From desktops to cell phones, computing technology keeps us connected wherever we go-and for nearly two decades, Intel Corporation and Carnegie Mellon University have pioneered research to improve devices that enhance our daily lives.
At the heart of that endeavor lies the Intel Labs vision of essential computing: recognizing which technologies we rely on the most and developing ways to incorporate them seamlessly into our lives. With Intel's foresight and Carnegie Mellon's expertise, essential computing will "collectively empower individuals, connect them to each other and into the fabric of networked society," said George Cox, strategist/architect of the Intel Communication Group.
Most recently, Carnegie Mellon's School of Computer Science became the latest research institution-one of only two in the United States-to host a site as part of Open Cirrus, a global, open-source test bed for the advancement of cloud computing research and education. This computing cluster will provide additional resources for Carnegie Mellon faculty and other researchers worldwide. Open Cirrus was launched in 2008 by HP, Intel and Yahoo! to promote open collaboration among industry, academia and governments on data-intensive, Internet-scale computing. The test bed now includes cloud computing infrastructure at 10 "centers of excellence" worldwide.
"The phenomenal success of the worldwide web (WWW) was built on open-source (the Linux-Apache-MySQL-Python stack) in partnership between universities and academia. At Intel, we hope that Open Cirrus will both enable academic research on cloud software from infrastructure to applications, but also recreate that dynamic partnership to power the development of the cloud as an global, open, interoperable, information and compute platform for the 21st century," said Andrew Chien, vice president of Intel Labs and director of Future Technologies Research.
"This site embodies our commitment to the collaborative, open-source research environment that Open Cirrus promotes and to aggressively pursuing cloud computing research on this campus," said Greg Ganger, professor of electrical and computer engineering and director of Carnegie Mellon's Parallel Data Lab.
Organizations increasingly take advantage of cloud computing, which allows them to use shared services and data processing and storage resources that are managed by other organizations. But until recently, university faculty and students did not have direct access to cloud computing resources necessary for research and education on this emerging computing paradigm. That limited universities in their ability to prepare students who will increasingly work in cloud environments. It also inhibited academic research on new applications for the cloud, and on how to improve the software and hardware that enables cloud computing.
"Having a facility like this and being able to participate in Open Cirrus will provide us with unprecedented opportunities for research and education on Internet-scale computing," said Randal E. Bryant, dean of the School of Computer Science. "We see applications well beyond those being pursued by industry today, including astronomy, neuroscience, and knowledge extraction and representation, and we will be able to delve more deeply into the design of the system itself."
The successful history of collaboration between Intel and Carnegie Mellon began when the world's leading manufacturer of microprocessors wanted to develop a parallel supercomputer to expand processing power. So, they tapped the university known for its cutting edge computing technology.
The iWarp project began in 1988 to investigate issues involved in building and using high performance computer systems with powerful communication support. The project led to the construction of the iWarp machines, jointly developed by Carnegie Mellon and Intel. Intel announced the iWarp systems as a product in 1989, and built iWarp systems with over 1500 nodes. In summer 1990, the first iWarp prototype system was delivered to Carnegie Mellon and the first 64 cell systems were delivered within months. The machines remained on campus until the mid-1990s.
The iWarp project marked a significant turning point in computer science, advancing greatly single-chip processing technology. Intel's willingness to equip Carnegie Mellon researchers with the tools necessary to build such a machine, and to work hand-in-hand with the university, resulted in a functional model that scientists could study and eventually improve.
iWarp's success inspired many similar projects at Carnegie Mellon in the following years, including Fx, Nectar, Airshed project, Quake project, Scandal project, and numerous supercomputing and parallel computing research groups.
As work on the iWarp project was winding down, Intel ran into a bugging problem in some of its processors. Although the bugs only occurred rarely, they had disastrous consequences. To fix the problem, Carnegie Mellon computer science professors Randal Bryant and Ed Clarke developed a system of formal verification to prove the correctness of system algorithms. Formal verification constructs an abstract model of the system, allowing researchers to test for vulnerability prior to taking the technology to market, thus saving millions of dollars. Intel subsequently picked up the software and integrated it into each new processor-and the technology continues to be in use today.
