In recent years several implementations of molecular dynamics Ε½ . Ε½ . MD codes have been reported on multiple instruction multiple data MIMD machines. However, very few implementations of MD codes on single instruction Ε½ . multiple data SIMD machines have been reported. The difficulty in using pair
The solution of linear equations on a SIMD computer using a parallel iterative algorithm
β Scribed by S.J. Webb; J.J. McKeown; D.J. Hunt
- Publisher
- Elsevier Science
- Year
- 1982
- Tongue
- English
- Weight
- 392 KB
- Volume
- 26
- Category
- Article
- ISSN
- 0010-4655
No coin nor oath required. For personal study only.
β¦ Synopsis
Techniques for solving linear equations on a single instruction multiple data (SIMD) computer such as the ICL DAP have so far been confined to simple methods such as the Successive Overrelaxation and Alternating Direction Implicit algorithms. While these techniques are adequate for simple finite difference problems more difficult problems require more complex algorithms. Preconditioned conjugate gradient methods have solved difficult problems successfully on serial machines. This paper describes a preconditioning technique suitable for parallel machines and numerical results obtained from a series of problems of varying degrees of difficulty.
π SIMILAR VOLUMES
We propose a method for computing the regular singular formal solutions of a linear differential system in the neighbourhood of a singular point. This algorithm avoids the use of cyclic vectors and has been implemented β in the computer algebra system Maple.
Numerous schemes and techniques exist for the solution of the Navier-Stokes equations on a serial machine, but the number which can be implemented efficiently and which exploit the special architectures of vector and parallel computers is relatively few. The paper discusses and comments on the appli