Markus Wittmann's Blog

Inhalt

Publications

2018

  • M. Wittmann, V. Haag, T. Zeiser, H. Köstler, and G. Wellein: Lattice Boltzmann Benchmark Kernels as a Testbed for Performance Analysis, (2018), Computer & Fluids, Special Issue DSFD2017. preprint arXiv:1711.11468. doi:10.1016/j.compfluid.2018.03.030.

2017

  • S. Bauer, M. Mohr, U. Rüde, J. Weismüller, M. Wittmann, B. Wohlmuth: A two-scale approach for efficient on-the-fly operator assembly in massively parallel high performance multigrid codes. Applied Numerical Mathematics (2017) preprint arXiv:1608.06473. doi:10.1016/j.apnum.2017.07.006.

2015

  • M. Wittmann, G. Hager, T. Zeiser, J. Treibig, G. Wellein: An analysis of energy-optimized lattice-Boltzmann CFD simulations from the chip to the highly parallel level. Concurrency and Computation: Practice & Experience (2016) preprint arXiv:1304.7664 doi:10.1002/cpe.3489.

2014

  • K. Selgrad, A. Lier, M. Wittmann, D. Lohmann, M. Stamminger: Defmacro for C: Lightweight, Ad Hoc Code Generation. Accepted for European Lisp Symposium at IRCAM, May 5-6, 2014, Paris, France.
  • W. Abu Abed, K. Kucher, M. Krafczyk, M. Wittmann, T. Zeiser, G. Wellein: FETOL: A devide-and-conquer based approach for resilient HPC. INFOCOMP 2013: The Third International Conference on Advanced Communications and Computation, Nov. 17-21, 2013, Lisbon, Portugal.

2013

  • F. Shahzad, M. Wittmann, M. Kreutzer, T. Zeiser, G. Hager, G. Wellein: A Survey of Checkpoint/Restart Techniques on Distributed Memory Systems. Parallel Processing Letters 23 (04) (2013). doi:10.1142/S0129626413400112.
  • F. Shahzad, M. Wittmann, M. Kreutzer, T. Zeiser, G. Hager, G. Wellein: PGAS implementation of SpMVM and LBM using GPI. Proceedings of the 7th International Conforence on PGAS Programming Models PGAS2013, 3./4. October 2013, Edinburgh, Scotland, UK.
  • M. Wittmann, G. Hager, G. Wellein, T. Zeiser, B. Krammer: MPC and Coarray Fortran: Alternatives to Classic MPI Implementations on the Examples of Scalable Lattice Boltzmann Flow Solvers. High Performance Computing in Science and Engineering ‘12, pages 367-372 (2013). doi:10.1007/978-3-642-33374-3_27.
  • F. Shahzad, M. Wittmann, T. Zeiser, G. Hager, G. Wellein: An Evaluation of Different IO Techniques for Checkpoint/Restart. Workshop on Large-Scale Parallel Processing 2013 (LSPP13) at IPDPS 2013.

2012

  • F. Shahzad, M. Wittmann, T. Zeiser, G. Wellein: Asynchronous checkpointing by dedicated checkpoint threads. Recent Advances in the Message Passing Interface, Volume 7490 of Lecture Notes in Computer Science, pp. 289-290 (2012). doi:10.1007/978-3-642-33518-1_36.
  • M. Wittmann, T. Zeiser, G. Hager, G. Wellein: Comparison of Different Propagation Steps for Lattice Boltzmann Methods. Computers and Mathematics with Applications (2012) doi:10.1016/j.camwa.2012.05.002 preprint arXiv:1111.0922.
  • M. Wittmann, T. Zeiser, G. Hager, G. Wellein: Domain decomposition and locality optimization for large-scale lattice Boltzmann simulations. Computers & Fluids (2012) doi:10.1016/j.compfluid.2012.02.007 preprint arXiv:1111.1129.