The combined success of iWarp and formal verification laid the foundation for an ongoing partnership between Intel and Carnegie Mellon. Among the most significant outgrowths of the relationship has been Intel Labs Pittsburgh, a laboratory designated to do exploratory research that makes an impact on both Intel and the external research community.
Intel Labs Pittsburgh
To fulfill its vision of essential computing, Intel established an industry-academia model to facilitate long-term collaboration. The university lablet is home to 22 full-time Intel employees who work closely with students and faculty from Carnegie Mellon, University of Pittsburgh, UPMC, and a number of other institutions.
The Intel lab is unique in that it promotes openness and joint ownership: Intel researchers and university faculty and students are encouraged to share information, publish findings, and even build on lab developments in other settings.
According to lab director David O'Hallaron, "The revolutionary approach frees up all researchers [from Intel and Carnegie Mellon] to work with us," thus deepening the intellectual talent pool. The result, he said, is a lab that feels like another department on campus, open to faculty and graduate students from across disciplines.
Part of that revolutionary approach, O'Hallaron explained, was Intel's decision to select Carnegie Mellon faculty to head the lab rather than industry professionals, resulting in broader access to the university research community.
Opened in early 2001, Intel Labs Pittsburgh was originally headed by renowned computer science professor Mahadev Satyanarayanan, who worked on creating new storage paradigms and better implementations of conventional storage systems. Dr. Satyanarayanan is a leader in mobile computing and principal architect of the Andrew File System, an integral part of the Andrew Computing System designed at Carnegie Mellon in the early 1980s.
Todd Mowry, associate professor of computer science, took over as head of the lab in 2004. Under his leadership, Intel Labs Pittsburgh developed the Internet Suspend/Resume project which allows users to work in one location, suspend activity, and resume work in another location with an identical computing environment.
Dr. O'Hallaron, who assumed the role of director in 2007, is a proven leader in computer systems and data-intensive computing. He is also Carnegie Mellon associate professor of computer science and electrical and computer engineering, and was awarded the 2004 Herbert A. Simon Award for Teaching Excellence in Computer Science, the 2003 Gordon Bell Award for Special Achievement, and the 1998 Allen Newell Medal for Research Excellence.
Inside the lab, the possibilities seem endless. The open spaces and state-of-the-art technology beg for innovative approaches to contemporary problems. Two research thrusts, in particular, are moving the future of computing technologies closer to our everyday lives: personal robotics and cloud computing.
Working closely with the Quality of Life Technology Center, a partnership between Carnegie Mellon and University of Pittsburgh, researchers at the Intel lab are developing software for a Home Exploring Robotic Butler (HERB) arm to assist in common household tasks. The software enables the arm to detect objects, determine their distance, and make the appropriate movements to pick them up without disturbing other objects. One day this technology will assist elderly or sick persons with daily tasks, thus allowing them to stay in their homes.
A second area of emerging technology is cloud computing. Cloud computing enables users to access a centralized computer to do their work. Big data clusters (such as Gmail) expand individual computational power exponentially and enable groups to advance research far beyond normal power.
"Intel has influenced virtually every college and school at Carnegie Mellon, from the cognitive sciences in [College of Humanities and Social Sciences] to computational finance in GSIA, to say nothing of the interactions in CIT and SCS," said President Jared L. Cohon when Intel Research Pittsburgh was announced.
Over the years, Intel has donated millions of dollars in funding and equipment to support research at Carnegie Mellon, including the Wireless Instructional Laboratory and Computer Architecture Lab. The company offers internships to Carnegie Mellon students and the Intel Foundation Ph.D. Fellowship is among the most coveted awards for School of Computer Science and electrical and computer engineering graduate students. Presently, Intel employs over 200 Carnegie Mellon graduates. With the recent news that Carnegie Mellon has been named one of ten Open Cirrus sites, the relationship will continue to grow to produce the kind of work that has the potential for true global change.