Parallel Scientific Computing and Optimization

Advances and Applications

274 Seiten, Hardcover

Kurzbeschreibung des Verlags

The book is divided into four parts: Parallel Algorithms for Matrix Computations, Parallel Optimization, Management of Parallel Programming Models and Data, and Parallel Scienti?c Computing in Industrial Applications. The ?rst part of the book includes chapters on parallel matrix computations. The chapter by R. Granat, I. Jonsson, and B. Kagstr ? om, ¿ "RECSY and SCASY Library Software: Recursive Blocked and Parallel Algorithms for Sylvester-type Matrix Equations with Some Applications", gives an overview of state-of-the-art high-performance computing (HPC) algorithms and software for solving various standard and generalized Sylvester-type matrix equations. Computer-aided control system design (CACSD) is a great source of applications for matrix equations - cluding different eigenvalue and subspace problems and for condition estimation. The parallelization is invoked at two levels: globally in a distributed memory paradigm, and locally on shared memory or multicore nodes as part of the d- tributed memory environment. ? In the chapter by A. Jakuse ? v, R. Ciegis, I. Laukaityte, ? and V. Tro?mov, "P- allelization of Linear Algebra Algorithms Using ParSol Library of Mathematical Objects", the mathematical objects library ParSol is described and evaluated. It is applied to implement the ?nite difference scheme to solve numerically a s- tem of PDEs describing a nonlinear interaction of two counter-propagating laser waves.

• Themen: Informatik und Informationstechnologie Informatik Künstliche Intelligenz (KI)
• ISBN: 9780387097060
• Sprache: Englisch
• Erscheinungsdatum: 21.11.2008
• Größe: 244 x 165 mm
• Verlag: Springer New York
• Herausgegeben von: David Henty, Bo Kågström, Julius Zilinskas, Raimondas Ciegis