Cray, a leading designer and supplier of supercomputers, has announced the company has broadened its support for accelerators and coprocessors, and is now selling the Cray XC30 series of affordable supercomputers with Nvidia Tesla K20X GPU accelerators and Intel Xeon Phi coprocessors. This marks the latest step in Cray's adaptive supercomputing vision, which is focused on delivering systems that integrate diverse technologies into a unified architecture.
"We designed the Cray XC30 supercomputer to be the realization of our adaptive supercomputing vision, which is about providing customers with a powerful, flexible tool for solving a multidisciplinary array of computing challenges. Integrating diverse accelerator and coprocessor technologies into our XC30 systems gives our customers a variety of processing options for their demanding computational needs. Equally as important, Cray XC30 supercomputers feature an innovative software environment that allows our customers to optimize their use of diverse processing options for their unique applications," said Peg Williams, Cray's senior vice president of high performance computing systems.
Leveraging years of successful production accelerator experience, adding the Intel Xeon Phi coprocessors and Nvidia Tesla GPU accelerators is a continuation of Cray's support for innovative hybrid supercomputing technologies. In addition to now being offered in both the Cray XC30 and Cray XC30-AC systems, Intel Xeon Phi coprocessors and Nvidia Tesla GPU accelerators are also available in the Cray CS300 line of cluster supercomputers.
Previously code-named “Cascade”, the Cray XC30 supercomputers are Cray's most advanced HPC systems and are engineered to meet the performance challenges of today's HPC users. The Cray XC30 and Cray XC30-AC supercomputers feature the unique Aries system interconnect; a Dragonfly network topology that frees applications from locality constraints; innovative cooling systems to lower customers' total cost of ownership; the next-generation of the scalable, high performance Cray Linux Environment supporting a wide range of ISV applications; Cray's HPC optimized programming environment; and the ability to handle a wide variety of processor types.
With prices starting at $500 thousand, the Cray XC30-AC (air cooled) supercomputer economizes the packaging, networking, cooling and power options of the Cray XC30 system to provide customers with the optimal balance of features and footprint that matches their unique price/performance requirements. The Cray XC30-AC enables technical enterprise HPC users in fields such as manufacturing, life sciences, financial services and energy to apply supercomputing resources towards solving the growing technical and business challenges that can only be addressed with high-end HPC technology.
"Our first experience with climate and materials science applications showed that replacing one of the multi-core processors in the XC30 with an Nvidia Tesla GPU boosts application performance and disproportionally reduced energy to solution. This provides necessary proof of principle in favor of hybrid compute nodes as a promising solution to the energy challenges we face in supercomputing," said Thomas Schulthess, professor at ETH Zurich and director of the Swiss national supercomputing center.