|
IBM recently announced that it has been awarded $53.3 million in funding from the Defense Advanced Research Projects Agency (DARPA) for the second phase of DARPA's High Productivity Computing Systems (HPCS) initiative. IBM's proposal, named PERCS (Productive, Easy-to-use, Reliable Computing System), is to conduct ground-breaking research over the next 36 months in areas that include revolutionary chip technology, new computer architecture, operating systems, compiler and programming environments.
The research program will allow IBM and its partners to pursue a vision of a highly adaptable system that configures its hardware and software components to match application demands. Adaptability enhances the technical efficiency of the system, its ease of use, and its commercial viability by accommodating a large set of commercial and high performance computing workloads. Ultimately, IBM's goal is to produce systems that automatically analyze the workload and dynamically respond to the changes in application demands by configuring its components to match application needs.
Commercial viability is another fundamental goal for the IBM effort. "This program builds on the unique breadth and depth of our research and development organizations," said Nick Donofrio, IBM senior vice president, corporate technology and manufacturing. "IBM has a proven track record of innovating with a sense of business reality and pushing out these innovations in commercially-viable products. This program matches our philosophy of accelerating the flow of innovation out of the labs into the marketplace."
Elmootazbellah Elnozahy, program manager of the PERCS project, also spoke about the business benefits of IBM's vision: "We're not here to build a one-time wonder. This is about changing the way mainstream systems are built. We follow an integrated hardware-software design that can adapt to different types of workloads, so that the system can accommodate the needs of different application classes with a single design point, instead of the current practice of optimizing the system for a particular application class."
PERCS is based on an integrated software-hardware co-design that will enable multi-petaflop sustained performance by 2010. It leverages IBM's Power architecture and will enable customers to preserve their existing solution and application investments. PERCS also aims at reducing the time-to-solution, starting from the inception to actual result. To this end, PERCS will include innovative middleware, compiler and programming environments that will be supported by hardware features to automate many phases of the program development process.
Receiving this DARPA funding allows IBM to continue building on its leadership in powering some of the world's biggest supercomputers as exemplified in the TOP 500 List of Supercomputers released in June. An independent study found IBM to be the number one provider of supercomputing power with a total of 130 teraflops (trillions of calculations per second), which represents more then 34 percent of the total processing power on the list.
This project is a three-year research and development effort. IBM is one of only three companies, along with Cray Inc. and Sun Microsystems, that received the DARPA HPCS grant for Phase II. In this phase, IBM will collaborate with a consortium of 12 leading universities and the Los Alamos National Lab to pursue an ambitious vision of an adaptable computing system with an eye on commercial viability. Hewlett-Packard and Silicon Graphics, Inc. were the other participants in Phase I, which focused on developing a vision and concept for the project.
The IBM project will be managed out of IBM's Research Lab in Austin and will include members from its worldwide research labs, Systems Group, Software Group, and the Microelectronics Division.
|
