Lighthouse: A taxonomy-based solver selection tool

Abstract

Linear algebra provides the building blocks for a wide variety of scientific and engineering simulation codes. Users face a world of continuously developing new algorithms and high-performance implementations of these fundamental calculations. In this paper, we describe new capabilities of our Lighthouse framework, whose goal is to match specific problems in the area of high-performance numerical computing with the best available solutions developed by experts. Lighthouse provides a searchable taxonomy of popular but difficult to use numerical software for dense and sparse linear algebra. Because multiple algorithms and implementations of the same mathematical operations are available, Lighthouse also classifies algorithms based on their performance. We introduce the design of Lighthouse and show some examples of the taxonomy interfaces and algorithm classification results for the preconditioned iterative linear solvers in the Parallel Extensible Toolkit for Scientific Computation (PETSc).