Leibniz Supercomputing Centre (LRZ) of the Bavarian Academy of Sciences and Humanities, Germany, has signed a contract with Intel for the delivery of a new supercomputer.
SuperMUC-NG will be the next-generation to the currently operated SuperMUC, it will provide an impressive computational power of 26.7 petaflops per second (PFlops/s) to a wide-ranging scientific community.
The new supercomputer will significantly improve computer power and will enable the handling of large amounts of data accumulated in experiments and simulations.
Another aim is to provide users with the flexibility to deploy their own software and visualisation environments for analysing the data generated by sharing the results.
Dieter Kranzmüller, Chairman of the board, LRZ, said: “The new supercomputer SuperMUC-NG will provide more compute power for scientists, but also will require more expertise. Researchers will be able to tackle problems that are more complex. The LRZ experts assist them, providing an interface between the scientific community and computer science. We are all well prepared to support scientists in achieving the next level of supercomputing. As part of the project we will again extend our user support team.”
Hannes Schwaderer, Head of Enterprise Sales Intel Deutschland GmbH added: “We are happy to contribute an essential part to this important project, thereby supporting LRZs service efforts. Handling huge amounts of data is vital”
Scott Tease, executive Director, HPC and AI, Lenovo Data Centre Group said: “Processing these data requires immense computational power. Intel’s state-of-the-art processor architecture provides an important basis and ensures that all demands for high performance computing can be optimally fulfilled.”
Just as SuperMUC has previously, the new super computer will be cooled using warm water. Lenovo, the system integrator, has developed a cooling concept that will further reduce power consumption and reuse the waste heat of the supercomputer to generate cold water.”
Up to now, cosmology and astrophysics, solid-state physics and fluid dynamics have been the classical domains of supercomputing. During the last years other scientific domains have entered the field, mainly projects from the life sciences as well as environmental and disaster research.
Two recent examples where SuperMUC has enabled scientific breakthrough are an international team studying personalised medicine figured out which treatment will be efficacious for specific patients, and a simulation of the Sumatra-Andaman Earthquake causing the tsunami in 2004.
Alongside colleagues from Canada, scientists at Ludwig-Maximilians Universität, Technical University Munich and LRZ performed comprehensive simulations of the effects of global warming on extreme rainfalls in Bavaria.
The funding of SuperMUC-NG is shared to equal parts by the government of Germany and by the Free State of Bavaria through a plan of the Gauss Centre for Supercomputing (GCS).
The total cost of the project sums up to €96m for six years.