Sparse Cholesky factorization on a local-memory multiprocessor
This article deals with the problem of factoring a large sparse positive definite matrix on a multiprocessor system. The processors are assumed to have substantial local memory but no globally shared memory. They communicate among themselves and with a host processor through message passing. The authors' primary interest is designing an algorithm which exploits parallelism, rather than in exploiting features of the underlying topology of the hardware. However, part of the study is aimed at determining for certain sparse matrix problems, whether hardware based on the binary hypercube topology adequately supports the communication requirements for such problems. Numerical results from experiments conducted on a hypercube multiprocessor are included.
- Research Organization:
- Dept. of Computer Science, Univ. of Tennessee, Knoxville, TN 37916 (US)
- OSTI ID:
- 5152267
- Journal Information:
- SIAM J. Sci. Stat. Comput.; (United States), Journal Name: SIAM J. Sci. Stat. Comput.; (United States) Vol. 9:2; ISSN SIJCD
- Country of Publication:
- United States
- Language:
- English
Similar Records
Sparse Cholesky factorization on a multiprocessor
Supernodal symbolic Cholesky factorization on a local-memory multiprocessor
Related Subjects
990210* -- Supercomputers-- (1987-1989)
ALGORITHMS
ARRAY PROCESSORS
COMMUNICATIONS
COMPUTER ARCHITECTURE
COMPUTER CALCULATIONS
DATA
DATA TRANSMISSION
DESIGN
ELECTRONIC CIRCUITS
INFORMATION
INTEGRATED CIRCUITS
MATHEMATICAL LOGIC
MATHEMATICS
MATRICES
MEMORY DEVICES
MICROELECTRONIC CIRCUITS
NUMERICAL DATA
PARALLEL PROCESSING
PROGRAMMING
TOPOLOGY