Distributed computing

Distributed computing is the process of running a single computational task on more than one distinct computer.

Table of contents

1 Introduction 2 See also 3 Distributed computing infrastructure 3.1 Proprietary 4 Distributed computing projects 5 Distributed projects directories

Introduction

This differs from cluster computing in that computers in a distributed computing environment are typically not dedicated to distributed computing, whereas clusters are almost always comprised of dedicated hardware. This makes distributed computing very attractive because it can utilize computational resources that would otherwise be unused, or it can make it possible to have resources for special computational purposes shared among users. It also means that high volumes of data that would otherwise require the power of supercomputers can be processed at low cost.

Distributed computing works so well because most of today's CPU power is wasted waiting for user input. The client is specially constructed as a low priority process to use only the computing power that would be wasted anyway, which can be well in excess of 90%.

However, having a low-priority process constantly running prevents operating systems' idlers from putting the processor into a low-power mode, resulting in increased electricity consumption. On powerful CPUs, the difference can be on the order of tens of watts.

There are also social factors, for example the "stat race": competing with other people using daily statistics about the amount of work done. This has been found so important that virtually all distributed computing projects offer on-line statistics updated at least daily, if not realtime.

Distributed computing is also an active area of research with abundant literature. The most known distributed computing conferences are The International Conference on Dependable Systems and Networks [1] and the ACM Symposium on Principles of Distributed Computing [1]. Journals include the Journal of Parallel and Distributed Computing [1].

See also

• Application server
• Grid computing
• Logical clocks
• Parallel computing
• Peer to peer
• Snapshot algorithm
• Software component
• Network of Workstations

Distributed computing infrastructure

• CORBA
• SOAP
• XML-RPC

Proprietary

• Xgrid

Distributed computing projects

• Berkeley NOW Project
• Distributed.net [1] has many projects, one of which is a search for optimal Golomb rulers. Some will venture that Distributed.net is not a non-profit project since the main RC5-72 project they do is indeed for a cash prize from RSA Labs.
• SETI@home[1], a project searching for signs of extra-terrestrial intelligence (SETI).
• GIMPS -- Great Internet Mersenne Prime Search
• United Devices[1] is the largest commercial distributed computing network.
• Genome@Home [1]
• Folding@Home [1] University of Illinois at Urbana-Champaign report on October 22 2002 confirm success in simulating protein folding
• Berkeley Open Infrastructure for Network Computing (BOINC) [1] a distributed computing infrastructure founded and developed by the SETI@home project ([1])
• Project Dolphin takes a count of the number of keys you press on your keyboard. This is mostly an event made of teams.
• Seventeen or bust[1] Attempts to find prime numbers in 17 sequences, to solve the Sierpinski problem. - So far prime in 5 sequences has been found.
• Lifemapper[1] Attempts to build global archive of biological species distributions.

Distributed projects directories

• Internet-based Distributed Computing Projects Lists ongoing, future and past projects, edited by Kirk Pearson.