Google and IBM help students learn parallel programming
Google and IBM have announced a new initiative to help students and researchers learn how to create the massively parallel programs that will be needed to address large-scale problems of the future. The two companies are teaming up to provide hardware, software, developer tools, and services to support curricula created by universities and researchers.
According to the press release, Google and IBM have created the following resources:
- A cluster of processors running an open source implementation of Google's published computing infrastructure (MapReduce and GFS from Apache's Hadoop project)
- A Creative Commons licensed university curriculum developed by Google and the University of Washington focusing on massively parallel computing techniques available at: http://code.google.com/edu/content/parallel.html
- Open source software designed by IBM to help students develop programs for clusters running Hadoop. The software works with Eclipse, an open source development platform. The plugin is currently available at: http://lucene.apache.org/hadoop/
- Management, monitoring and dynamic resource provisioning of the cluster by IBM using IBM Tivoli systems management software
- A website to encourage collaboration among universities in the program. This will be built on Web 2.0 technologies from IBM's Innovation Factory.
A number of free slide shows and videos are already available, with more to come.
Software developers used to single-threaded von-Neumann architectures have largely been caught unprepared by modern hardware designs. One problem is a the huge base of legacy code that developers don't want to just "throw away". This inertia creates an opportunity for new graduates and startups to use disruptive parallel software techniques to far out pace established players in such fields as financial simulations, social networking, and new drug development. The IBM/Google initiative will help train this new generation of engineers to prepare them for our massively parallel future.