Simulation and High Performance Computing
High Performance Computing
High performance computing is a catalysator for insights-through-computing. With new hardware generations arriving, it emancipates from a nice-to-have feature into a mandatory craft in many disciplines. Our research in this field goes beyond traditional service, i.e. application-specific number crunching, code analysis and tuning. Instead, it searches for innovative algorithms, algorithmic paradigms, patterns, and methodolgies to meet next generation's supercomputing challenges.
For many research questions we are in a position where we wish to evaluate a system or potentially evaluate an adaption to a system - performing a "what if?" analysis. Often it is not possible to evaluate the live system or make changes to a live system. This may be due to the expense of performing such changes, the time required to obtain statistically significant results from such a system or the fact that such evaluations would be far too dangerous to perform. Under such circumstances we can use the approaches of modeling and simulation to evaluate a representation of the system.
Researchers within the group are using modeling and simulation to:
- Evaluate optimal resource provisioning techniques for the Cloud
- Evaluate scheduling approaches for energy saving within a large distributed cluster of computers
- Perform landscape evolution modelling to determine how landscapes will change over milions of years
- Simulate the processing of water treatment plants in order to improve the removal of toxic chemicals