NAMD: Biomolecular Simulation on Thousands of Processors
International Conference for High Performance Computing, Networking, Storage and Analysis (SC) 2002
Publication Type: Paper
Repository URL:
Abstract
NAMD is a fully featured, production molecular dynamics program for
high performance simulation of large biomolecular systems. We have
previously, at SC 2000, presented scaling results for simulations
with cutoff electrostatics on up to 2048 processors of the ASCI Red
machine, achieved with an object-based hybrid force and spatial
decomposition scheme and an aggressive measurement-based predictive
load balancing framework. We extend this work by demontrating
similar scaling on the much faster processors of the PSC Lemieux
Alpha cluster, and for simulations employing efficient (N log N)
particle mesh Ewald full electrostatics. This unprecedented
scalability in a biomolecular simulation code has been attained
through latency tolerance, adaptation to multiprocessor nodes, and
the direct use of the Quadrics Elan library in place on MPI by the
Charm++/Converse parallel runtime system.
TextRef
James C. Phillips and Gengbin Zheng and Sameer Kumar and Laxmikant V. Kale,
"NAMD: Biomolecular Simulation on Thousands of Processors", Proceedings of the 2002
ACM/IEEE conference on Supercomputing, Baltimore, MD, pp. 1-18, September, 2002.
People
- James Phillips
- Gengbin Zheng
- Sameer Kumar
- Laxmikant Kale
Research Areas