Scheduling Divisible Loads in Parallel and Distributed Systems

This book provides an in-depth study concerning a claqss of
problems in the general area of load sharing and balancing in
parallel and distributed systems. The authors present the design
and analysis of load distribution strategies for arbitrarily
divisible loads in multiprocessor/multicomputer systems subjects to
the system constraints in the form of communication delays. In
particular, two system architecture-single-level tree or star
network, and linear network-are thoroughly analyzed.

The text studies two different cases, one of processors with
front-ends and the other without. It concentrates on load
distribution strategies and performance analysis, and does not
cover issues related to implementation of these strategies on a
specific system. The book collates research results developed
mainly by two groups at the Indian Institute of Science and the
State University of New York at Stony Brook. It also covers results
by other researchers that have either appeared or are due to appear
in computer science literature. The book also provides relevant but
easily understandable numerical examples and figures to illustrate
important concepts. It is the first book in this area and is
intended to spur further research enabling these ideas to be
applied to a more general class of loads. The new methodology
introduced here allows a close examination of issues involving the
integration of communication and computation. In fact, what is
presented is a new "calculus" for load sharing problems.