Symmetric multiprocessing (SMP) is a computer architecture where multiple CPUs share a common connection to the same memory. It originated in the 1960s and has been used in various configurations. SMP treats all processors equally, allowing any processor to access and run software from any portion of shared memory. It has advantages over other techniques, but its popularity has fluctuated over the years. SMP can be combined with other technologies to create more powerful desktop computers.
Symmetric multiprocessing (SMP) is a type of computer architecture in which two or more central processing units (CPUs) share a common connection to the same memory. It was originally developed in the 1960s and has been used in various configurations ever since. Any processor in an SMP system can access and run software from any portion of shared memory. The popularity of this configuration has fluctuated over the year as technology has evolved and markets have changed, but it is still among the most common forms of multiprocessor technology.
SMP originated in the early 1960s as a way to connect multiple processors over a high-speed connection and allow them to access the same set of memory modules. Because memory is shared between processors, SMP hardware can be cheaper than other technologies that can dedicate memory to each processor. Many variations of this configuration have been used, some using a simple crossbar to connect two processors, while others employed more sophisticated interconnects between as many as 32 processors. Any symmetric multiprocessor system can be held back by the speed and capacity of this interconnect; a system with 32 processors will not necessarily be 32 times faster because the common link between these processors and system memory can become congested.
A key advantage that symmetric multiprocessing has over other techniques is that an SMP system treats all of its processors more or less equally, thus giving each the same quality of access to the other computer hardware. This means that any processor in the system can read and execute instructions from software programs regardless of where those programs reside in computer memory. Many software programs are now broken up into smaller chunks known as threads; when these programs are run on an SMP system, each processor can execute one thread of the program, further increasing overall performance. User-level software must not be modified to run on a system that supports symmetric multiprocessing, but the underlying operating system must support the technology.
The popularity of symmetric multiprocessing has waxed and waned over the years as other techniques have been developed and new architectures have been explored. Publicity about the possible impact of technology on computing emerged in the early 1990s; a number of companies, most notably Sequent Computer Systems, began to specialize in building high-end SMP systems. Sequent, which was acquired by IBM in 1999, has been praised for its designs, but has never been able to compete effectively with the giants of the computer industry. New multiprocessing techniques such as non-uniform memory access (NUMA) have partially supplanted SMP in high-end systems.
Computer manufacturers have experimented with symmetric multiprocessing in consumer-grade hardware over the years; outside of expensive enthusiast hardware, however, most personal computers lack the technology. New techniques for making single-CPU systems more efficient, such as simultaneous multithreading or “hyperthreading,” coupled with the rise of multicore technology have increased computer performance without the added cost of SMP. However, these technologies can be combined, and more powerful desktop computers can include multiple multicore processors connected via SMP, thus creating a system with massive amounts of computing power.
Protect your devices with Threat Protection by NordVPN