The Berkeley Open Infrastructure for Network Computing (BOINC) software is a distributed computing infrastructure originally developed out of the SETI home project, but intended to be useful to fields beyond SETI.
BOINC is the information technology infrastructure for distributing work in the form of work units and downloading the distributed applications that process them.
BOINC does no useful scientific work itself. Scientific computations are run on user computers and results are analyzed after they are validated and transferred from BOINC into a scientific database.
Multiple independent projects use BOING such as: Einstein@Home, BBC Climate Change Experiment and more.
Participants can participate in multiple projects; they control which projects they participate in, and how their resources are divided among these projects. When a project is down or has no work, the resources of its participants are divided among other projects.
Projects do not rely on powerful supercomputers for its data processing; instead, the primary contributors to the projects are many thousands of personal computer users who have installed BOINC client program. The client runs in the background, and makes use of the CPU when it is not busy.
· Pentium 233 MHz (Recommended: Pentium 500 MHz or greater)
· 64 MB RAM (Recommended: 128 MB RAM or greater)
· 20 MB disk space
· You must have administrator privileges to install BOINC.
· You must have driver version 185.85 or better installed in order to use your GPU.
· You must have driver version 8.12 or better installed in order to use your GPU.
What's New in This Release: [ read full changelog ]
· Fix: Fix installer for Windows 8 (Windows Only)
· Fix: Fix issue with screensaver shutdown logic. (Windows Only)
· Fix: Fix issue where the client reports that the science applications exited with a status code of 1. (Windows Only)
· Fix: Fix log growth issue. (Windows Only)
· Fix: Don't assign CUDA jobs to a GPU where only OpenCL has been detected on an Nvidia GPU.
· Fix: Fix GPU naming issue when there is more than one GPU by a vendor in the machine.