Symmetrical Multiprocessing Architecture: Clusters and grids are increasingly prevalent solutions to large-scale computing challenges. Understanding how these multiprocessing 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, principal analyst, Pacific Data Works LLC. Intel Corp.

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.

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.

Multiprocessor systems: multiple processors in a single system
Multiple processors were once the exclusive domain of mainframes and high-end servers. Today, they are common in all kinds of systems, including high-end PCs and workstations. The most common architecture used in these devices is Symmetrical Multiprocessing. The term symmetrical is both important and misleading. Multiple processors are, by definition, symmetrical if any of them can execute any given function.