Experimental study of methods for parallel preconditioned Krylov methods. Research report
Technical Report
·
OSTI ID:6566518
High-performance multiprocessor architectures differ both in the number of processors, and in the delay costs for synchronization and communication. In order to obtain good performance on a given architecture for a given problem, adequate parallelization, good balance of load and an appropriate choice of granularity are essential. This document discusses the implementation of parallel version of PCGPAK for both shared-memory architectures and hypercubes. The authors' parallel implementation is sufficiently efficient to allow them to complete the solution of the test problems on 16 processors of the Encore Multimax/320 in an amount of time that is a small multiple of that required by a single head of a Cray X/MP, despite the fact that the peak performance of the Multimax processors is not even close to that of the supercomputer range. The authors illustrate the effectiveness of the approach on a number of model problems from reservoir engineering and mathematics.
- Research Organization:
- Yale Univ., New Haven, CT (USA). Dept. of Computer Science
- OSTI ID:
- 6566518
- Report Number(s):
- AD-A-198697/5/XAB; YALEU/DCS/RR-629
- Country of Publication:
- United States
- Language:
- English
Similar Records
The Lanczos algorithm for the generalized symmetric eigenproblem on shared-memory architectures
Practical parallel union-find algorithms for transitive closure and clustering
APRIL: A processor architecture for multiprocessing. Technical report
Conference
·
Sat Sep 01 00:00:00 EDT 1990
·
OSTI ID:5748587
Practical parallel union-find algorithms for transitive closure and clustering
Journal Article
·
Sat Oct 01 00:00:00 EDT 1988
· International Journal of Parallel Programming; (USA)
·
OSTI ID:6193129
APRIL: A processor architecture for multiprocessing. Technical report
Technical Report
·
Sat Jun 01 00:00:00 EDT 1991
·
OSTI ID:5217066