Program

Wednesday, April 19

12:00 – 13:00 Participants’ arrival, registration, and reception
13:00 – 14:00 Lunch at Research Campus
14:00 – 14:20 Conference opening
14:20 – 15:55 Keynote session
14:20 – 15:10 Iain Duff (Keynote talk) “Direct solution of sparse linear equations on parallel computers
15:10 – 15:55 Lois Curfman McInnes (Invited talk) “Community software ecosystems for high-performance computational science: Opportunities and challenges
15:55 – 16:30 Coffee break
16:30 – 18:10 Scheduling and communication aspects of high performance computing
16:30 – 16:50 Imad Kissami “HPC as a service for computational fluid dynamics problems
16:50 – 17:10 Michael Hofmann “Transparent execution of numerical libraries on distributed HPC platforms
17:10 – 17:30 Michael Obersteiner “A highly scalable MPI parallelization of the Fast Multipole Method
17:30 – 17:50 Elias Wimmer “Is Gossip-inspired reduction competitive in high performance computing?
17:50 – 18:10 Roman Trobec “Impact of interconnection network topology on parallel performance – a survey
18:30 Discussion “Gender and minority issues in scientific computing” with invited speakers, followed by joint barbecue

 

Thursday, April 20

07:15 – 08:30 Breakfast
08:30 – 10:35 Advanced parallel methods for solving partial differential equations
08:30 – 09:15 Linda Stals (Invited talk) “Use of domain decomposition for the solution of the Thin Plate Spline saddle point problem
09:15 – 09:35 Axel Klawonn “Computing on the extreme scale in nonlinear solid mechanics
09:35 – 09:55 Martin Lanser “A framework for nonlinear FETI-DP and BDDC methods
09:55 – 10:15 Jonas Thies “Employing HPC for analyzing nonlinear PDE systems beyond simulation
10:15 – 10:35 Michael Rippl “Efficient transformation of the general eigenproblem with symmetric banded matrices to a banded standard eigenproblem
10:35 – 11:00 Coffee break
11:00 – 13:00 Matrix factorization methods and applications
11:00 – 11:20 Yusaku Yamamoto “Roundoff error analysis of the CholeskyQR2 and related algorithms
11:20 – 11:40 Miroslav Rozložník “The factors in the SR decomposition and their conditioning
11:40 – 12:00 Gabriel Okša “Convergence of the parallel Block-Jacobi EVD algorithm for Hermitian matrices
12:00 – 12:20 Rade Kutil and Markus Flatz “Convergence and parallelization of nonnegative matrix factorization with Newton iteration
12:20 – 12:40 Mária Lucká “Parallel multi-density based clustering
12:40 – 13:00 Robert Spir “Workflow for parallel processing of biomedical images
13:00 – 14:15 Lunch at Research Campus
14:15 – 15:00 Fluid-particle interaction simulations
14:15 – 15:00 Katarina Gustavsson (Invited talk) “Large scale simulations of fibers in Stokes flow
15:10 Trip to Bamberg (UNESCO World Heritage) including social event

 

Friday, April 21

07:15 – 08:30 Breakfast
08:30 – 10:35 Iterative solvers, preconditioners, and matrix inversion techniques
08:30 – 09:15 Selime Gürol (Invited talk) “Parallelization in the time dimension of geophysical data assimilation problems
09:15 – 09:35 Miroslav Tůma “Mixed sparse-dense linear least squares and preconditioned iterative methods
09:35 – 09:55 Thomas Huckle “Parallel solution of tridiagonal matrices
09:55 – 10:15 Louise Spellacy “Partial inverses of block tridiagonal non-Hermitian matrices
10:15 – 10:35 Zdeněk Strakoš “On the numerical stability analysis of pipelined Krylov subspace methods
10:35 – 11:00 Coffee break
11:00 – 12:40 Programming techniques for GPUs and hybrid architectures
11:00 – 11:20 Tim Werner “Efficient GPU-based Smoothed Particle Hydrodynamics
11:20 – 11:40 Stefan Rosenberger “OpenACC parallelization for the solution of the Bidomain equations
11:40 – 12:00 Thomas Heller “Asynchronous integration of CUDA/OpenCL within HPX for utilizing full cluster capabilities
12:00 – 12:20 Kamil Halbiniak “Exploring programming models for accelerating scientific applications on hybrid CPU-MIC platforms
12:20 – 12:40 Alban Lumi “Energy aware computations on manycore systems
12:45 – 14:15 Lunch at Research Campus
14:15 – 15:15 Data layout and vectorization approaches for modern architectures
14:15 – 14:35 Manfred Liebmann “Explicit vectorization as a design tool for parallel algorithms on modern hardware architectures
14:35 – 14:55 Ivan Kotenkov “Design of cache-efficient multithreaded sparse matrix format for modern era
14:55 – 15:15 Jean-Matthieu Gallard “Code generation for a high order ADER-DG solver in a hyperbolic PDE engine
15:15 – 15:30 Conference closing and participants’ departure

 

PDF file of this program.