Editing Real-time computing (section)

== History ==
The term ''real-time'' derives from its use in early [[simulation]], where a real-world process is simulated at a rate which matched that of the real process (now called [[real-time simulation]] to avoid ambiguity). [[Analog computer]]s, most often, were capable of simulating at a much faster pace than real-time, a situation that could be just as dangerous as a slow simulation if it were not also recognized and accounted for. <!-- What does this mean? Where did "dangerous" become an issue? --><!-- The historical origins of the term has no bearing on its current, correct, technical definition. ''Real-time'' does not refer to either fast or slow processing. In fact, the speed of processing is independent of whether it is considered ''real-time'' or not. For a system to be defined as ''real-time'' it must meet its time constraints — whether those constraints require extremely fast processing or can be met at a more leisurely pace has no bearing on the matter. -->

Minicomputers, particularly in the 1970s onwards, when built into dedicated [[embedded system]]s such as DOG ([[Digital on-screen graphic]]) scanners, increased the need for low-latency priority-driven responses to important interactions with incoming data. Operating systems such as [[Data General]]'s [[Data General RDOS|RDOS (Real-Time Disk Operating System)]] and RTOS with [[Foreground-background|background and foreground scheduling]] as well as [[Digital Equipment Corporation]]'s [[RT-11]] date from this era. Background-foreground scheduling allowed low priority tasks CPU time when no foreground task needed to execute, and gave absolute priority within the foreground to threads/tasks with the highest priority. Real-time operating systems would also be used for [[time-sharing]] multiuser duties. For example, [[Data General Business Basic]] could run in the foreground or background of RDOS and would introduce additional elements to the scheduling algorithm to make it more appropriate for people interacting via [[dumb terminal]]s.

Early personal computers were sometimes used for real-time computing. The possibility of deactivating other interrupts allowed for hard-coded loops with defined timing, and the low [[interrupt latency]] allowed the implementation of a real-time operating system, giving the user interface and the disk drives lower priority than the real-time thread. Compared to these the [[programmable interrupt controller]] of the Intel CPUs (8086..80586) generates a very large latency and the Windows operating system is neither a real-time operating system nor does it allow a program to take over the CPU completely and use its own [[Scheduling (computing)|scheduler]], without using native machine language and thus bypassing all interrupting Windows code. However, several coding libraries exist which offer real time capabilities in a high level language on a variety of operating systems, for example [[Real time Java|Java Real Time]]. Later microprocessors such as the [[Motorola 68000]] and subsequent family members (68010, 68020, [[NXP ColdFire|ColdFire]] etc.) also became popular with manufacturers of industrial control systems. This application area is one where real-time control offers genuine advantages in terms of process performance and safety.{{citation needed|date=September 2013|reason=This whole paragraph contains several questionable statements in regard to MOS, AMD and Motorola CPUs and their interrupt handling, and therefore needs to be rewritten and sourced by reliable sources.}}