Supercomputer to Perform a Quadrillion Mathematical Operations per Second, Crack Plasma Physics

The contract for the supply of a high performance supercomputer center that will perform complex plasma physics calculations has been signed between the Commissariat à l’Energie Atomique et aux Energies Alternatives (CEA) and Bull. The supercomputer is an important milestone of Europe’s contribution to the Broader Approach (BA), an agreement signed between Europe and Japan to complement the ITER project through various R&D activities which are developed in the field of nuclear fusion. The European participation to the BA is coordinated by Fusion for Energy (F4E), the EU organization managing Europe’s contribution to ITER. This specific activity is provided by France as a part of its voluntary contribution to the BA.

The supercomputer will be located in Rokkasho, Japan, at the International Fusion Energy Research Center (IFERC), and will be available to a scientific community of more than 1,000 European and Japanese fusion researchers for the next five years starting from January 2012. With a computational power above one petaflop, the supercomputer will be ranked among the most powerful systems in the world and at least 10 times more powerful than any existing system dedicated to the most advanced modeling and simulation in the field of plasmas and controlled fusion equipment in Europe and Japan. The supercomputer, with a memory exceeding 280 TB and high speed storage system exceeding five PB, will be complemented by a medium-term storage system and a pre/post-processing and visualization system.

The operation of the supercomputer will begin with a few high-visibility code runs, otherwise known as “light-house projects” because of the light they are expected to shed with their findings, to test drive the capacities of the supercomputer and achieve maximum performance. During the rest of its exploitation period, European and Japanese researchers will be invited to submit proposals, which will be selected according to their importance for the development of ITER and fusion research. The volume of findings stemming from this activity will feed into the plasma codes in preparation for ITER and into the design of the future DEMO reactor.

The supercomputer will be the third machine designed and developed by Bull exceeding one petaflop performance. The new supercomputer is designed to be operational 24 hours per day. The computing components combine, within a cluster architecture, 4410 blades bullx series B including 8820 Intel Xeon processors of the "Sandy Bridge" type and 70,560 cores. The supercomputer is equipped with a memory exceeding 280 terabytes and a high bandwidth storage system of more than 5.7 petabytes, supplemented by a secondary storage system designed to support 50 petabytes. The connection network for the cluster is based on InfiniBand technology.

To supplement the computing component, 36 bullx series S systems and 38 bullx series R systems will be used for the cluster's administration; for management of the Lustre file systems and for user access.

Bull also will provide 32 bullx series R systems including high-performance graphics cards for pre-and post processing and visualization.

The supercomputer will be equipped with the bullx supercomputer suite advanced edition, the software suite developed and optimized by Bull for petaflop class systems based on the Linux operating system and including many Open Source components.

Bull will be responsible for the design and realization of the electrical and liquid cooling infrastructures within the computer rooms. It also will be responsible for installation, maintenance and operation of the supercomputer and its peripheral equipment for five years. For all these services, Bull will be assisted by its local partner SGI Japan. The installation of the supercomputer in Rokkasho will start on June 2, 2011.

For further information: