updated 12:03 pm EST, Thu November 8, 2012
Intel Xeon processor use allows for over 1 million cores
Cray has launched its new supercomputing creation, the Cray XC30, codenamed Cascade. The new system combines Intel Xeon processors with the Aries interconnect, new cooling and power technologies and Cray's integrated software environment, to create a supercomputer capable of workloads higher than 100 petaflops.
Partly developed under the DARPA High Productivity Computing Systems program, the system uses a Dragonfly topology that frees applications from locality constraints, and a cooling system that uses a transverse airflow to lower the total cost of ownership for the supercomputer. It will use the Intel Xeon E5-2600 product family, allowing the XC30 to scale to over one million cores. Future versions of the XC30 promise to use the Intel Xeon Phi coprocessors and NVIDIA Tesla GPUs, in a similar way to Titan, located at the Department of Energy's Oak Ridge National Laboratory in Tennessee.
So far, the Department of Energy's National Energy Research Scientific Computing Center in California, as well as other research centers in Switzerland, Finland, Australia, and Japan have all signed contracts to purchase the XC30, the first to do so being the University of Stuttgart in Germany. Shipments of the supercomputers are starting now, with systems expected to be available for use in the first quarter of 2013.