The Federal University of Rio de Janeiro Embarks on Ground-Breaking Energy Research Powered by New SGI Supercomputer
The Federal University of Rio de Janeiro (UFRJ), the largest university in Brazil, selected an SGI® ICE™ X system to advance critical research for the university and private companies across Brazil. For the past 15 years, UFRJ has used SGI systems to support research in several fields, providing data-intensive capabilities such as high fidelity simulations and seismic imaging. The high performance computing (HPC) system will be installed through the SGI valued partner, Versatus HPC.
Today, SGI is honored to attend the ribbon-cutting event at UFRJ unveiling this new system. The SGI ICE X supercomputer will be operated and maintained by UFRJ’s Alberto Luiz Coimbra Institute and Graduate School of Research and Engineering (COPPE), enabling both public and private partners to analyze highly complex problems at greater scale. This SGI HPC system, powered by the latest Intel® Xeon® processor, will deliver ground-breaking modeling and insights in the areas of seismic imaging, computational fluid dynamics (CFD) and other data intensive applications.
Supercomputers Aid Energy Research
The new system named “Lobo Carneiro”—in honor of Prof. Lobo Carneiro, who was a Professor and the founder for COPPE/ UFRJ—will help support COPPE/UFRJ research and development for various scientific and engineering applications, including oil and gas, wind energy and renewable biofuels.
In oil and gas research, the simulation of turbidity currents, seismic imaging and oil spills are ongoing projects involving several academic and industrial partners. The SGI supercomputer will simulate exploration and production of energy, giving researchers a deeper understanding of the behavior of energy reserves. This information will help lead to more precise data to reduce costs associated with discovery, exploration and extraction. In addition, the new system will support international cooperation projects, such as the Brazil EU HPC for Energy, jointly developed with the Barcelona Supercomputing Center (BSC) in Spain.
The system will also be used to research renewable energy sources. COPPE/UFRJ is partnering with BSC on a three-year project, HPC4E, to help the industry address future energy demands and to reduce carbon footprints. The SGI ICE X supercomputer allows COPPE/UFRJ to more efficiently assess resources and respond to demand peaks and output predictions in wind energy. The system can also assist in the development of efficient biomass-derived fuels, reducing greenhouse gas emissions, hydrocarbon dependency and fuel costs.
The project attracted additional partners from Europe and Brazil, including energy companies TOTAL, REPSOL, Iberdrola and Petrobras along with research centers: CIEMAT, INRIA, University of Lancaster (ULANC), LNNC, ITA, Universidad Federal do Rio Grande do Sur and Universidad Federal de Pernambuco.
“After a lengthy procurement process, we selected SGI because we needed a system that would meet our immediate needs while also giving us a path for future growth,” said Guilherme Horta Travassos, professor of Software Engineering at COPPE/UFRJ.
According to Professor Alvaro Coutinho, head of the High Performance Computing Center at COPPE/UFRJ, “Supercomputing has long been a cornerstone of our scientific research and this new system will ensure we are better equipped to study the most complex issues we are facing today and in the future.”
“As the volume and variety of data continues to grow, so does the ambition of energy researchers hoping to leverage this information to glean meaningful insight in the discovery and extraction phases,” said Gabriel Broner, vice president and general manager of high performance computing at SGI. “SGI is at the forefront of providing researchers with the tools necessary to unlock these insights. We are honored that a renowned institution such as UFRJ has selected SGI to support them in these endeavors.”
UFRJ is the latest customer showing how supercomputing can be utilized in the energy sector. UFRJ chose SGI because of its system’s powerful performance that can visualize, analyze and manage large amounts of data in real time — as well as the ability to provide local technical support to further a strong customer and partner relationship. With the new solution UFRJ will be able to reduce energy costs while leveraging the best ratio of processor power to energy use making faster and more insightful business decisions.
- The new SGI ICE X supercomputer will allow UFRJ to support research and development in different science and engineering applications.
- In oil and gas, the simulation of turbidity currents, seismic imaging, and oil spills are ongoing projects that will get immediate benefits from using the new supercomputer.
- The new system will support international cooperation projects, such as HPC4E.
- SGI is making significant strides in the energy sector with the new UFRJ installation.
The scale-out system includes:
- The UFRJ system will deliver a peak 226 teraflops and is based on the SGI ICE flagship scale-out platform which combines speed, scale and efficiency to provide some of the most powerful distributed-memory supercomputers in the world.
- Three SGI InfiniteStorage IS5600 support 720 Terabytes at 17GB/s using the Intel® Enterprise Editon for Lustre* software. This is the equivalent to 150,000 DVDs or 14,000 Blu-ray Discs.
- The system includes 506 Intel® Xeon® E5-2670 v3 12-Cores 2.3GHz processors with 16 Terabytes of memory across 253 compute nodes.
- UFRJ is expecting an increase up to 2x in processing power with an energy reduction of 3x.
- Installation of this system began in April 2016 and the system will be fully deployed on July 13, 2016.
© 2016 Silicon Graphics International Corp. All rights reserved. SGI, the SGI logo and ICE are trademarks or registered trademarks of Silicon Graphics International Corp. or its subsidiaries in the United States and/or other countries. Intel and Xeon are trademarks or registered trademarks of Intel Corporation. All other product and service names mentioned are the trademarks of their respective companies.