Parallel Computing on Distributed Memory Multiprocessors, 1993
NATO ASI Subseries F: Series, Vol. 103

Advances in microelectronic technology have made massively parallel computing a reality and triggered an outburst of research activity in parallel processing architectures and algorithms. Distributed memory multiprocessors - parallel computers that consist of microprocessors connected in a regular topology - are increasingly being used to solve large problems in many application areas. In order to use these computers for a specific application, existing algorithms need to be restructured for the architecture and new algorithms developed. The performance of a computation on a distributed memory multiprocessor is affected by the node and communication architecture, the interconnection network topology, the I/O subsystem, and the parallel algorithm and communication protocols. Each of these parametersis a complex problem, and solutions require an understanding of the interactions among them. This book is based on the papers presented at the NATO Advanced Study Institute held at Bilkent University, Turkey, in July 1991. The book is organized in five parts: Parallel computing structures and communication, Parallel numerical algorithms, Parallel programming, Fault tolerance, and Applications and algorithms.

I. Parallel Computing Structures and Communication.- Mechanisms for Parallel Computers.- Reconfigurable Mesh Algorithms For Fundamental Data Manipulation Operations.- Spanning Trees and Communication Primitives on Hypercubes.- The Effect of Configurations and Algorithms on Performance.- Dedicated and General-Purpose Systems for Parallel Application Development.- II. Parallel Numerical Algorithms.- Parallel Direct Solution of Sparse Linear Systems.- The Performance of Linear Algebra Algorithms on Intel Parallel Supercomputers.- Sparse LU-Decomposition for Chemical Process Flowsheeting on a Multicomputer.- III. Parallel Programming.- Distributed Control Algorithms (Selected Topics).- A Data-Driven Environment For A Multiprocessor System.- Critical Path Length of Large Acyclic Task Graphs.- Logic Program Execution on Distributed Memory Parallel Computers.- IV. Fault Tolerance.- Tools and Techniques for Adding Fault Tolerance to Distributed and Parallel Programs.- Fault Tolerance in Hypercubes.- V. Applications, Algorithms.- Parallel Relational Database Algorithms.- High Quality Image Synthesis on Distributed Memory Multiprocessors.- Parallel Implementation of the Backpropagation Algorithm on Hypercube Systems.- Random Number Generation for Parallel Computers.- List of Participants.