To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
An Efficient Sparse Matrix-Vector Multiplication on Distributed Memory Parallel Computers |
|
Author |
Rukhsana Shahnaz, Anila Usman |
| Citation |
Vol. 7 No. 1 pp. 77-82 |
|
Abstract |
The matrix-vector product is one of the most important computational components of Krylov methods. This kernel is an irregular problem, which has led to the development of several compressed storage formats. We design a data structure for distributed matrix to compute the matrix-vector product efficiently on distributed memory parallel computers using MPI. We conduct numerical experiments on several different sparse matrices and show the parallel performance of our sparse matrix-vector product routines. |
|
Keywords |
Sparse matrices, matrix-vector product, sparse storage formats, distributed computing |
|
URL |
