摘要:

Achieving efficiency in parallel sparse sub-matrix Cholesky factorization is known to be difficult. The relevance of the underlying architecture in obtaining good performance is demonstrated, by choosing the linear array. The linear array architecture is chosen to suit the data flow pattern inherent to sub-matrix Cholesky scheme. The linear array is synthesized on the reconfigurable transputer based PARAM (and the MEIKO CSN) machine. The data structure used is an array of linked lists. Results obtained indicate almost linear speed-up up to 64 processors though the tests were conducted for 128 processors This highlights the significance of the underlying architecture for an efficient parallel implementation.

ISSN:1063-7192    

DOI:10.1080/10637199808947367

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor

摘要:

Two triangular system solvers, one for the lower triangular system and the other for the upper triangular system, are developed and implemented on the linear array. Tests conducted with respect to these two solvers reveal that the performance of the backward solver is better than that of the forward solver. The matrix multiplication routine that is implemented on the linear array shows linear speed-up up to 64 processors.

ISSN:1063-7192    

DOI:10.1080/10637199808947368

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor

摘要:

In this article, we propose new difference methods of order two and four using three grid points in a coupled manner for solving the one dimensional nonlinear biharmonic problems with specified boundary conditions at the end points. The resulting matrix system is solved by the block iterative methods on a parallel computer. Derivatives of the solution are obtained as a by-product of the methods. Numerical examples are provided to demonstrate the efficiency and accuracy of the methods on both sequential and parallel computations.

ISSN:1063-7192    

DOI:10.1080/10637199808947369

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor

摘要:

The paper presents parallel algorithms for efficient solution of the Singular Value Decomposition (SVD) problem by the block two-sided Jacobi method. In this part of the work, we show how the method may be used on MIMD computers with hypercube and ring topologies. We analyse three types of orderings for solving SVD on block-structured submatrices from the point of view of communication requirements and suitability for parallel execution of the computational process The algorithms map well onto the hypercube topology. Two of the ordering schemes can also be directly implemented on rings. Results obtained on an Intel Paragon are shown and discussed for all the three types of orderings.

ISSN:1063-7192    

DOI:10.1080/10637199808947370

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor