Intel, HP, Yahoo create cloud-computing labs

A global cloud infrastructure for researchers will help advance the technology, according to the companies

HP, Intel and Yahoo, in conjunction with academic and other institutions around the world, have announced the creation of a global, experimental environment for cloud computing.

The Cloud Computing Test Bed will initially comprise of six 'Centers of Excellence', with the University of Illinois at Urbana-Champaign (UIUC), the Karlsruhe Institute of Technology in Germany and the Infocomm Development Authority of Singapore joining in with the three companies.

The companies said that the goal of the Cloud Computing Test Bed is to advance research and education in cloud computing, by promoting open collaboration among industry, academia and governments. Cloud applications and services, together with software, hardware and datacentre-management issues, will also be addressed.

"This is a very exciting new initiative in cloud computing. The key thing is that this is a global initiative across three continents — an open-source testbed where people can add anything they wish to, to advance cloud computing and education," said Prith Banerjee, director of HP Labs.

Each centre will have between 1,000 and 4,000 processor cores running Apache Hadoop — an open-source, distributed computing project from the Apache Software Foundation, already used by Yahoo in web search and advertising — and other parallel programming tools and languages. Researchers will be able to apply for access through a selection process later this year, when the centres are expected to become fully operational.

Earlier this year, Intel and Microsoft announced two Universal Parallel Computing Research Centers, one at UIUC and one at the University of California at Berkeley, while, in March, HP set five new goals for its labs, one of which was 'dynamic cloud services'.

Andrew Chien, director of Intel Research, said: "Cloud computing is of critical importance to the industry. We see this as a big challenge not just in services but in what the shape of the hardware layers should be for energy efficiency, manageability and so on. Particularly important [is] that it's an open, community collaboration to allow empirical work at scale. It's one thing to do a paper study, one thing to do a small test-tube study, [and] another to run on a large infrastructure with real network effects, real network contention and so on."