SCCS Colloquium - Apr 24, 2019
|Date:||April 24, 2019|
|Time:||14:30 - 15:45|
This session starts earlier, in order to balance the skipped session next week (due to May Day). You are welcome to join even later, at the normal time (15:00).
Jieyi Zhang: Sparse Grid Coarsening for Classification
This is a Guided Research talk. Jieyi is advised by Kilian Röhner.
This work introduces a sparse grid coarsening algorithm for classification problems. It can also be applied to multi-classes problems. The final presentation will cover the sparse grid basics, classification with density estimation and the coarsening algorithm.
Keywords: Sparse Grids
Stephan Pirner: Profiling of a Distributed Task Stealing Implementation in the Parallel Adaptive Mesh Refinement Framework sam(oa)2
This is a Bachelor's thesis submission talk. Stephan is advised by Philipp Samfass.
While easier access to Multi-core architecture and distributed memory drives the development of parallel applications further, load balancing mechanisms for this technology have to be developed. For this purpose, the adaptive mesh refinement framework sam(oa)2 has been developed. While the common approach supposes that an equal distribution of the work on the ranks results in the best runtime, imbalances between nodes are not minded. To get rid of these imbalances a task stealing feature has been implemented in sam(oa)2, this feature provides the possibility to reactively steal a task from another rank on demand in distributed memory. This thesis aims to profile the efficiency of the strategy standing alone and in combination with the a state-of-the-art predictive chains-on-chains partitioning load balancing mechanism. Besides, the chains on chains partitioning is compared in its efficiency to distribute the load among ranks. For this purpose, an integrated profiler is implemented in sam(oa)2 and several experiments are conducted during this work, which will provide deeper information about the load balancing strategies of sam(oa)2.
Keywords: samoa (tsunami simulation), profiler
Ayman Noureldin: A Master-Slave Approach for Multi-Phase Fluid-Fluid Coupling of OpenFOAM and ATHLET
Cooling systems of nuclear reactors are often simulated with 1D thermal-hydraulic system codes such as ATHLET, which allows for quick simulation of potential instabilities in the system. However, 1D solvers cannot reproduce complex 3D phenomena, such as turbulent, multi-phase flow around cooling devices. 3D solvers, such as OpenFOAM, can simulate the complete behavior, in expense of higher computational resources. A hybrid solution, coupling ATHLET and OpenFOAM in a master-slave approach, has been applied in the past for single- and two-phase flows, with limited numerical performance. This talk will present the current state of the two-phase flow coupling and a structured approach to improve its accuracy and extend it to multi-phase flows.