Last week IBM and Google announced a joint “academic cluster computing initiative” to provide data centers for the promotion of computer programming techniques for clusters of processors known as “clouds.” The centers will grant access and processing power to large numbers of students and programmers for writing software code involving massive amounts of data over the Internet, a practice known as “cloud computing.”
Cloud computing allows computers in remote data centers to run parallel, increasing their processing power. The cloud can run many software applications and can be accessed by many users, improving efficiency for common tasks and making it easier to complete difficult tasks that require extreme amounts of processing power. The program will allow companies and universities to share resources, preventing them from having to expand their own costly data centers. However, the concept does generate some daunting questions about security, reliability and ease of use.
The program, which is already under way at the University of Washington, will also be rolled out at Carnegie-Mellon University, the Massachusetts Institute of Technology, Stanford University, the University of California at Berkeley and the University of Maryland. IBM and Google will provide hardware, software and services.
Three different university curricula on topics related to cluster computing are offered by the University of Washington in conjunction with Google. Google is also offering a series of free video lectures on cluster computing. IBM will provide Hadoop, an open-source software platform for developing clusters, as well as a collaboration Web site for universities and students via the IBM Innovation Factory.
For more details check out extensive cloud computing articles at c|net News or the Wall Street Journal Online.















