A survey of parallel computer architectures

  title={A survey of parallel computer architectures},
  author={Ralph Duncan},
  • R. Duncan
  • Published 1990
  • Computer Science
  • Computer
An attempt is made to place recent architectural innovations in the broader context of parallel architecture development by surveying the fundamentals of both newer and more established parallel computer architectures and by placing these architectural alternatives in a coherent framework. The primary emphasis is on architectural constructs rather than specific parallel machines. Three categories of architecture are defined and discussed: synchronous architectures, comprising vector, SIMD… 

Reduction of Complexity and Automation of Parallel Execution through Loop Level Parallelism

  • Robert A. TefftR. Lee
  • Computer Science
    Seventh International Conference on Quality Software (QSIC 2007)
  • 2007
This paper proposes a language structure that applies the SIMD concept to the Java virtual machine to reduce the complexity of the code and ease implementation of parallelization by running a single set of instructions concurrently on an entire collection of objects.

MasPar MP-1: An SIMD Array Processor

The architecture of MasPar MP-1, a massively parallel processor, belongs to the category of SIMD array processors, which handles same instruction but operate on different data sets.

Dataflow development of medium-grained parallel software

This thesis examines the possibilities which the dataflow paradigm has to offer as the basis for a set of visual parallel programming tools, and presents a dataflow notation designed as a framework for medium-grained parallel programming.

A scalable tuple space model for structured parallel programming

The paper proposes and analyses a scalable model of an associative distributed shared memory for massively parallel architectures that fits the modern style of structured parallel programming and shows the effectiveness of the model with a transputer-based implementation.

Introduction to Advanced Computer Architecture and Parallel Processing

This book will study advanced computer architectures that utilize parallelism via multiple processing units, and major characteristics of the different computing paradigms are associated with each decade of computing.

An Examination of the Current State of the Art in SIMD Processor Extensions for CS 570 Winter 2012

This paper will discuss the hardware itself, the compiler techniques that are used to exploit the presence of data-level parallelism, and the programming interfaces that make it as easy as possible to include those features in the current production chip sets.

A barrel shift microsystem for parallel processing

  • R. BakalashZhong Xu
  • Computer Science
    [1990] Proceedings of the 23rd Annual Workshop and Symposium@m_MICRO 23: Microprogramming and Microarchitecture
  • 1990
A flow-through interconnection network microsystem is described. It is part of a parallel SIMD graphics architecture called Cube in which the network interconnects between n pairs of processors and

A New Type of Parallel Computing Architecture and Its Parallel Computer Based on N+1 Programs

  • Z. XuNing ZhangHaoyuan Xu
  • Computer Science
    2010 3rd International Symposium on Parallel Architectures, Algorithms and Programming
  • 2010
An N+1 computer prototype machine was trialed which could be considered to be a new general type of platform on parallel processing studies and analyzed the operate ability, the computability, and the compilability of the system.

A Survey of High-Level Parallel Programming Models

The properties, advantages, and disadvantages of highlevel approaches to parallel programming that are deemed more exible for eciently utilising modern and future heterogeneous architectures are surveyed.

A Basic Comparison of Different Memories for Object Oriented Computer Architecture

This position paper is focused on the abstract model of Object Oriented Computer Architecture and specifically the memory unit of such a computing system which would be able to handle the type of



An Architectural Comparison of Dataflow Systems

An architectural comparison of seven dataflow processors based on sixteen criteria forms the major part of the article and presents the challenges in the design of processors.

Very high-speed computing systems

The constituents of a system: storage, execution, and instruction handling (branching) are discussed with regard to recent developments and/or systems limitations.

A taxonomy for computer architectures

A taxonomy is presented that extends M.J. Flynn's (IEEE Trans.Comput., vol. C-21, no.948-60, Sept. 1972) based on a state-machine view of processors and shows how this applies to a number of modern architectures.

The DADO Production System Machine

Experimental parallel computing architectures

Parallel Supercomputing Today and the Cedar approach and Questions and Unexpected Answers in Concurrent Computation (G. Gottlieb).

Data-Driven and Demand-Driven Computer Architecture

The aim of this paper is to identify the concepts and relationships that exist both within and between the two areas of research, data-driven and demand-driven computer architectures.

Design of a Massively Parallel Processor

  • K. Batcher
  • Mathematics
    IEEE Transactions on Computers
  • 1980
The massively parallel processor system is designed to process satellite imagery at high rates and can occur at 6553 million operations per second (MOPS) and multiplication at 1861 MOPS.

Classification and Evaluation of Parallel Computer Systems

  • R. Hockney
  • Computer Science
    Parallel Computing in Science and Engineering
  • 1987
A classification is presented of both vector (i.e. SIMD) and parallel (i.e. MIMD) computers, and two simple benchmarks are defined to assess performance. Results are presented for the Cray X-MP

Interconnection networks for large-scale parallel processing: theory and case studies (2nd ed.)

This book presents the theoretical basis and a number of case studies that demonstrate how the construction of an interconnection network to provide interprocessor communications is done.

Wavefront Array Processors-Concept to Implementation

With VLSI it becomes feasible to construct an array processor that closely resembles the flow graph of a particular algorithm, and this type of array maximizes the main strength of VLSi-intensive computing power-and yet circumvents its main weakness-restricted communication.