Philipp Samfass, M.Sc.

Technische Universität München

Institut für Informatik
Boltzmannstrasse 3
85748 Garching
Germany

Office: E.02.040 (Leibniz-Rechenzentrum, Boltzmannstr. 1)
Mail: samfass (at) in.tum.de 

Tel: +49-89-35831-7813
Office Hours: by arrangement

 

Background

Research interests

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

Projects

Teaching

Open and Running Student Projects

Finished Student Projects

2021

  • Amartya Das Sharma: Implementation of a Distributed Actor Library using GPI. Master thesis, 2021 more…
  • Atamert Rahma: Towards Soft Error Resilience in SWE with TeaMPI. Bachelor thesis, 2021 more…
  • Manuel Schnaus: Towards Resilience Methods for Simulation Applications based on Actor Replication. Bachelor thesis, 2021 more…
  • Nikola Nincic: Evaluation of Modern PGAS Libraries for Work Stealing in Distributed Memory. Bachelor thesis, 2021 more…
  • Simon Schuck: Integrating Task Sharing with Team Recovery for Hard Failure Tolerance in teaMPI and SWE. Bachelor thesis, 2021 more…

2020

  • Alexander Hölzl: Integrating TeaMPI with ULFM for Hard Failure Tolerance in Simulation Software. Bachelor thesis, 2020 more…
  • Dominik Mehringer: Solving the Shallow Water Equations on Heterogeneous Architectures with Kokkos. Bachelor thesis, 2020 more…
  • Maximilian Karpfinger: Exploring Load Balancing for Modern Numerical Software. Bachelor thesis, 2020 more…
  • Nicolas Witter: From Predictive to Reactive Load Balancing: Exploring Modern Load Balancing Approaches. Bachelor thesis, 2020 more…

2019

  • Martin Bogusz: Exploring Modern Runtime Systems for the SWE Framework. Bachelor thesis, 2019 more…
  • Stephan Pirner: Profiling of a Distributed Task Stealing Implementation in the Parallel Adaptive Mesh Refinement Framework sam(oa)^2. Bachelor thesis, 2019 more…

2018

  • Olden, Jurek: Performance Analysis of SWE Implementations based on modern parallel Runtime Systems. Bachelor thesis, 2018 more…

Publications

2021

  • Joseph Schuchart; Philipp Samfass; Christoph Niethammer; José Gracia, George Bosilca: Callback-based completion notification using MPI Continuations. Parallel Computing, 2021 more…

2020

  • Jannis Klinkenberg; Philipp Samfass; Michael Bader; Christian Terboven; Matthias S. Müller: Reactive Task Migration for Hybrid MPI+OpenMP Applications. Parallel Processing and Applied Mathematics. 13th International Conference, PPAM 2019 (Lecture Notes in Computer Science 12044), Springer, 2020Bialystok, Poland, 59-71 more…
  • Klinkenberg, Jannis; Samfass, Philipp; Bader, Michael; Terboven, Christian; Müller, Matthias S.: CHAMELEON: Reactive Load Balancing for Hybrid MPI+OpenMP Task-Parallel Applications. Journal of Parallel and Distributed Computing 138, 2020, 55-64 more…
  • Martin Bogusz; Philipp Samfass; Alexander Pöppl; Jannis Klinkenberg; Michael Bader: Evaluation of Multiple HPC Parallelization Frameworks in a Shallow Water Proxy Application with Multi-Rate Local Time Stepping. Parallel Applications Workshop, Alternatives To MPI (PAW-ATM), IEEE/ACM sigARCH, 2020 more…
  • Philipp Samfass; Tobias Weinzierl; Benjamin Hazelwood; Michael Bader: TeaMPI - Replication-based Resilience without the (Performance) Pain. High Performance Computing 35th International Conference, ISC High Performance 2020 (Lecture Notes in Computer Science 12151), 2020 more…
  • Reinarz, Anne; Charrier, Dominic; Bader, Michael; Bovard, Luke; Dumbser, Michael; Duru, Kenneth; Fambri, Francesco; Gabriel, Alice-Agnes; Gallard, Jean-Matthieu; Koeppel, Sven Köppel; Krenz, Lukas; Rannabauer, Leonhard; Rezzolla, Luciano; Samfass, Philipp; Tavelli, Maurizio; Weinzierl, Tobias: ExaHyPE: An Engine for Parallel Dynamically Adaptive Simulations of Wave Problems. Computer Physics Communications 254, 2020, 107251 more…
  • Samfass, Philipp; Weinzierl, Tobias; Charrier, Dominic E.; Bader, Michael: Lightweight task offloading exploiting MPI wait times for parallel adaptive mesh refinement. Concurrency and Computation: Practice and Experience 32 (24), 2020 more…

2018

  • Jannis Klinkenberg, Philipp Samfass, Christian Terboven, Alejandro Duran, Michael Klemm, Xavier Teruel, Sergi Mateo, Stephen L. Olivier, Matthias S. Müller: Assessing Task-to-Data Affinity in the LLVM OpenMP Runtime. Evolving OpenMP for Evolving Architectures, 2018 more…
  • Philipp Samfass, Jannis Klinkenberg, Michael Bader: Hybrid MPI+OpenMP Reactive Work Stealing in Distributed Memory in the PDE Framework sam(oa)^2. 2018 IEEE International Conference on Cluster Computing (CLUSTER), 2018 more…

2016

  • Samfass, Philipp; Schaller, Raphael: A parallel non-hydrostatic shallow water model on adaptive triangular meshes in sam(oa)^2. Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI), 2016 more…
  • William Gropp; Luke Olson; Philipp Samfass: Modeling MPI communication performance on SMP nodes: Is it time to retire the ping pong test. Proceedings of the 23rd European MPI Users' Group Meeting (EuroMPI 2016), ACM, 2016 more…

2015

  • Samfass, Philipp: A Non-Hydrostatic Shallow Water Model on Triangular Meshes in sam(oa)^2. Studien thesis/SEP/IDP, 2015 more…
  • Samfaß, Philipp: A Non-Hydrostatic Shallow Water Model on Triangular Meshes in sam(oa)^2. Studien thesis/SEP/IDP, 2015 more…

2014

  • Samfass, Philipp: Extension of the Finite Volume Solver SWE towards the Non-Hydrostatic Shallow Water Equations. Bachelor's thesis, 2014 more…
  • Samfaß, Philipp Johannes: Extension of the Finite Volume Solver SWE towards the Non-Hydrostatic Shallow Water Equations. Bachelor thesis, 2014 more…
  • Samfaß, Philipp Johannes: Extension of the Finite Volume Solver SWE towards the Non-Hydrostatic Shallow Water Equations. Bachelor's thesis, 2014 more…

Talks

2019

  • Philipp Samfass: (Reactive) Load Balancing Mechanisms for Simulation Applications. (Talk / Invited Talk at Durham University) 2019 more…

2018

  • Philipp Samfass: Parallel Adaptive Mesh Refinement in Sam(oa)^2 - Load Balancing vs. Work Stealing. SIAM Conference on Parallel Processing for Scientific Computing , 2018 more…

2017

  • Philipp Samfass: Towards Reactive Task-Based Work Stealing in Distributed Memory in sam(oa)^2. 4th International Conference on Computational Engineering (ICCE 2017), 2017 more…

Posters