Главная страница Случайная страница КАТЕГОРИИ: АвтомобилиАстрономияБиологияГеографияДом и садДругие языкиДругоеИнформатикаИсторияКультураЛитератураЛогикаМатематикаМедицинаМеталлургияМеханикаОбразованиеОхрана трудаПедагогикаПолитикаПравоПсихологияРелигияРиторикаСоциологияСпортСтроительствоТехнологияТуризмФизикаФилософияФинансыХимияЧерчениеЭкологияЭкономикаЭлектроника |
Non-von Neumann Architectures
The linear fetch-execute cycle of the von Neumann architecture still dominates the technology today. However, since 1990, alternative parallel-processing systems have entered the marketplace. They have the potential to process much more data at much higher speeds. One approach to parallelism is to have multiple processors apply the same program to multiple data sets. In this approach, processors often execute the same instructions at the same time, i.e., a common program is run at each processor. This approach is called synchronous processing and is effective when the same process needs to be applied to many data sets. This approach is similar to that of the NASA backup system in which three computers do the same thing as a security measure. However, here there are multiple processors applying the same process to different data sets in parallel. Another configuration arranges processors in tandem, where each processor contributes one part to an overall computation. This approach is called pipelining, and is reminiscent of an assembly line. When this organization is applied to data, the first processor does the first task. Then the second processor starts working on the output from the first processor, while the first processor applies its computation to the next data set. Eventually, each processor is working on one phase of the job, each getting material or data from the previous stage of processing, and each in turn handing over its work to the next stage. The third approach is to have different processors doing different things with different data. This configuration allows processors to work independently much of the time, but introduces the problems of coordination among the processors. This leads to a configuration where the processors each have local memory and a shared memory. The processors use the shared memory for communication, and the configuration is thus called a shared memory configuration.
Notes: Per track - на трек, на каждую дорожку Drive partition - разбиение жесткого диска на логические разделы NASA (National Aeronautics and Space Administration) backup system - In the early days of manned space flights, NASA used a backup system composed of three mainframe computers, each of which calculated exactly the same thing. If one computer failed, there were still two computers carrying out the necessary calculations. If two computers failed, there was still one computer left to do the necessary processing. If three computers failed - fortunately, that never happened. PDA (Personal Digital Computer) - карманный персональный компьютер (КПК)
|