Interconnection Networks and Mapping and Scheduling Parallel Computations

by Hsu, D. Frank; Rosenberg, Arnold L.

• ISBN13: 9780821802380
• ISBN10: 0821802380
• Format: Hardcover
• Copyright: 1995-06-01
• Publisher: Amer Mathematical Society

Summary

The interconnection network is one of the most basic components of a massively parallel computer system. Such systems consist of hundreds or thousands of processors interconnected to work cooperatively on computations. One of the central problems in parallel computing is the task of mapping a collection of processes onto the processors and routing network of a parallel machine. Once this mapping is done, it is critical to schedule computations within and communication among processors so that the necessary inputs for a process are available where and when the process is scheduled to be computed. This book contains the refereed proceedings of a DIMACS Workshop on Massively Parallel Computation, held in February 1994. The workshop brought together researchers from universities and laboratories, as well as practitioners involved in the design, implementation, and application of massively parallel systems. Focusing on interconnection networks of parallel architectures of today and of the near future, the book includes topics such as network topologies, network properties, message routing, network embeddings, network emulation, mappings, and efficient scheduling.

Table of Contents

Ranking algorithms for Hamiltonian paths in hypercubic networks

Dense bus networks of diameter $2$

On broadcasting schemes in restricted optical passive star systems

Restricted routing and wide diameter of the cycle prefix network

Permutation routing via Cayley graphs with an example for bus interconnection networks

Using helpful sets to improve graph bisections

Modification of consecutive-$d$ digraphs

Highly adaptive wormhole routing algorithms for $N$-dimensional torus

Conflict-free access to constant-perimeter rectangular subarrays

Makespan minimization of task graphs with random task running times

Scheduling of structured and unstructured computation

Routing in optical networks: The problem of contention

Communications in optically interconnected parallel computer systems

Fault-tolerant Kautz networks

Asynchronous packet routers

Cayley digraphs of finite cyclic groups with minimal average distance

Shuffled tree based fault-tolerant hierarchical interconnection networks

Restricted connectivity and restricted fault diameter of some interconnection networks

Sorting and selection on interconnection networks

Towards a simple construction method for Hamiltonian decomposition of the hypercube

Generalized reduced hypercube interconnection networks for massively parallel computers

Table of Contents provided by Publisher. All Rights Reserved.