Aachen, Midterm review Meeting & Training Programe, 1- 5 September 2014:
September 1, 2014 Midterm Review Meeting
in Presence of REA Project Officer and REA Expert Reviewer
IT Center, RWTH Aachen
September 2-5, 2014
Training on High-performance computing, parallelisation, GPU computing:
Computer architectures and programming models / languages for high-performance computing (HPC) play a central role in the AboutFlow project. Adjoint -based optimization of industrial and unsteady flows require modern HPC infrastructure as well as appropriately trained research and development personnel.
The highly ambitious goals of AboutFlow are unlikely to be met unless solution methods followed make full use of the state of the art in this quickly evolving area.
This workshop aims to set the stage for the successful implementation of continuous and discrete adjoint optimization methods by introducing the various HPC programming models targeting distributed and shared memory architectures (MPI/OpenMP) and modern accelerator technology (CUDA, OpenACC). Lecture-style sessions are combined with hands-on practical exercises leaving participants with bot conceptual insight as well as reference implementations. We provide ready access to the corresponding computer architectures through the RWTH Compute Cluster (https://doc.itc.rwth-aachen.de/display/CC/General) with appropriately configured Laptop computers used as front-ends in class.
AboutFlow team in Aachen : Visit to Jülich Supercomputing Centre