With the Parallel Computing it is possible to subdivide a program in more processes that work on different processors and that they exchange data in cooperation. In this way the resources of memory and ability to calculation can be taken advantage of parallel more computer, optimizing and diminishing in drastic way the times of execution of the programs.

What is the cluster of computer?

A cluster of computer it is constituted from a group of computer, interconnected with a fast net, whose nodes are characterized by powerful and equipped CPU of much memory RAM. Therefore through an operating system (of Linux type) and with specific software used for the programming parallel they come from each other interconnected in order to form a supercomputer. The main advantages of the cluster of computer regarding the supercomputers trade them are:

o Economization: from 5 to 10 more economic times regarding the workstation and to the supercomputers it trades them.

o Reliability and easy maintenance: a cluster can be always maintained with easy available hardware on the market of the PC, and in the same way can be repaired.

Cloud computing and multicore chips have a similar problem. There just aren't enough programmers out there who know how to do parallel programming.

Frankly, it's a bit of a chicken-and-egg problem. Why use multicore chips or move to parallel computing when you don't have anyone who can design the applications to take advantage of their strengths? And if the technologies aren't used, why bother learning parallel programming?

That's exactly why it's good news that IBM and Google are teaming up to promote parallel programming at six U.S. universities.

According to a recent InfoWorld article, parallel programming requires you to examine tasks and break them into hundreds to thousands of smaller pieces, which then will run on various servers at the same time. Michael Suess, a researcher associate at the University of Kassel who writes the blog Thinking Parallel,