Berkeley Open Infrastructure for Network Computing
From Wikipedia, the free encyclopedia
 |
|
 Current (top) and former (bottom) BOINC logos |
|
| Developed by | University of California, Berkeley |
|---|---|
| Latest release | 6.4.7 / 2009-03-03 |
| Operating system | Cross-platform |
| Type | Grid computing |
| License | GNU Lesser General Public License |
| Website | http://boinc.berkeley.edu/ |
The Berkeley Open Infrastructure for Network Computing (BOINC) is a non-commercial middleware system for volunteer and grid computing. It was originally developed to support the SETI@home project before it became useful as a platform for other distributed applications in areas as diverse as mathematics, medicine, molecular biology, climatology, and astrophysics. The intent of BOINC is to make it possible for researchers to tap into the enormous processing power of personal computers around the world.
BOINC has been developed by a team based at the Space Sciences Laboratory at the University of California, Berkeley led by David Anderson, who also leads SETI@home. As a "quasi-supercomputing" platform, BOINC has about 550,000 active computers (hosts) worldwide processing on average 1.5 PetaFLOPS as of March 2009,[1] which tops the processing power of the current fastest supercomputer system (IBM Roadrunner, with a sustained processing rate of 1.026 PFLOPS). BOINC is funded by the National Science Foundation through awards SCI/0221529,[2] SCI/0438443[3] and SCI/0721124.[4]
The framework is supported by various operating systems, including Microsoft Windows, Mac OS X and various Unix-like systems including Linux and FreeBSD. BOINC is free software which is released under the GNU Lesser General Public License.
Contents |
[edit] History
BOINC was originally developed to manage the SETI@home project.
The original SETI client was a non-BOINC software exclusively for SETI@home. Being one of the first volunteer grid computing projects, it was not designed with a high level of security. Some participants in the project attempted to cheat the project to gain "credits"; while some others submitted entirely falsified work. BOINC was designed, in part, to combat these security breaches.[5]
The BOINC project started in February 2002 and the first version was released on 10 April 2002. The first BOINC-based project was Predictor@home launched on 9 June 2004.
[edit] Design and structure
BOINC is designed to be a free structure for anyone wishing to start a volunteer computing project. Most BOINC projects are nonprofit and rely heavily, if not completely, on volunteers.[citation needed]
In essence BOINC is software that can use the unused CPU and GPU cycles on a computer to do scientific computing—what one individual doesn't use of his/her computer, BOINC uses. In late 2008, BOINC's official website[6] announced that NVIDIA (a leading GPU manufacturer) had developed a system called CUDA that uses GPUs for scientific computing. With NVIDIA's assistance, some BOINC-based projects have now applications that run on NVIDIA GPUs using CUDA. These applications run from 2X to 10X faster than the former CPU-only versions.
BOINC consists of a server system and client software that communicate with each other to distribute, process, and return workunits.
[edit] User interfaces
BOINC can be controlled remotely by Remote Procedure Calls, from the command line, and from the BOINC Account Manager.
BOINC Manager currently has three 'views': the Advanced View, the Grid View and the Simplified GUI.
The appearance (skin) of the Simplified GUI is user-customizable, in that users can create their own designs.
[edit] Account managers
The account manager concept was conceived and developed jointly by GridRepublic and BOINC. Current account managers include:
- BOINC Account Manager (The first publicly available Account Manager)[citation needed]
- GridRepublic (Follows the idea of keep it simple and keep it neat when it comes to account management)
The account managers are the unifying points for all the BOINC projects. They create a site that one can find and manage project settings with a single log in and password.
[edit] Credit system
The BOINC Credit System is designed to avoid cheating by validating results before granting credit.
- A credit management system helps to ensure that users are returning results which are both scientifically and statistically accurate.
- Online distributed computing is almost entirely a volunteer endeavor. For this reason projects are dependent on a complicated and variable mix of new users, long-term users, and retiring users.
- There is no single generic reason why someone chooses to donate his or her computing resources to any given project.
[edit] Projects using BOINC framework
[edit] See also
[edit] References
- ^ "BOINCstats - BOINC combined credit overview". http://www.boincstats.com/stats/project_graph.php?pr=bo. Retrieved on 2009-03-25.
- ^ Research and Infrastructure Development for Public-Resource Scientific Computing, The National Science Foundation
- ^ SCI: NMI Development for Public-Resource Computing and Storage, The National Science Foundation
- ^ SDCI NMI Improvement: Middleware for Volunteer Computing, The National Science Foundation
- ^ Anderson, David P.. "Public Computing: Reconnecting People to Science". http://boinc.berkeley.edu/madrid.html. Retrieved on 2007-06-13.
- ^ Use your NVIDIA GPU for scientific computing, BOINC official site (December 18 2008)
- ^ BOINC - Berkeley Open Infrastructure for Network Computing, Dr. David Anderson describes SETI@home, BOINC and Distributed Computing, youtube.com
- Vance, Ashlee (2003-12-17). "Sun and UC Berkeley are about to BOINC". The Register. http://www.theregister.co.uk/content/61/34570.html. Retrieved on 2006-11-13.
[edit] External links
 |
Wikimedia Commons has media related to: Berkeley Open Infrastructure for Network Computing |
- Berkeley Open Infrastructure for Network Computing (BOINC)
- BOIN developer Rom Walton's Blog
- Boincoid - A Java/Android port of BOINC
- Interview with David Anderson
- Unofficial wiki
|
||||||||||||||||||||
