Developing applications that scale well on massively parallel architectures is quite difficult, due to problems with synchronization and communication time as well as fault tolerance. This book reviews current algorithms and presents new mathematical versions that avoid such problems. It details the implementation and validates the proposed versions on real examples. The methods are built on top of asynchronous algorithms, which do not need synchronization and thus have low sensitivity to communication delay. Moreover, they have huge potential as fault tolerant algorithms.
Reihe
Sprache
Verlagsort
Zielgruppe
Für höhere Schule und Studium
Mathematicians, engineers, and computer scientists in high performance computing.
Illustrationen
50 s/w Abbildungen
50 Illustrations, black and white
Maße
Höhe: 235 mm
Breite: 156 mm
ISBN-13
978-1-4398-6941-3 (9781439869413)
Copyright in bibliographic data is held by Nielsen Book Services Limited or its licensors: all rights reserved.
Schweitzer Klassifikation
Autor*in
Ecole Centrale Paris, Chatenay Malabry, France
Introduction to Parallel Computing. Synchronous and Asynchronous Iterations. Iterative Methods for Linear Systems. Sub-Structuring Methods. Multi-Splitting Methods. Schwan Methods. Waveform Relaxation Methods. Fault Recovery and Fault tolerance. Implementation.
