ParaSLRF: A High Performance Rational Filter Method for Solving Large Scale Eigenvalue Problems

TL;DR

ParaSLRF introduces a parallel rational filter method for efficiently solving large-scale eigenvalue problems, leveraging iterative linear solvers and optimized load balancing for high parallel performance.

Contribution

It presents a novel parallel implementation of the SLRF method, improving load balance and efficiency by using iterative solvers and specific pole selection.

Findings

Achieves the best parallel efficiency among rational filter methods.

Demonstrates excellent load balance and scalability in numerical experiments.

Shows improved performance with eigenpair locking and good initial guesses.

Abstract

In \emph{Wang et al., A Shifted Laplace Rational Filter for Large-Scale Eigenvalue Problems}, the SLRF method was proposed to compute all eigenvalues of a symmetric definite generalized eigenvalue problem lying in an interval on the real positive axis. The current paper discusses a parallel implementation of this method, abbreviated as ParaSLRF. The parallelization consists of two levels: (1) on the highest level, the application of the rational filter to the various vectors is partitioned among groups of processors; (2) within each group, every linear system is solved in parallel. In ParaSLRF, the linear systems are solved by iterative methods instead of direct ones, in contrast to other rational filter methods, such as, PFEAST. Because of the specific selection of poles in ParaSLRF, the computational cost of solving the associated linear systems for each pole, is almost the same. This intrinsically leads to a better load balance between each group of resources, and reduces waiting times of processes. We show numerical experiments from finite element models of mechanical vibrations, and show a detailed parallel performance analysis. ParaSLRF shows the best parallel efficiency, compared to other rational filter methods based on quadrature rules for contour integration. To further improve performance, the converged eigenpairs are locked, and a good initial guess of iterative linear solver is proposed. These enhancements of ParaSLRF show good two-level strong scalability and excellent load balance in our experiments.