Parallel Algorithms for Regular Architectures: Meshes and Pyramids (Scientific Computation)

Parallel-Algorithms for Regular Architectures is the first book to concentrate exclusively on algorithms and paradigms for programming parallel computers such as the hypercube, mesh, pyramid, and mesh-of-trees. Algorithms are given to solve fundamental tasks such as sorting and matrix operations, as well as problems in the field of image processing, graph theory, and computational geometry. The first chapter defines the computer models, problems to be solved, and notation that will be used throughout the book. It also describes fundamental abstract data movement operations that serve as the foundation to many of the algorithms presented in the book. The remaining chapters describe efficient implementations of these operations for specific models of computation and present algorithms (with asymptotic analyses) that are often based on these operations.

The algorithms presented are the most efficient known, including a number of new algorithms for the hypercube and mesh-of-trees that are better than those that have previously appeared in the literature. The chapters may be read independently, allowing anyone interested in a specific model to read the introduction and then move directly to the chapter(s) devoted to the particular model of interest.

Russ Miller is Assistant Professor in the Department of Computer Science, State University of New York at Buffalo. Quentin F. Stout is Associate Professor in the Department of Electrical Engineering and Computer Science at the University of Michigan. Parallel Algorithms for Regular Architectures is included in the Scientific Computation series, edited by Dennis Gannon.