Multis: a new class of multiprocessor computers.

نویسنده

  • C G Bell
چکیده

Multis are a new class of computers based on multiple microprocessors. The small size, low cost, and high performance of microprocessors allow the design and construction of computer structures that offer significant advantages in manufacture, price-performance ratio, and reliability over traditional computer families. Currently, commercial multis consist of 4 to 28 modules, which include microprocessors, common memories, and input-output devices, all of which communicate through a single set of wires called a bus. Adding microprocessors together increases the performance of multis in direct proportion to their price and allows multis to offer a performance range that spans that of small minicomputers to mainframe computers. Multis are commercially available for applications ranging from real-time industrial control to transaction processing. Traditional batch, time-sharing, and transaction systems process a number of independent jobs that can be distributed among the microprocessors of a multi with a resulting increased throughput (number of jobs completed per unit of time). Many scientific applications (such as the solving of partial differential equations) and engineering applications (such as the checking of integrated circuit designs) are speeded up by this parallel computation; thus, multis produce results at supercomputer speed but at a fraction of the cost. Multis are likely to be the basis for the next, the fifth, generation of computers-a generation based on parallel processing.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

The Encore Continuum: a complete distributed work station-multiprocessor computing environment

The Encore Continuum is a UNIX-compatible computing environment designed to provide a range of computing styles from distributed work stations to host multis. The multi, meaning multiple microprocessor, is a new computer class that spans an order of magnitude performance range covering large micros to small mainframes. The multis’ parallelism can be exploited for transparent timesharing, transa...

متن کامل

Performance Analysis of a New Neural Network for Routing in Mesh Interconnection Networks

Routing is one of the basic parts of a message passing multiprocessor system. The routing procedure has a great impact on the efficiency of a system. Neural algorithms that are currently in use for computer networks require a large number of neurons. If a specific topology of a multiprocessor network is considered, the number of neurons can be reduced. In this paper a new recurrent neural ne...

متن کامل

Load Balancing for Multiprocessor: a Novel Architecture

One of the most important issues is how to effectively utilized parallel computers that has become increasingly complex to improve the performance. Such systems are constructed by different processor connected with communication link to operate in parallel with relatively low cost known as multi processor system.The parallel computer is one of the remarkable developments of methodology and tech...

متن کامل

A comparison of multiprocessor task scheduling algorithms with communication costs

Both parallel and distributed network environment systems play a vital role in the improvement of high performance computing. Of primary concern when analyzing these systems is multiprocessor task scheduling. Therefore, this paper addresses the challenge of multiprocessor task scheduling parallel programs, represented as directed acyclic task graph (DAG), for execution onmultiprocessors with co...

متن کامل

Scheduling of a flexible flow shop with multiprocessor task by a hybrid approach based on genetic and imperialist competitive algorithms

This paper presents a new mathematical model for a hybrid flow shop scheduling problem with multiprocessor tasks in which sequence dependent set up times and preemption are considered. The objective is to minimize the weighted sum of makespan and maximum tardiness. Three meta-heuristic methods based on genetic algorithm (GA), imperialist competitive algorithm (ICA) and a hybrid approach of GA a...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • Science

دوره 228 4698  شماره 

صفحات  -

تاریخ انتشار 1985