NVIDIA Joins Forces with IIT Delhi to Accelerate India’s Bid for Exascale Computing NVIDIA today announced that it is collaborating with the Indian Institute of Technology Delhi (IIT Delhi) to establish a research lab to help the country reach its goal of achieving exascale computing by 2017.
The Indian government has proposed major investments to upgrade the country’s supercomputing infrastructure and develop an exaflop – or 1,000 petaflops – supercomputer. The new Exascale Research Lab (ERL), co-developed by NVIDIA and IIT Delhi, will help the nation achieve this  goal by providing advanced ongoing research, testing, and technology development in a variety of areas, including processor architecture, circuits, memory architecture, high-speed signaling, programming models, algorithms, and applications.
The lab will also apply its work to address next-generation scientific challenges in computer science, nanotechnology, material science, power engineering, and other domains.
NVIDIA’s latest GPU accelerators will be used for the development of exascale technologies and applications on systems in the lab, as well as for the delivery of cloud-based high-performance computing services. Based on the ultra-high-performance, energy-efficient NVIDIA® Kepler™ compute architecture, these accelerators powersome of the world’s fastest supercomputers, including “Titan” at Oak Ridge National Laboratory in Oak Ridge, Tenn., the world’s highest-performance supercomputer.
“The Exascale Research Lab can potentially help India leapfrog ahead in the supercomputing world,” said Vishal Dhupar, managing director of NVIDIA India. “The lab’s high-performance, energy efficient NVIDIA GPU accelerators will enable Indian researchers to build next-generation supercomputing technologies while maximizing costs and power savings—a critical challenge to overcome for the success of any exascale initiative.”
More than a dozen universities and research institutions across India have collaborated with NVIDIA to drive adoption of GPU-accelerated computing, advancing research across a range of scientific and engineering fields. The development of exascale computing systems, which would be hundreds of times faster than most of today’s petascale systems, will enable unprecedented innovation and breakthroughs in biology, earth sciences, genomics, life sciences, medicine, materials science, energy, national security, and many other scientific domains.
“NVIDIA and ITT Delhi share the common vision of developing technologies that boost computing performance to exascale levels in order to help find solutions to next-generation problems,” said Dr. Subodh Kumar, Professor, Dept. of Computer Science & Engineering at IIT Delhi. “Working with NVIDIA presents significant opportunities for innovation. The pool of talent available at our institute coupled with the access to the latest GPU technology is a promising prospect that will surely propel our race to creating radical, ground-breaking technologies.”
IIT Delhi will provide the infrastructure for the Exascale Research Lab, including software and computing systems, and will maintain an active research program on exascale development and GPU computing. In addition to GPU accelerators, NVIDIA will provide access to its supercomputing and scientific application domain expertise and marketing support.
This new collaboration with IIT Delhi expands NVIDIA’s ongoing support for top academic institutions and other organizations advancing the growth of GPU-accelerated computing across the globe. NVIDIA currently has more than 75 Academic Partnership Programs (APPs) with professors from educational and research institutes across India, many of which offer NVIDIA CUDA® programming courses. NVIDIA also offers the CUDA Research Centre and CUDA Teaching Centre programs, which recognize institutions that embrace GPU computing across multiple research fields and have integrated these techniques into their mainstream computer programming curriculums.
In addition, NVIDIA’s CUDA Centre of Excellence Program recognizes, rewards and fosters collaboration with leading institutions at the forefront of parallel computing research. More information on NVIDIA research activities and these programs is available at the NV Research website