IWCC 2001: Advanced Environments, Tools, and Applications for Cluster Computing pp 156-165 | Cite as
The Parallel Algorithm of Conjugate Gradient Method
Abstract
In this paper authors investigate parallel implementation of a conjugate gradient algorithm used for solving a large system of linear algebraic equations. Computations were carried out using a heterogeneous cluster of PCs, working under control of Windows 2000 operating system and an MPI library, as well as a massive parallel processor machine Hitachi SR-2201. The authors implemented two versions of the algorithm in cluster computations: an algorithm with equally distributed data among all processors, and another one with distribution depending on the speed of each PC processor. Speedup in all implementations was investigated and the conclusions were drawn.
Preview
Unable to display preview. Download preview PDF.
References
- 1.A. Chtchelkanova, C. Edwards, J. Gunnels, G. Morrow, J. Overleft, R. van de Geijn: Towards Usable and Lean Parallel Linear Algebra Libraries. CS-TR-96-09, 1996.Google Scholar
- 2.A. Gupta, V. Kumar, A. Sameh: Performance and Scalability of Preconditioned Conjugate Gradient Methods on Parallel Computers. IEEE Transactions on Parallel and Distributed Systems, vol. 6, no. 5, pp. 455–469, 1995.CrossRefGoogle Scholar
- 3.Jianming Jin: The Finite Element Method in Electromagnetics. John Wiley, New York, 1993.MATHGoogle Scholar
- 4.A. Jordan: Theoretical Background of Parallel Electromagnetic Field Computations. The 10th International Symposium on Applied Electromagnetics and Mechanics, pp. 193–194, May 13–16, 2000, Tokyo, Japan.Google Scholar
- 5.P. S. Pacheco: A User’s Guide to MPI. USFCA, 1998.Google Scholar
- 6.W. Peterson: Fixed point technique in computing eddy currents within ferromagnetic conductors exposed to transverse magnetic field. Archives of electrical engineering, Vol. XLVII, no. 1, pp. 57–68, 1998.Google Scholar