Anzeige
Erschienen in:
2017 | OriginalPaper | Buchkapitel
Parallel Numerical Methods Course for Future Scientists and Engineers
verfasst von : Iosif Meyerov, Sergey Bastrakov, Konstantin Barkalov, Alexander Sysoyev, Victor Gergel
Erschienen in: Supercomputing
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
The rise of computational science has facilitated rapid progress in many areas of science and technology over the last decade. There is a growing demand in computational scientists and engineers capable of efficient collaboration in interdisciplinary groups. Training such specialists includes courses on numerical analysis and parallel computing. In this paper we present a new Master’s course Parallel Numerical Methods which bridges the gap between theoretical aspects of numerical methods and issues of implementation for modern multicore and manycore systems. The course aims to guide students through the complete process of solving computational problems, from a problem statement to developing parallel software and analyzing results of computational experiments. An important feature is that many of practical classes are based on research done at the HPC Center of the University of Nizhni Novgorod and therefore illustrate issues, which students may encounter in their research and future career.