As its highest ranked system, JUQUEEN at Jülich captured the #9 position with a Linpack performance of 5 Petaflops (Rmax). Combining JUQUEEN’s compute power with the Rmax performance of the HPC systems of the other GCS member centres – SuperMUC Phase 1 and 2 (2.9 Petaflops respectively 2.8 Petaflops) of the Leibniz Supercomputing Centre (LRZ) and the 2.8 Petaflops of HPC system Hornet of the High Performance Computing Center Stuttgart – GCS now offers a total of 13.5 Petaflops Rmax to its users from science and research, which represents the by far most powerful supercomputing infrastructure in all of Europe.
We are very proud of the fact that after all this time JUQUEEN still shines in the Top-10 of the TOP500,” comments Prof. Dr. Thomas Lippert, Director of the JSC who also serves as the GCS Chairman of the Board. “However, to us, this ranking is only one important aspect. The other is that we at GCS focus first and foremost on economical aspects and on our customers, thus system features like energy efficiency, versatile employment and sustained performance to serve our vast field of users enjoy ultimate priority.”
All GCS centers offer leading-edge supercomputing technologies which are designed to satisfy even the highest demands for compute performance by its users coming from all fields of science and research. Advanced cooling technologies in combination with additional sophisticated energy saving concepts ensure energy-efficient computing in all three GCS locations.
The GCS focus on efficiency is underpinned by the recent system expansion of SuperMUC at LRZ, which significantly reduced power consumption and required system footprint from its predecessor. SuperMUC Phase 2 delivers a Linpack performance of 2.8 Petaflops, which adds to the previously available 2.9 Petaflops of SuperMUC Phase 1. For its users, the divided LRZ system environment is transparent: SuperMUC Phase 1 and 2 are still operated like one single system as the programming environment and the file system are identical. In the current TOP500, the systems are listed separately, capturing position 20 and 21 respectively.
The GCS system infrastructure is complemented by the Cray XC40 System at the High Performance Computing Center in Stuttgart (HLRS). Code-named Hornet, the CRAY installation at HLRS will see a system upgrade later this summer, which shall result in almost doubling the now available Linpack performance of 2.8 Petaflops.