2010

  • M. Wittmann, G. Hager, J. Treibig, G. Wellein: Leveraging shared caches for parallel temporal blocking of stencil codes on multicore processors and clusters. Parallel Processing Letters 20 (4), 359-376 (2010). doi:10.1142/S0129626410000296 preprint arXiv:1006.3148.
  • M. Wittmann, G. Hager, G. Wellein: Multicore-aware parallel temporal blocking of stencil codes for shared and distributed memory, Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW), IPDPS 2010, pp. 1-7, 19-23 April 2010, doi:10.1109/IPDPSW.2010.5470813

2009

  • G. Wellein, G. Hager, T. Zeiser, M. Wittmann, H. Fehske: Efficient temporal blocking for stencil computations by multicore-aware wavefront parallelization. Proceedings of 2009 33rd Annual IEEE International Computer Software and Applications Conference (COMPSAC 2009, Seattle, USA, Juli 20 -24, 2009). IEEE Computer Society : IPSJ/IEEE SAINT Conference, (2009), pp. 579-586. doi 10.1109/COMPSAC.2009.82.

  • Markus Wittmann, Hardware-effiziente, hochparallele Implementierungen von Lattice-Boltzmann-Verfahren für komplexe Geometrien, Technische Fakultät der Friedrich-Alexander-Universität Erlangen-Nürnberg, Dissertation, September 2016.
  • Markus Wittmann, Potentials of temporal blocking for stencil-based computations on multi-core systems, Georg Simon Ohm University of Applied Sciences Nuremberg, Master’s Thesis, March 2009, supervisors: Prof. Dr. Eck and Dr. Georg Hager. Poster, presentet at SC09 (USA, Portland, OR).
  • Markus Wittmann, Ein Maple-Paket zur Bestimmung von Nullstellen, Diploma Thesis, Georg Simon Ohm University of Applied Sciences Nuremberg, September 2007, supervisors: Prof. Dr. Wermuth and Prof. Dr. Delfs.

2018

  • R. Baader, J. Eitzinger, S. Mendez, V. Weinberg, M. Wittmann: Annual course on Advanced Parallel Programming of High Performance Systems. LRZ, Garching, Germany, April 3-6, 2018.
  • M. Martone, G. Hager, L. Iapichino, C. Navarrete, V. Weinberg, M. Wittmann: Annual course on Parallel Programming of High Performance Systems. RRZE, Erlangen, Germany, March 6-10, 2018.

2017

  • M. Wittmann, G. Hager, R. Janalik, A. Klawonn, O. Rheinbach, O. Schenk, G. Wellein: Performance analysis of sparse triangular solve on current hardware architectures. GAMM Workshop on Applied and Numerical Linear Algebra, Cologne, Germany, September 7-8, 2017.
  • M. Wittmann, V. Haag, T. Zeiser, G. Wellein, H. Köstler: Lattice Boltzmann Benchmark Kernel as a Testbed for Performance Analysis. DSFD’17, Erlangen, Germany, July 10-14, 2017.
  • R. Baader, J. Eitzinger, G. Hager, S. Mendez, V. Weinberg, M. Wittmann: Annual course on Advanced Parallel Programming of High Performance Systems. LRZ, Garching, Germany, April 3-6, 2017.
  • F. Baruffa, G. Hager, A. Karmakar, C. Navarrete, V. Weinberg, M. Wittmann: Annual course on Parallel Programming of High Performance Systems. LRZ, Garching, Germany, March 6-10, 2017.

2016

  • J. Eitzinger, S. Mendez, V. Weinberg, M. Wittmann: Annual course on Advanced Parallel Programming of High Performance Systems. LRZ, Garching, Germany, April 4-7, 2016.
  • F. Baruffa, C. Guillen, G. Hager, A. Karmakar, V. Weinberg, M. Wittmann: Annual course on Parallel Programming of High Performance Systems. RRZE, Erlangen, Germany, March 7-11, 2016.

