Leibniz Computing Centre Begins New Era in German HPC

By Nicole Hemsoth

July 28, 2006

On Friday, July 21 2006, Federal Minister for Education and Research Dr. Annette Schavan, the Bavarian Prime Minister Dr. Edmund Stoiber, and the Bavarian Minister for Science, Research and Arts Dr. Thomas Goppel inaugurated the new building of the Leibniz Computing Centre in Garching near Munich (budgeted at ca. 45.2 million euros). At the same time the new national supercomputing system (budgeted at ca. 38 million euros) started operation.

The new system will not only strengthen LRZ's standing in the area of high performance computing, but will also ensure improved competitiveness of the Munich area as well as Bavaria on an international level with respect to scientific computing capability. The new, extensible building, the technical infrastructure, the existing know-how, the firm foundation in many application areas and the nationwide unique combination of economic, industrial and scientific surroundings combine in an ideal manner in favor of LRZ. As a consequence, LRZ is a prime candidate for becoming a European supercomputing center.

The newly erected building which now houses the Leibniz Computing Centre of the Bavarian Academy of Sciences is the most modern and — due to its 5700 square meters of total floor space and 5000 square meters of system floor space — the largest computing center building in Germany. The building, which was designed by the building enterprise, Herzog & Partner BDA, is architecturally divided into three major parts:

1. ComputeCube: National supercomputing system, servers for network and IT infrastructure, the Linux cluster and the extensive data backup and archiving facilities as well as the expensive infrastructure providing electricity and cooling are housed in a remarkable, cube-shaped building measuring 36 meters in each dimension. Within this area increased security measures are enforced, and hence no public access is possible. An electrical power of nominally 4.8 MVA can provide up to 2 Megawatts to the compute systems, and a further 2 Megawatts to the cooling systems. Uninterruptible power supplies are provided. The cooling of the national supercomputing system requires an air throughput of 400,000 cubic meters/hour. Sophisticated security and fire extinguishing equipment protect the technical infrastructure. Further extension due to future demands from additional cooling, electricity or compute systems can easily be performed.

2. Institute Building: The offices and labs of the 170 LRZ staff members are located in the institute building. The ground floor also provides public access (reception, PC-equipped work places for students, offices for help desk and telephone hotline). The three upper stories house the staff offices, labs, conference rooms and the central control room.

3. Lecture and Conference Building: The new building provides a lecture room with 120 seats and a number of seminar rooms of varying sizes. This area of intense public access will mainly be used by students and scientists of the universities in Munich for LRZ presentations (e.g., workshops for computational sciences, DEISA, D-Grid), for series of lectures, or for short-term courses.

The new building was completed within only two years. The cost of around 45.2 million euros was borne by the German Federation and the State of Bavaria in equal parts, based on the HBFG (Hochschulbauförderungsgesetz). It would not have been possible to install the new supercomputing system within the old LRZ building in the center of Munich (Barer St. 21) due to an aged and insufficient infrastructure; furthermore more office space was needed for a staff which is considerably increasing because of new areas of responsibility and recent successes in starting third-party funded projects.

The new supercomputing system replaces the previously used Hitachi SR8000, which was retired on June 30, 2006 after more than six years of user operation. The investment budget for the new system, which is deployed as a nation-wide supercomputing system, is 38 million euros. This budget is also provided via the HBFG, and hence is covered in equal part by Federal Republic and the State. With respect to sustained performance, that is, the performance achieved by the actual scientific users' application profile running on the system, it can be numbered among the fastest systems available worldwide.

Based on a Europe-wide tendering procedure which yielded a number of interesting offers, SGI's Altix 4700 system which makes use of Intel's Itanium 2 processors was selected, since it promised to deliver the highest application performance. A special feature of the selected system consists in its large, uniformly addressable shared memory. This significantly eases the programming of parallelized applications. Due to the well-balanced ratio between compute and I/O performance, the wealth of available software tools and applications, and the usability-targeted embedding into the computing center's infrastructure, the new national supercomputing system Altix 4700 represents a massive progress for the users of scientific computing systems throughout Germany.

The performance of the new computer is impressive. Phase 1 which is starting operation now, is comprised of 4096 Madison 9M processors which are coupled via a ccNUMA fabric, and provides a peak performance of 27 trillion floating point operations per second (27 TFlops). In Phase 2, to be installed in summer 2007, this number will increase to more than 60 TFlops. The size of its main memory is presently 17 TB, and will be increased to approximately 40 TB. The presently available 300 TB scratch disk space will be later increased to 600 TB. For the user's home directories, 40 TB of NAS storage (later 60 TB) will be available. Connection to the outside world is provided by the German scientific network using 10 Gigabit/s Ethernet technologies.

All common programming languages, tools, and parallelization paradigms (from pure OpenMP parallelization on up to 252 processors in a shared memory up to pure MPI parallelization using more than 4000 CPUs as well as any hybrid combination of the two) will be available. As a result, new orders of magnitudes of computability will open up in many areas of scientific investigation.

The new system will be mainly deployed for simulations of complex systems and processes in physics, materials science, fluid dynamics, astrophysics, chemistry as well as in geo- and bio-sciences. Examples are: the investigation of turbulence, of flows in porous media, of the interaction of flows with deformable structures, the generation and propagation of acoustic waves, high temperature superconductivity, materials with form memory, chemical reactions during catalytic and combustion processes, the propagation of seismic waves and earthquakes, as well as investigations of sequence, structure and function of proteins. A prerequisite for usage of the system is a positive assessment of the prospective user's project by a committee of experts.

Leibniz Computing Centre of the Bavarian Academy of Sciences

Leibniz Computing Centre (LRZ) is an institution of the commission for informatics at the Bavarian Academy of Sciences. Nowadays, it employs 170 staff members. LRZ understands itself as a service-oriented enterprise for scientific institutions. Via the Munich scientific network, which is also operated by LRZ, all central servers and systems of the universities in Munich as well as from other scientific institutions (e.g., the Bavarian Academy of Sciences, the Max-Planck Institutes, the Fraunhofer society etc.) are interconnected. In its role as a center for technical and scientific supercomputing, LRZ operates an HPC system for state-wide usage, and since March 2000 also one of three national supercomputing systems, which can be used by scientists throughout Germany. Apart from investigations in the area of scientific supercomputing and IT management LRZ also is a nation-wide competence center for data communication networks, collaborating with other scientific institutions and industrial partners within a number of pilot projects.

Bavarian Academy of Sciences

The Bavarian Academy of Sciences was founded in Munich in 1759. With a full-time staff of 350 and an annual budget of 35 million euros it is the largest of the seven scientific Academies in Germany. Its main focus is on interdisciplinary basic research, long-term research projects in the arts and humanities as well as the natural sciences, for example the compilation of scientific dictionaries, publication indices, and critical complete editions, which provide an essential basis for scientific teaching and research. The Academy maintains international contacts and arranges symposia on present research activities, e.g. in the area of ecology or medicine. The 39 commissions encompassed by the Academy presently supervise 129 research projects. Two of the commissions additionally operate scientific institutions in Garching: Leibniz Computing Centre and the Walther-Meissner Institute for low-temperature research.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire