In this paper, we present the StarNEig library for solving dense nonsymmetric standard and generalized eigenvalue problems. The library is built on top of the StarPU runtime system and targets both shared and distributed memory machines. Some components of the library have support for GPU acceleration. The library is currently in an early beta state and supports only real matrices. Support for complex matrices is planned for a future release. This paper is aimed at potential users of the library. We describe the design choices and capabilities of the library, and contrast them to existing software such as ScaLAPACK. StarNEig implements a ScaLAPACK compatibility layer which should assist new users in the transition to StarNEig. We demonstrate the performance of the library with a sample of computational experiments.
@article{arxiv.2002.05024,
title = {Task-based, GPU-accelerated and Robust Library for Solving Dense Nonsymmetric Eigenvalue Problems},
author = {Mirko Myllykoski and Carl Christian Kjelgaard Mikkelsen},
journal= {arXiv preprint arXiv:2002.05024},
year = {2020}
}
Comments
18 pages, 11 figures (18 when counting sub-figures), 1 tex-files. Invited article submitted to Concurrency and Computation: Practice and Experience. Second author's first name is "Carl Christian" and last name "Kjelgaard Mikkelsen"