Computational models and task scheduling for parallel sparse Cholesky factorization. Final report, 1 October 1986-30 September 1987
In this paper, a systematic and unified treatment of computational task models for parallel sparse Cholesky factorization is presented. They are classified as fine-, medium-, and large-gained graph models. In particular, a new medium-grained model based on column-oriented tasks is introduced, and it is shown to correspond structurally to the filled graph of the given sparse matrix. The task-scheduling problem for the various task graphs is also discussed. A practical algorithm to schedule the column tasks of the medium-grained model for multiple processors is described. It is based on a heuristic critical path scheduling method. This will give an overall scheme for parallel sparse Cholesky factorization, appropriate for parallel machines with shared-memory architecture like the Denelcor HEP.
- Research Organization:
- Oak Ridge National Lab., TN (USA)
- OSTI ID:
- 5384897
- Report Number(s):
- AD-A-187038/5/XAB
- Resource Relation:
- Other Information: Pub. in Parallel Computing, Vol. 3, No. 4, 327-342(Oct 1986)
- Country of Publication:
- United States
- Language:
- English
Similar Records
Parallel Cholesky factorization on a multiprocessor
Efficient parallel sparse Cholesky factorization
Related Subjects
COMPUTER ARCHITECTURE
COMPUTER GRAPHICS
PARALLEL PROCESSING
TASK SCHEDULING
ALGORITHMS
ARRAY PROCESSORS
GRAPHS
MATHEMATICAL MODELS
PROGRESS REPORT
DATA PROCESSING
DOCUMENT TYPES
MATHEMATICAL LOGIC
PROCESSING
PROGRAMMING
990210* - Supercomputers- (1987-1989)