Implementation of parallel matrix decomposition for NIKE3D on the KSR1 system
New massively parallel computer architecture has revolutionized the design of computer algorithms and promises to have significant influence on algorithms for engineering computations. Realistic engineering problems using finite element analysis typically imply excessively large computational requirements. Parallel supercomputers that have the potential for significantly increasing calculation speeds can meet these computational requirements. This report explores the potential for the parallel Cholesky (U{sup T}DU) matrix decomposition algorithm on NIKE3D through actual computations. The examples of two- and three-dimensional nonlinear dynamic finite element problems are presented on the Kendall Square Research (KSR1) multiprocessor system, with 64 processors, at Oak Ridge National Laboratory. The numerical results indicate that the parallel Cholesky (U{sup T}DU) matrix decomposition algorithm is attractive for NIKE3D under multi-processor system environments.
- Research Organization:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- DOE Contract Number:
- AC05-84OR21400
- OSTI ID:
- 102449
- Report Number(s):
- ORNL/TM-12733; ON: DE95017197
- Resource Relation:
- Other Information: PBD: Jun 1995
- Country of Publication:
- United States
- Language:
- English
Similar Records
Singular value decomposition utilizing parallel algorithms on graphical processors
A parallel domain decomposition finite element method for massively parallel computers