June 07, 2012
Despite the volatile economic conditions in Europe and Japan, both areas continue to be a hotbed of supercomputer deployments. This week alone, four new university systems were announced, two installed, with the other two on order.
First up are a couple of systems that have been deployed at two German universities in the state of Rhineland-Palatinate. According to the press release, both are already up and running, one at Johannes Gutenberg University Mainz, and the other at the University of Kaiserslautern.
The supercomputers will only be available to researchers at the two universities, as part of a joint HPC facility, known as the Alliance for High-Performance Computing Rhineland-Palatinate (AHRP). Access to the machines will be provided via a 120 Gbps network pipe connecting the Mainz and Kaiserslautern.
The Mainz system is a 287-teraflop cluster, known as "Mogon" (the Roman name for Mainz), while the University of Kaiserslautern will be host to a smaller machine, known as "Elwetritsch" (named after a mythical creature of southwest Germany). Elwetritsch is said to be about half the size of its Mainz sibling (although no flops rating was provided), and is slated for be expansion in 2013. The new systems will be host to an array of science and engineering applications in physics, mathematics, biology, medicine, and the geosciences.
Mogon and Elwetritsch came with a price tag of €5.5 million ($6.9 million), an investment that was shared between the German federal government, the German Research Foundation, and the two universities. System vendors were not revealed.
Meanwhile in the UK, the University of Leicester announced plans to install a multi-million pound (pound sterling, not tonnage) supercomputer there sometime this summer. The system will be dedicated to astronomy apps, supporting research in areas like dark matter studies, star formation, and black hole physics.
Once again, the machine's flops performance was not revealed, but the cost suggests something in the hundreds of teraflops range. HP will provide the system.
The fourth new supercomputer announced this week is a new Fujitsu PRIMEHPC FX10 machine for the University of Kobe, in Japan. The system will be used for "creating new fields of research and interdisciplinary areas utilizing supercomputer technology."
The PRIMEHPC FX10 is the commercial implementation of Japan's famous K computer, the current reigning champ of the TOP500. Although using the older generation SPARC64 VIIIfx CPU, the original K super delivers over 10 petaflops of performance. By contrast, the new SPARC64 IXfx-powered system to be installed at Kobe is a much smaller machine, and will deliver just 20 teraflops. It's scheduled for boot-up in August.
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?