Abstract
We investigate the parallel performance of an iterative solver for 3D heterogeneous Helmholtz problems related to applications in seismic wave propagation. For large 3D problems, the computation is no longer feasible on a single processor, and the memory requirements increase rapidly. Therefore, parallelization of the solver is needed. We employ a complex shifted-Laplace preconditioner combined with the Bi-CGSTAB iterative method and use a multigrid method to approximate the inverse of the resulting preconditioning operator. A 3D multigrid method with 2D semi-coarsening is employed. We show numerical results for large problems arising in geophysical applications.
Original language | English |
---|---|
Pages (from-to) | 431-448 |
Number of pages | 18 |
Journal | Journal of Computational Physics |
Volume | 224 |
Issue number | 1 |
DOIs | |
Publication status | Published - 20 May 2007 |
Keywords
- Helmholtz equation
- Krylov subspace method
- Multigrid method
- Preconditioner