The applicability of the Chebyshev time propagation algorithm for the solution of the time-dependent Schrodinger equation is investigated within the context of differencing schemes for the representation of the spatial operators. Representative numerical tests for the harmonic oscillator and Morse p
Parallelized implicit propagators for the finite-difference Schrödinger equation
✍ Scribed by Jonathan Parker; K.T. Taylor
- Publisher
- Elsevier Science
- Year
- 1995
- Tongue
- English
- Weight
- 1016 KB
- Volume
- 88
- Category
- Article
- ISSN
- 0010-4655
No coin nor oath required. For personal study only.
✦ Synopsis
We describe the application of block Gauss-Seidel and block Jacobi iterative methods to the design of implicit propagators for finite-difference models of the time-dependent Schrrdinger equation. The block-wise iterative methods discussed here are mixed direct-iterative methods for solving simultaneous equations, in the sense that direct methods (e.g. LU decomposition) are used to invert certain block sub-matrices, and iterative methods are used to complete the solution. We describe parallel variants of the basic algorithm that are well suited to the medium-to coarse-grained parallelism of work-station clusters, and MIMD supercomputers, and we show that under a wide range of conditions, fine-grained parallelism of the computation can be achieved. Numerical tests are conducted on a typical one-electron atom Hamiltonian. The methods converge robustly to machine precision ( 15 significant figures), in some cases in as few as 6 or 7 iterations. The rate of convergence is nearly independent of the finite-difference grid-point separations.
📜 SIMILAR VOLUMES
We present several new finite-difference schemes that can be used to numerically integrate the time-dependent Schrodinger equation. These schemes are explicit and use an Euler-type expression for the discrete time derivative. However, the second-order space derivative is modeled by a novel form not
explicit and local. Its novel features include the exact evaluation of a major contribution to an approximation to the The matrix elements of the exponential of a finite difference realization of the one-dimensional Laplacian are found exactly. This evolution operator (Eq. ( )) and a first-order ap