Distributed computing: Difference between revisions
Jump to navigation
Jump to search
imported>Robert Tito mNo edit summary |
imported>Robert Tito mNo edit summary |
||
| Line 6: | Line 6: | ||
== Network Topology == | == Network Topology == | ||
A distributed computer system generally employs one or more ''master'' computers, and very many ''worker'' computers. The master computer's role is to break the problem into a series of smaller problems (work loads) and to send these | A distributed computer system generally employs one or more ''master'' computers, and very many ''worker'' computers. The master computer's role is to break the problem into a series of smaller problems (work loads) and to send these to participating workers. The workers then perform the work and send the results back to the master computer. | ||
Revision as of 08:28, 24 February 2007
In computer science, distributed computation refers to a strategy for improving the speed of highly parallelizable tasks by distributing pieces of the problem across many computers that together form a distributed computer. Unlike clusters, the computers in a distributed computer may be distributed over large networks, and may be owned by many people or institutions.
Network Topology
A distributed computer system generally employs one or more master computers, and very many worker computers. The master computer's role is to break the problem into a series of smaller problems (work loads) and to send these to participating workers. The workers then perform the work and send the results back to the master computer.
Famous Examples
- SETI@Home is perhaps the most famous example of distributed computation. It is comprised of more than one million computers, of varying architectures and platforms, and is dedicated to computing Fourier Transforms on data recieved from radio telescopes.