The third annual HPCAC-ISC Student Cluster Competition (SCC) is a joint event hosted by the HPC Advisory Council (HPCAC) and the organizers if the International Supercomputing Conference (ISC). It is an excellent opportunity to showcase students’ HPC expertise in a friendly yet spirited competition. The SCC event will be held during the ISC’14 Conference and Exhibition in Leipzig, Germany from June 22 to 26, 2014.
The competition will feature small teams that compete to demonstrate the incredible capabilities of state-of- the-art high-performance cluster hardware and software. In a real-time challenge, it will feature 11 teams of six undergraduate students from around the world to showcase the small clusters of their own design on the ISC’14 exhibit floor. In this three-day event, the university teams will race to demonstrate the greatest performance across a range of HPC benchmarks and applications. The participating teams for this year’s competition at ISC’14 are:
- Ulsan National Institute of Science and Technology (UNIST), South Korea
- Massachusetts Green Team, a combined team of students from Massachusetts Institute of Technology (MIT), Bentley University, Northeastern University (NEU), United States
- The University of Edinburgh (EPCC), United Kingdom
- Chemnitz University of Technology, Germany
- University of Hamburg, Germany
- University of São Paulo, Brazil
- University of Colorado at Boulder, United States
- A university to be determined in a run-off competition via the Centre for High Performance Computing (CHPC), South Africa
- University of Science and Technology of China (USTC), China
- Shanghai Jiao Tong University (SJTU), China
- Tsinghua University, China
The students will have a unique opportunity to learn, experience and demonstrate how HPC can influence our world and day-to-day learning. This experience will help them enhance their knowledge and will become useful for their professional careers. The selected applications for the competition come from different areas of sciences that uses HPC:
- Quantum ESPRESSO is an integrated suite of Open-Source computer codes for electronic-structure calculations and materials modeling at the nano-scale. The application is based on density-functional theory, plane waves, and pseudo-potentials. For more information:
- OpenFOAM is a popular free, open source CFD software package, licensed and distributed by the OpenFOAM Foundation and developed by OpenCFD Ltd.
- GADGET is a freely available code for cosmological N-body/SPH simulations on massively parallel computers with distributed memory. GADGET represents fluids by means of smoothed particle hydrodynamics (SPH). The code can be used for studies of isolated systems, or for simulations that include the cosmological expansion of space, both with or without periodic boundary conditions. GADGET can therefore be used to address a wide array of interesting problems in astrophysics, ranging from colliding and merging galaxies, to the formation of large-scale structure in the Universe.
- There will be secret applications announced on each day of the competition. The intent is to present a challenging problems for the teams, thus good team work within members of each team is required to analyze and solve the unfamiliar workload.
The teams will have a constraint of power limited to 3 kW on their cluster configuration. The power draw from their compute cluster will have to stay under the 3 KW power limit. Aside from that, it is up for the team to use any of the hardware they can get from their equipment sponsors on the hardware side, as well as any compilers, software and operating systems level tuning they may deploy on the software stack to achieve the best application performance.
It all concludes with ceremony on the main conference keynote stage to award and recognize all student participants in front of thousands of HPC luminaries. In the end, there will be five awards given:
- Highest LINPACK, for the highest score received for the LINPACK benchmark under the power budget.
- Fan Favorite, to be given to the team which receives the most unique votes from ISC participants during the Student Cluster Competition.
- 1st, 2nd and 3rd Place Overall Winners, for the 3 overall winner awards given to the teams that are determined by the scoring of all the chosen HPC applications, benchmarks, as well as judging by the panel of HPC experts during the interview sessions.
For more information, please visit: http://hpcadvisorycouncil.com/events/2014/isc14-student-cluster-competition
Pak Lui is responsible for application characterization, profiling and testing. Before joining the HPC Advisory Council, Lui was a cluster and software engineer, responsible for building and testing different configurations and environments. He holds a B.Sc. in Computer Systems Engineering and a M.Sc. in Computer Science from Boston University.