ACADEMIA

Building upon its Adaptive Supercomputing vision, Cray has announced that its next-generation supercomputer code-named “Cascade” will be available with NVIDIA Tesla GPUs based on the next-generation NVIDIA Kepler GPU computing architecture.

“This is an exciting announcement for us, and for our customers, as it proves that we remain committed to our vision of integrating a range of advanced processing technologies into a single, scalable architecture,” said Peg Williams, Cray’s senior vice president of high performance computing systems. “Adaptive Supercomputing is about building a robust hardware and software environment that ultimately supports giving our customers choices. Adding the NVIDIA Tesla Kepler-based GPUs, which are designed for computationally intensive HPC environments, into future versions of our Cascade system will give our customers the flexibility to choose from a variety of powerful accelerator options.”

In June, Cray announced that the Cascade supercomputer will be available with the new Intel Xeon Phi coprocessors. With these new offerings, Cray customers will be able to customize a Cascade supercomputer with innovative processor technologies that best meets the high performance computing (HPC) needs of their scientific applications. NVIDIA Tesla GPUs and Intel Xeon Phi coprocessors will be available in future versions of Cray’s Cascade supercomputer.

Cray’s Cascade supercomputer, which is expected to be widely available in 2013, is the next step in Cray’s Adaptive Supercomputing vision. The system will feature major advancements to the Cray Linux Environment, Cray’s HPC-optimized programming environment, and the next-generation Aries interconnect chipset. Cascade will also feature support for Intel Xeon processors – a first for Cray’s high-end systems.

“Cascade will be the first system to combine three key technologies: the latest Intel Xeon CPUs, Cray’s next-generation Aries system interconnect, and new Tesla Kepler-based GPUs, the highest performance, most energy-efficient accelerators ever built,” said Sumit Gupta, senior director of the Tesla business unit at NVIDIA. “This combination enables applications to scale to tens of thousands of CPU-GPU nodes to solve the world’s most complex scientific computing problems.”

A number of leading HPC centers around the world have already signed contracts to purchase Cascade systems:

· In July, Cray announced it had signed a contract with the Commonwealth Scientific and Industrial Research Organization (CSIRO) to provide the Pawsey Centre in Perth, Australia with a Cascade supercomputer and a next-generation Cray Sonexion storage system as part of a $21 million agreement.

· Also in July, Cray announced it had been awarded a supercomputer contract to provide the Finish IT Center for Science Ltd. (CSC) with a Cascade supercomputer.

· Cray announced in June that it will install a Cascade supercomputer and a next-generation Cray Sonexion storage system at the Department of Energy’s National Energy Research Scientific Computing Center (NERSC) in Berkeley, California as part of a $40 million supercomputing agreement.

· In December 2011, Cray announced it was awarded a contract to provide a Cascade supercomputer to the Academic Center for Computing and Media Studies (ACMS) at Kyoto University in Kyoto, Japan.

· In October 2010, Cray announced it had signed a contract with the University of Stuttgart to provide a Cascade system to the High Performance Computing Centre Stuttgart (HLRS) in Germany.

The Cascade supercomputer is in part made possible by Cray’s participation in the Defense Advanced Research Projects Agency’s (DARPA) High Productivity Computing Systems program.