Complexity of parallel implementation of domain decomposition techniques for elliptic partial differential equations

Journal Article · Tue Mar 01 00:00:00 EST 1988 · SIAM J. Sci. Stat. Comput.; (United States)

DOI:https://doi.org/10.1137/0909020· OSTI ID:5299325

Gropp, W D; Keyes, D E

The authors discuss the parallel implementation of preconditioned conjugate gradient (PCG)-based domain decomposition techniques for self-adjoint elliptic partial differential equations in two dimensions on several architectures. The complexity of these methods is described on a variety of message-passing parallel computers as a function of the size of the problem, number of processors and relative communication speeds of the processors. They show that communication startups are very important, and that even the small amount of global communication in these methods can significantly reduce the performance of many message-passing architectures.

• Research Organization: Research Center for Scientific Computation, Yale Univ., New Haven, CT 06520 (US)
• OSTI ID: 5299325
• Journal Information: SIAM J. Sci. Stat. Comput.; (United States), Vol. 9:2
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
ALGORITHMS
MEASURING METHODS
NUMERICAL SOLUTION
PARALLEL PROCESSING
PARTIAL DIFFERENTIAL EQUATIONS
PERFORMANCE
ARRAY PROCESSORS
COMPUTER ARCHITECTURE
DATA TRANSMISSION
COMMUNICATIONS
DIFFERENTIAL EQUATIONS
EQUATIONS
MATHEMATICAL LOGIC
PROGRAMMING
990210* - Supercomputers- (1987-1989)