While being located at Forschungszentrum Jülich, this research group is at the same time affiliated with the Computer Science Department of RWTH Aachen University.

Our objective is to make the optimization of parallel applications both more effective and more efficient. Facing increasing power dissipation, little instruction-level parallelism left to exploit, and almost unchanged memory latency, computer architects are realizing further performance gains by placing multiple "slower" processor cores on a chip rather than by building faster uniprocessors. As a consequence, numerical simulations are being required to harness higher degrees of parallelism in order to satisfy their growing demand for computing power. However, writing codes that run efficiently on large numbers of processors and cores is extraordinarily challenging and requires adequate tool support for performance analysis. Unfortunately, tools that normally assist developers in the optimization process often cease to work in a satisfactory manner when deployed on large processor counts. To improve the efficiency of large-scale applications and, thus, to expand their potential, our group develops scalable tools that collect relevant data on code performance and identify the causes of performance problems. In addition to mastering parallelism inside a single machine, further challenges for achieving high application performance arise in Grid environments, which allow the coordinated use of multiple computing resources from different organizations. Therefore, a second goal of our group is developing new solutions to study the performance characteristics of Grid applications reaching beyond the limits of a single computer.