-0280.
- Portable
Self-Describing Binary Data Streams, Greg Eisenhauer, Technical
Report GIT-CC-94-45, College of Computing, Georgia Institute of Technology,
Atlanta, GA 30332-0280.
Contact Information:
Greg Eisenhauer,
College of Computing,
Georgia Institute of Technology