We first briefly report on the status and recent achievements of the ELPA-AEO (Eigenvalue Solvers for Petaflop Applications - Algorithmic Extensions and Optimizations) and ESSEX II (Equipping Sparse Solvers for Exascale) projects. In both collaboratory efforts, scientists from the application areas, mathematicians, and computer scientists work together to develop and make available efficient highly parallel methods for the solution of eigenvalue problems. Then we focus on a topic addressed in both projects, the use of mixed precision computations to enhance efficiency. We give a more detailed description of our approaches for benefiting from either lower or higher precision in three selected contexts and of the results thus obtained.
@article{arxiv.1806.01036,
title = {Benefits from using mixed precision computations in the ELPA-AEO and ESSEX-II eigensolver projects},
author = {Andreas Alvermann and Achim Basermann and Hans-Joachim Bungartz and Christian Carbogno and Dominik Ernst and Holger Fehske and Yasunori Futamura and Martin Galgon and Georg Hager and Sarah Huber and Thomas Huckle and Akihiro Ida and Akira Imakura and Masatoshi Kawai and Simone Köcher and Moritz Kreutzer and Pavel Kus and Bruno Lang and Hermann Lederer and Valeriy Manin and Andreas Marek and Kengo Nakajima and Lydia Nemec and Karsten Reuter and Michael Rippl and Melven Röhrig-Zöllner and Tetsuya Sakurai and Matthias Scheffler and Christoph Scheurer and Faisal Shahzad and Danilo Simoes Brambila and Jonas Thies and Gerhard Wellein},
journal= {arXiv preprint arXiv:1806.01036},
year = {2018}
}