AUSTIN, Tex., Nov. 17 — The Gauss Centre for Supercomputing (GCS) continues to be a global key player in high performance computing (HPC). Its latest HPC installation, the Cray XC40 system named Hazel Hen, which was recently taken into operation at GCS member centre HLRS (High Performance Computing Center Stuttgart), gave its debut on position 8 of the 46th edition of the TOP500 which lists the most powerful HPC systems world-wide. With its Rmax performance of 5.64 petaflops on the Linpack benchmark, Hazel Hen to date is the strongest German representative in the world of supercomputing and the most powerful HPC system of PRACE (Partnership for Advanced Computing in Europe), the Tier-0 infrastructure of the European HPC network.
In the new TOP500 list, which was officially released on November 16 at the Supercomputing Conference 2015 in Austin, Texas, HPC system JUQUEEN of Jülich Supercomputing Centre (Rmax 5.01 petaflops) now takes position 11 while the SuperMUC installations Phase 1 and Phase 2 at the Leibniz Supercomputing Centre in Garching/Munich (LRZ) are listed on position 23 and 24 (2.90 petaflops respectively 2.81 petaflops).
Combining the available computing power of its three member centres, the GCS continues to offer the by far most powerful HPC system infrastructure in all of Europe to its large number of users from the various fields of scientific and industrial research.
“We are very proud to see our new Hazel Hen system positioned in the top 10 of the world’s most powerful HPC machines,” comments Prof. Dr.-Ing. Michael M. Resch, Director of the HLRS. “We cannot stress enough, though, that to us this ranking is only one important criterion. Our clear focus continues on best serving our wide field of users from industry and science, and they have rather divergent requirements on the HPC platform. Thus to us, system features like versatile deployment, sustained performance, and high scalability of applications enjoy ultimate priority – and last but not least, the energy efficiency of the installation has to be kept in mind,” stresses Professor Resch.
All three member centres of the GCS – the High Performance Computing Center Stuttgart (HLRS), the Jülich Supercomputing Centre (JSC) and the Leibniz Supercomputing Centre (LRZ) in Garching near Munich – offer leading-edge supercomputing technologies of complimentary system architecture and design. Due to this approach, GCS is in the unique position to offer its users a system infrastructure which is best possibly suited to meet their specific requirements. The HPC installation at HLRS, a Cray XC40 system, is complemented by JSC’s BlueQueen/G installation code named JUQUEEN, and by the LRZ SuperMUC installations which feature an IBM System X iDataPlex and a Lenovo NeXtScale WCT system.
On the TOP500 list, Tianhe-2, a supercomputer developed by China’s National University of Defense Technology, has retained its position as the world’s No. 1 system for the 6th consecutive time with a performance of 33.86 petaflops (quadrillions of calculations per second or Pflop/s) on the Linpack benchmark.
The Gauss Centre for Supercomputing (GCS) combines the three national supercomputing centres HLRS (High Performance Computing Center Stuttgart), JSC (Jülich Supercomputing Centre), and LRZ (Leibniz Supercomputing Centre, Garching near Munich) into Germany’s Tier-0 supercomputing institution. Concertedly, the three centres provide the largest and most powerful supercomputing infrastructure in all of Europe to serve a wide range of industrial and research activities in various disciplines. They also provide top-class training and education for the national as well as the European High-Performance Computing (HPC) community. GCS is the German member of PRACE (Partnership for Advance Computing in Europe), an international non- profit association consisting of 25 member countries, whose representative organizations create a pan-European supercomputing infrastructure, providing access to computing and data management resources and services for large-scale scientific and engineering applications at the highest performance level.