Distributed simulation, 1989

Conference · Sun Jan 01 04:00:00 EST 1989

OSTI ID:6274691

Unger, B ^[1]; Fujimoto, R ^[2]

---

1. Univ. of Calgary (CA)
2. Univ. of Utah, UT (US)

Computer simulation of large, complex systems remains a major stumbling block in many research and development efforts. Computational requirements continue to grow and far exceed the capabilities of uniprocessor hardware. Simulation of many important applications in engineering and economics require excessive amounts of time on existing machines, and many large-scale simulations cannot be performed because computation costs are prohibitive. Obtaining truly significant speedups for these problems requires the widespread exploitation of parallelism. Research in parallel simulation, and parallel discrete event simulation in particular, has expanded dramatically over the last few years. The increased availability of parallel computers, coupled with the intellectual challenges associated with exploring new uncharted territory in this difficult problem domain, has lead to a renaissance of activity. The authors report recent developments regarding the application of parallel computation to both discrete event simulation problems. Many of the papers address advances in parallel discrete event simulation, where synchronization of simulated time clocks across the parallel simulator represents a major stumbling block to achieving significant speedups.

• OSTI ID: 6274691
• Report Number(s): CONF-890360--; ISBN: 0-911801-49-9
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
ABSTRACTS
ALGORITHMS
ARRAY PROCESSORS
COMPUTER ARCHITECTURE
COMPUTER NETWORKS
COMPUTERIZED SIMULATION
COMPUTERS
DATA PROCESSING
DIGITAL COMPUTERS
DISTRIBUTED DATA PROCESSING
DOCUMENT TYPES
LEADING ABSTRACT
MATHEMATICAL LOGIC
PARALLEL PROCESSING
PROCESSING
PROGRAMMING
SIMULATION
SUPERCOMPUTERS