Personal tools

Philipp Samfass, M.Sc.

From Sccswiki

Jump to: navigation, search

Address:

TU München
Institut für Informatik
Boltzmannstr. 3
85748 Garching b. München
Office:
Leibniz Supercomputing Centre
Boltzmannstr. 1
E.2.040
Email:
Samfassmail.png
Phone:
(089) 35831-7813
Fax:
Office Hours:
by arrangement

Contents

Research Interests

  • (Hybrid) parallel programming models
  • Accelerators and heterogeneous architectures
  • Performance models
  • Load balancing

Publications

  • P. Samfass and R. Schaller: A parallel non-hydrostatic shallow water model on adaptive triangular meshes in sam(oa)^2 [BibTeX].
    In Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI), Volume 259, p. 2053–2064, September 2016.
  • W. Gropp, L. Olson and P. Samfass: Modeling MPI communication performance on SMP nodes: Is it time to retire the ping pong test [BibTeX].
    In Proceedings of the 23rd European MPI Users' Group Meeting of EuroMPI 2016, p. 41–50. ACM, Edinburgh, United Kingdom, 2016.
  • P. Samfass: A Non-Hydrostatic Shallow Water Model on Triangular Meshes in sam(oa)^2 [BibTeX].
    Studienarbeit/SEP/IDP, Department of Informatics, Technical University of Munich, April 2015.
  • P. Samfass: Extension of the Finite Volume Solver SWE towards the Non-Hydrostatic Shallow Water Equations [BibTeX].
    Bachelor's thesis, Department of Informatics, Technical University of Munich, September 2014.


Talks

  • P. Samfass: Parallel Adaptive Mesh Refinement in Sam(oa)^2 - Load Balancing vs. Work Stealing [BibTeX].
    SIAM Conference on Parallel Processing for Scientific Computing, Tokio, March 2018.
  • P. Samfass: Towards Reactive Task-Based Work Stealing in Distributed Memory in sam(oa)^2 [BibTeX].
    4th International Conference on Computational Engineering (ICCE 2017), TU Darmstadt, September 2017.


Teaching

Further Interests

  • HPC in Machine Learning and "Big Data"
  • Energy-efficient HPC