HPC is undergoing a major change as the next generation of Exascale system pose numerous challenge :
- Close to a 100 fold reduction in energy consumption;
- Computing models capable of using several tens of millions of computing elements;
- Heterogeneous computing nodes with a deep memory hierarchy.
The exascale transition will require radical innovation in computing technology, both hardware and software
Clear objectives and strong impact for all challenges, EoCoE is working on production applications not mini-apps
- Optimization of turbine placements to maximize power output and reduce wind turbine maintenance.
- Help the European wind industry to be more competitive by reducing the cost of wind energy.
- Enhanced resilience of power market to variability and extreme events.
- Application to actual power management systems for selected site locations.
- increase in performance and extension of lifetime of organic and silicon solar cells.
- ascertain the best electrode/electrolyte combination which optimizes the electricity production in electrochemical systems.
Water for Energy
- High-resolution and reliable long-term predictions for the efficient management of hydropower plants and the optimal configuration of geothermal plants.
Contribute to the success of ITER, shorten time-to- market of commercial fusion power plant, possibly at lower cost.
Each Technical Challenge tackles an important bottle-neck for exascale applications. All Technical Challenges are closely linked to our Scientific Challenges but the tools/methodology developed have impact much beyond our flagship codes.
Programming models : HPC performance, scalability, code architecture and parallelism issues to prepare selected applications to the Exascale ecosystem.
Scalable solvers : design and implement exascale-enabled linear algebra solvers for SC applications and integrate them into the SC application codes.
Data Flow : provide I/O and data-flow support to SC taking care of resiliency, performance, data-size and accessibility.
Ensemble Runs : develop an exascale-ready framework for ensemble runs and in-situ data analysis to empower the Weather and Hydrology applications enabling them to take benefit of next generation exascale machines.
Partnership with EERA, the European Energy Research Alliance
- New transversal Joint Programme devoted to digitalization for energy
- Position paper on HPC for Energy