Nvidia GPUs to drive supercomputer
Tesla GPUs will work alongside Cray CPUs to drive Blue Waters project
The National Centre for Supercomputing Applications (NCSA), at the University of Illinois in Urbana-Champaign, is creating a Cray supercomputer accelerated by Nvidia Tesla GPUs.
This supercomputer is part of the Blue Waters project to build one of the world's most powerful computer systems. It is hoped that Blue Waters will enable scientists and engineers across the United States to perform breakthrough scientific research.
"NCSA is excited about the inclusion of Nvidia's Tesla GPUs in Blue Waters," said Thom Dunning, director of the Institute for Advanced Computing Applications and Technologies and the National Centre for Supercomputing Applications at the University of Illinois at Urbana-Champaign. "GPUs provide extraordinary capabilities for numerically-intensive computations and a cost-effective, energy-efficient way to build tomorrow's petascale supercomputers."
Tesla GPUs are designed for high performance computing (HPC) and will help enable NCSA to deploy a supercomputer capable of sustained performance of one petaflop (one quadrillion calculations per second) on a diverse range of real-world science and engineering applications. The project is supported by the National Science Foundation and the University of Illinois.
"NCSA has seized this opportunity to make Blue Waters into an even more amazing scientific computing instrument than originally planned," said Steve Scott, chief technology officer of Tesla at Nvidia. "The performance and wide access of Blue Waters will enable the scientific community to accelerate the race for better science."
Extreme-scale supercomputers, such as Blue Waters, are designed to enable computer simulations to more closely mimic nature. Over 25 science teams have already been selected to run research on Blue Waters, in fields ranging from molecular dynamics and astrophysics, to earthquake engineering and materials science.
Nvidia's Tesla GPUs will accelerate some of those compute-intensive applications in conjunction with the large number of Cray system's general purpose CPUs.
The Blue Waters system is designed to be a powerful hybrid supercomputer with more than 235 Cray XE6 cabinets, and more than 30 cabinets of a future version of the recently announced Cray XK6 supercomputer, which includes next-generation NvidiaTesla GPUs based on the "Kepler" architecture.
Tesla GPUs are massively parallel accelerators based on the CUDA parallel computing architecture. Application developers for the Blue Waters supercomputer can accelerate applications in C, C++, or Fortran using simple compiler directives, or with Nvidia's CUDA tools. Compiler directives are a rapidly evolving approach that allows developers to simply augment their code with a few hints that direct the compiler on how to automatically parallelise the application.