High Performance Cluster Computing: Architectures and Systems, Vol. 1
Books / Paperback
Books › Computers › Distributed Systems › General
ISBN: 0130137847 / Publisher: Pearson College Div, May 1999
As the editor explains, cluster computing was developed by IBM in the 1960s as a way of linking larg...
Read More
As the editor explains, cluster computing was developed by IBM in the 1960s as a way of linking large mainframes to provide commercial parallel capability cost-effectively. Contributions from some 100 experts provide a state-of-the-art overview of theory and practice in network and processor performance transforming clustered commodity workstations into the supercomputing solution of choice. The 36 chapters are organized into sections on: requirements and general issues; networking, protocols, and I/O; process scheduling, load sharing, and balancing; and representative cluster systems (e.g. Beowulf and SP/2). Annotation c. Book News, Inc., Portland, OR (booknews.com)
Read Less