Parallel Computing

V.V. Voevodin (Autor)

Media-Kombination

500 Seiten

2005
Charles River Media
978-1-58450-439-9 (ISBN)

Infos

Parallel implementation of algorithms involves many difficult problems. These problems include round-off analysis, the way to convert sequential programs and algorithms into parallel mode, the choice of appropriate or optimal computer architecture, and so on. To solve the stumbling blocks of these problems it is necessary to know the structure of algorithms. Parallel Computing is a must-have textbook that teaches computer science students how to approach parallel computing from a mathematical perspective. It covers in detail the mathematical mechanism that permits students to investigate structures of both sequential and parallel algorithms. This mechanism allows readers to recognize and explain the relations between different methods of constructing parallel algorithms, analyzing round-off errors, optimizing memory traffic, working out the fastest implementation for a given parallel computer, and other methods attending the joint investigation of algorithms and computers.

Autor

V.V. Voevodin has published 110 scientific works. His scientific interests include theoretical and applied aspects of linear algebra, computing methods and features of their realization on the computer, studying of behavior of mistakes of a rounding off in computing processes, methods of construction of the numerical software, transferable(tolerable) on computing systems of various architecture. He currently is the main scientific employee of the Institute of Calculus Mathematics of the Russian Academy of Science.

Inhalt

Chapter 1: Algorithm and Its Graph - General Notion of Algorithm, Algorithm Notations, Graph of Algorithm, Topological Sorting, Schedules and Graph Machine, Examples; Chapter 2: Algorithm Execution Time - Vector Properties of Schedules, Number Semirings and Other Sets, Minimax Properties of Schedules, Optimal and High-Speed Schedules, Examples; Chapter 3: Algorithms and Computer Memory - Examples, Total Required Memory Size, Hierarchical Memory, Sectioning of Memory, Decomposition of Algorithm and of Its Graph; Chapter 4: Matrix Investigation of Algorithm Structure - Graphs and Matrices, Recovering the Linear Functional, Computing Gradient and Derivative, Roundoff Error Analysis, Examples: Chapter 5: Functional Investigation of Algorithm Structure - Space-Time Schedules, Regular Graphs, Passage to the Limit, Data Streams, Examples; Chapter 6: Algorithm Graph and Schedules Building - Some Statistics, Order Relation, Notation Particularities, Guidelines for Algorithm Graph Building, Splitting the Algorithm Graph, Linear Index Expressions, Branching, Linear Information Closure, Examples; Index.

Produkt-Details

• Erscheint lt. Verlag: 1.9.2005
• Verlagsort: Hingham
• Sprache: englisch
• Maße: 186 x 235 mm
• Themenwelt: Mathematik / Informatik ► Informatik ► Theorie / Studium
• ISBN-10: 1-58450-439-0 / 1584504390
• ISBN-13: 978-1-58450-439-9 / 9781584504399
• Zustand: Neuware