Whether analysing complex molecules, searching for new medically active substances, calculating the global climate or modelling astronomical events, computer simulations are becoming an indispensable tool in an increasing number of scientific fields. New and more powerful supercomputers enable more realistic and more detailed simulations of complex global processes, and at the same time it is becoming more and more difficult for researchers to monitor programme execution and to identify sources of error or performance bottlenecks.
Today the fastest supercomputers have tens or hundreds of thousands of processors working in parallel which, if possible, have to be utilised uniformly during the course of a simulation. In order to help users optimise performance more easily, Russian and European experts have established two projects which will for the first time consider all aspects in a performance analysis – ranging from designing new algorithms and running supercomputer applications down to the hardware actually used.
The HOPSA Project: ‘Holistic Performance System Analysis’:
“The combination and integration of measured data as well as all tools at both levels permits a new holistic analysis of any possible performance bottlenecks in computer simulations and will thus considerably simplify and improve optimization measures,” explains Bernd Mohr from Jülich Supercomputing Centre (JSC). From his base at Forschungszentrum Jülich, home to the fastest supercomputer in Germany, he coordinates the collaboration of the European partners. The Russian project coordinator, Vladimir Voevodin from the Research Computing Center (RCC) of Moscow State University, with the most powerful supercomputer in Russia, also expects increased efficiency, “The HOPSA Project will help scientists to find faster and more efficient solutions to their problems.”
The APOS Project: ‘Advanced Performance Optimisation and Scalability’:
The motivation behind the APOS-EU and APOS-RU projects was twofold: firstly, the project studied the scalability and performance of real-life scientific applications on current HPC platforms and proposed improvements to the applications in order to be able to exploit next-generation HPC hardware; secondly, the project brought together computational scientists from the European Union and Russia to collaborate on solving the issues of preparing HPC software and application domains for the future.
The HPC research represented in the APOS and HOPSA projects allowed the European and Russian partners to focus on their strengths. On the European side, the project partners demonstrated excellent software development expertise on HPC systems. On the Russian side, the project partners demonstrated excellent mathematical skills and a strong ability to translate physical problems into mathematical algorithms. These different but complementary skill sets were very important. The two projects FP7-funded, APOS and HOPSA, both concluded successfully and established strong long-term collaboration relationships between the European and Russian partners.
More information at:
Find out all about the Year of Science activities!
Browse info and press materials!