New computing cluster explores data-intensive computing

A recently-announced NSF grant award to the University of Illinois, Urbana-Champaign (UIUC) will give the university access to an on-campus experimental computing cluster.

Funding from the NSF grant will be combined with contributions from UIUC and Yahoo! to purchase the cluster's computing equipment. HP will provide a significant equipment discount and Intel will be donating processors.

The centre will be part of the HP, Intel, Yahoo! Cloud Computing Test Bed, one of six ‘centres of excellence’ that the industry giants are creating around the world to help foster research in data-intensive computing.

Each location hosts a cloud computing infrastructure with 1,000 to 4,000 processor cores capable of supporting the data-intensive research associated with cloud computing.

UIUC will manage the new computer cluster, which will be made open to academic users from other institutions to explore data-intensive computing.

The centre is expected to expand the NSF Cluster Exploratory (CluE) initiative by providing researchers a new platform to conduct systems-level research in support of data-intensive computing.

“This effort will differ markedly from existing experimental clusters,” said UIUC computer science professor and interim head of department Michael Heath, one of three researchers leading the Illinois effort.

“With previous efforts focused on networking or user-level applications, the gaping need to process and respond to large amounts of data has been inadequately addressed.”

“Our effort will go deep into the system software stack to explore new and better ways to provide system-level support for data-intensive computing,” he said.

The NSF Cluster Exploratory (CluE) initiative was first announced in April 2008 to provide NSF-funded researchers access to software and services running on a Google-IBM cluster.

Research into data-intensive computing is expected to shape how the industry and academia could use new computing technologies to solve problems that were previously impractical to solve.

“The challenge for the computing research community is to find a way to turn massive data into knowledge,” explained Jeannette Wing, NSF’s assistant director for Computer and Information Science and Engineering.

“The potential impact in fields as diverse as medicine, biology, physics, meteorology and even the social sciences like economics are virtually limitless,” she said.