The efficiency of Linda for general purpose scientific programming

Authors:
Timothy G. Mattson
Affiliations:
-
Venue:
Scientific Programming
Year:
1994

Citing 7
Cited 0

PVM: a framework for parallel distributed computing

Concurrency: Practice and Experience
How to write parallel programs: a first course

How to write parallel programs: a first course
Molecular dynamics simulation on a network of workstations using a machine-independent parallel programming language

Computers and Biomedical Research
Linda on distributed memory multiprocessors

Linda on distributed memory multiprocessors
The Linda alternative to message-passing systems

Parallel Computing - Special issue: message passing interfaces
Real-Time Data Fusion in the Intensive Care Unit

Computer
Implementation of tuple space machines

Implementation of tuple space machines

Quantified Score

Hi-index	0.00

Visualization

Abstract

Linda (Linda is a registered trademark of Scientific ComputingAssociates, Inc.) is a programming language for coordinating theexecution and interaction of processes. When combined with alanguage for computation (such as C or Fortran), the resultinghybrid language can be used to write portable programs for paralleland distributed multiple instruction multiple data (MIMD)computers. The Linda programming model is based on operations thatread, write, and erase a virtual shared memory. It is easy to use,and lets the programmer code in a very expressive, uncoupledprogramming style. These benefits, however, are of little valueunless Linda programs execute efficiently. The goal of this articleis to demonstrate that Linda programs are efficient making Linda aneffective general purpose tool for programming MIMD parallelcomputers. Two arguments for Linda's efficiency are given; thefirst is based on Linda's implementation and the second on a rangeof case studies spanning a complete set of parallel algorithmclasses.