Google and IBM offer students a parallel playground
IBM and Google have set up a project to improve education in massively parallel application development.
The high cost associated with teaching this programming method is a barrier to entry for many universities, but the new scheme will provide hardware and software tools.
Both companies have a vested interest in pursuing parallel computing. Web services, for example, require computational tasks to be split so they can run on hundreds of servers, distributing the load. This new scheme should ensure that there are more engineers with experience in this area.
“Google is excited to partner with IBM to provide resources which will better equip students and researchers to address today’s developing computational challenges,” says Eric Schmidt, CEO of Google.
“In order to most effectively serve the long-term interests of our users, it is imperative that students are adequately equipped to harness the potential of modern computing systems and for researchers to be able to innovate ways to address emerging problems.”
A cluster of several hundred Google and IBM servers has been made accessible to students over the internet, on which they can test their parallel programming course projects. The servers run open-source software including Linux, XEN systems virtualisation and Apache’s Hadoop project.
The University of Washington was the first to join the initiative, and others will also run a pilot of the scheme, including Carnegie-Mellon University, the Massachusetts Institute of Technology and Stanford University.