|This article does not cite any references or sources. (December 2009)|
As of late 2011, computer microprocessors run at very high speeds, while memory technology does not seem to be able to catch up: typical PC processors like the Intel Core 2 and the AMD Athlon 64 X2 run with a clock of several GHz, which means that one clock cycle is less than 1 nanosecond (typically about 0.3 ns to 0.5 ns on modern desktop CPUs), while main memory has a latency of about 15–30 ns. Some second-level CPU caches run slower than the processor core.
When the processor needs to access external memory, it starts placing the address of the requested information on the address bus. It then must wait for the answer, that may come back tens if not hundreds of cycles later. Each of the cycles spent waiting is called a wait state.
Wait states are a pure waste for a processor's performance. Modern designs try to eliminate or hide them using a variety of techniques: CPU caches, instruction pipelines, instruction prefetch, branch prediction, simultaneous multithreading and others. No single technique is 100% successful, but together they can significantly reduce the problem.
Wait states can be used to reduce the energy consumption of a processor, by allowing the main processor clock to either slow down or temporarily pause during the wait state if the CPU has no other work to do. Rather than spinning uselessly in a tight loop waiting for data, sporadically reducing the clock speed in this manner helps to keep the processor core cool and to extend battery life in portable computing devices.