Project P5
Contents
High Performance Visual Computing
This project was implemented in the framework of the partnership between the King Abdullah University of Science and Technology (KAUST) and TUM
The project will combine fundamental methodological research in the field of high performance computing (HPC) in a unique way with data exploration on HPC devices and the question how to cross-fertilise seamlessly into applications used at KAUST and TUM to obtain new insight from supercomputing – today and in the upcoming exascale age. It comprises three major goals:
First, we ensure the sustainability of some work conducted under the umbrella of Simulating CO2 Sequestration, as codes stemming from KAUST faculty but extended by TUM project members and associates are prepared for the upcoming generation of supercomputers besides the KAUST facilities. This is of value for KAUST’s TUM projects depending heavily on state-of-the-art algorithms and applications to demonstrate the value of their HPC research and for the KAUST supercomputing community, as they will get access to different machines – in particular Munich’s petaflop system SuperMUC currently ranked number four world-wide – as well as researchers both at KAUST and TUM who want to take part in the next generation research in scientific computing that will rely heavily on the usage of scalable codes on massively parallel machines.
Second, we combine visualization techniques and supercomputing paving the way to interactive, immersive simulation and computational steering. This endeavour both brings together insights from Virtual Arabia and researchers with a supercomputing and algorithmic affinity and it uses synergies from both KAUST’s visualization and supercomputing laboratories. Such an endeavour will pay off for future research both at KAUST and TUM, when insight is not obtained in a batch mode as it is today, but problems and phenomena have to be studied interactively.
Third, we integrate research results obtained with TUM codes into KAUST applications as well as codes from the Virtual Arabia project, i.e. we demonstrate the broader applicability of work done under the umbrella of the KAUST-TUM special partnership projects.
News
19th November 2012: Peano gains resiliency support by supporting Cobra as back-end
Participants
Principal Investigator:
Project Coordinator:
Project Members:
- TUM - Chair for Scientific Computing in Computer Science:
- Atanas Atanasov
- Hans-Joachim Bungartz (Subproject Leader)
- Michael Lieb
- Christoph Kowitz
- Philipp Neumann
- Kristof Unterweger
- Tobias Weinzierl (Subproject Leader)
- Roland Wittmann
- TUM - Chair for Computation in Engineering:
- Jerome Frisch
- Ralf-Peter Mundani
- Ernst Rank (Subproject Leader)
- Vasco Varduhn
- Jerome Frisch
- KAUST:
- Shuyu Sun
- Kai Bao
- Amgad Salama
- Yuanqing Wu
Publications
Poster (PDF) - Philipp Neumann |
Poster (PDF) - Philipp Neumann |
P. Neumann and J. Harting. Massively Parallel Molecular-Continuum Simulations with the Macro-Micro-Coupling Tool. Poster: Workshop on Hybrid Particle-Continuum Methods in Computational Materials Physics, Jülich. 2013.
P. Neumann. Hybrid Multiscale Simulation Approaches for Micro- and Nanoflows. GACM, Hamburg-Harburg. 2013.
- M. Schreiber, T. Weinzierl and H.-J. Bungartz: Cluster optimization of parallel simulations with dynamically adaptive grids [BibTeX]. In EuroPar 2013, 2013. submitted.
- Philipp Neumann and Jens Harting. Massively Parallel Molecular-Continuum Simulations with the Macro-Micro-Coupling Tool . Proceedings of the Workshop on Hybrid Particle-Continuum Methods in Computational Materials Physics, Jülich. 2013
- Philipp Neumann, Tijana Kovacevic, Wolfgang Eckhardt and Hans-Joachim Bungartz. On RDF-Based Boundary Force Models for Multi-Centered Atoms in Open Molecular Dynamics Simulations . Journal of Computational Physics. submitted.
- Philipp Neumann, Wolfgang Eckhardt and Hans-Joachim Bungartz, Hybrid Molecular-Continuum Methods: From Prototypes to Coupling Software , Special Issue in Computers and Mathematics with Applications (ICMMES 2012) (published online)
- Philipp Neumann, Hybrid Multiscale Simulation Approaches For Micro- and Nanoflows , Dissertation, 2013
Software
Peano - a Framework for Solvers on Spacetree Grids
Gallery
- Loadbalancing experiments
- Pictures
- Dynamic adaptive refinement of a circle with online loadbalancing on 512 MPI processes, each rectangle represents a MPI process: Video (~1.2M)
- Visualization on FRAVE:
- Heat source around building and the related mesh illustration
- Visualization at KAUST: Pictures
- Simulation Videos and Images