Clusters and grids are increasingly prevalent solutions to large-scale computing challenges. Understanding how these architectures work – and which processors support them best – is the first step in identifying the many ways they can add raw processing muscle to your infrastructure
By Andrew Binstock
Computer systems using multiple processors have existed for decades in various forms, the most common of which have been multiprocessing servers and mainframes. The advent of inexpensive, high-performance processors has provided impetus to the development of multiprocessor designs. These have made their way into all corners of IT sites because of their relatively low price points. These designs fall into two main categories: those that are confined to a single integrated computer system, and those composed of multiple, distinct computers that are tied together. This article examines both types.
