Direct and Iterative Matrix Solvers in Parallel Computing
碩士 === 國立中正大學 === 應用數學研究所 === 90 === The purpose of this work is to study the performance of direct and iterative solvers using parallel computers. Using the existing PCs, an affordable heterogeneous PC cluster using MPI programs will be used in our numerical computations. The numerical e...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2002
|
Online Access: | http://ndltd.ncl.edu.tw/handle/84361817752804935458 |
Summary: | 碩士 === 國立中正大學 === 應用數學研究所 === 90 === The purpose of this work is to study the performance of direct and iterative solvers using parallel computers. Using the existing PCs, an affordable heterogeneous PC cluster using MPI programs will be used in our numerical computations. The numerical experiments are performed only on Jacobi method and tridiagonal LU decomposition. The linear speedup and efficiency of the PC cluster for these numerical methods will be demonstrated.
|
---|