2015

  • M. Wittmann, H. Stengel, G. Wellein, B. Gmeiner, U. Rüde, C. Waluga, B. Wohlmuth, M. Mohr, J. Weismüller and H.-P. Bunge: Performance Modeling and Analysis of Stencil operations in Earth Mantle Convection Simulations. ParCo 2015, Symposium on Parallel solvers for very large PDE based systems in the Earth- and atmospheric sciences, Edinburgh, Scotland, September 1-4, 2015.
  • Hammer, N., Satzger, H., Jamitzky, F., Allalen, M., Block, A., Karmakar, A., Brehm, M., Bader, R., Iapichino, L., Ragagnin, A., Karakasis, V., Kranzlmüller, D., Bode, A., Huber, H., Kühn, M., Machado, R., Grünewald, D., Edelmann, P. V. F., Röpke, F. K., Wittmann, M., Zeiser, T., Wellein, G., Mathias, G., Schwörer, M., Lorenzen, K., Federrath, C., Klessen, R., Bamberg, K., Ruhl, H., Schornbaum, F., Bauer, M., Nikhil, A., Qi, J., Klimach, H., Stüben, H., Deshmukh, A., Falkenstein, T., Dolag, K. and Petkova, M.: Extreme Scale-Out SuperMUC Phase 2, lessons learned. ParCo 2015, Edinburgh, Scotland, September 1-4, 2015.
  • M. Wittmann, T. Zeiser, G. Hager, G. Wellein: Locality and Performance Optimized Adjacency List Generation for Lattice Boltzmann Based Simulations. ParCFD 2015, Montreal, Canada, May 17-21, 2015.
  • J. Eitzinger, S. Mendez, V. Weinberg, M. Wittmann: Annual course on Advanced Parallel Programming of High Performance Systems. LRZ, Garching, Germany, April 7-10, 2015.
  • M. Wittmann, T. Zeiser, G. Hager, G. Wellein: Bestimmung eines optimalen Betriebspunkts am Beispiel eines Lattice-Boltzmann-Lösers auf SuperMUC. ZKI AK Supercomputing, CAU, Kiel, Germany, March 16-17, 2015.
  • C. Guillen, G. Hager, V. Karakasis, A. Karmakar, V. Weinberg, M. Wittmann: Annual course on Parallel Programming of High Performance Systems. LRZ, Garching, Germany, March 9-13, 2015.

2014

  • M. Wittmann, T. Zeiser, G. Hager, G. Wellein: Single Node Performance and Energy Modeling. Invited Talk, Lehrstuhl für Rechnertechnik und Rechnerorganisation / Parallelrechnerarchitektur (LRR), TUM, Garching, Germany, June 10th, 2014.
  • M. Wittmann, T. Zeiser, G. Hager, G. Wellein: Modeling and Analyzing Performance for Highly Optimized Propagation Steps of the Lattice Boltzmann Method on Sparse Lattices. ParCFD 2014, Trondheim, Norway, May 20-22, 2014.
  • Brietzke, Karmakar, M. Klemm, Mendez, C. Navarrete, V. Weinberg, M. Wittmann: Annual course on Advanced Parallel Programming of High Performance Systems. LRZ, Garching, Germany, March 31-April 03, 2014.
  • C. Guillen Carias, G. Hager, J. Treibig, V. Weinberg, M. Wittmann : Annual course on Parallel Programming of High Performance Systems. RRZE, Erlangen, Germany, March 10-14, 2014.

2013

  • R. Bader, A. Block, N. Hammer, C. Navarrete, M. Wittmann: Annual course on Advanced Parallel Programming of High Performance Systems. LRZ, Garching, Germany, March 18-21, 2013.
  • C. Guillen Carias, G. Hager, J. Treibig, V. Weinberg, M. Wittmann : Annual course on Parallel Programming of High Performance Systems. LRZ, Garching, Germany, March 4-8, 2013.

2012

  • M. Wittmann, G. Hager, K. Sembritzki, G. Wellein, T. Zeiser, B. Krammer: MPC and Coarray Fortran: alternatives to classic MPI implementations on the examples of scalable lattice Boltzmann flow solvers. Poster, 15th Results and Review Workshop of the HLRS, Stuttgart, Germany, 10-11. October 2012.
  • M. Wittmann, M. Kreutzer: LIKWID Tutorial: Lightweight performance tools, 6th International Parallel Tools Workshop, HLRS, Stuttgart, Germany, 26. September 2012.

2011

  • M. Wittmann, T. Zeiser: Domain decomposition and locality optimization for large-scale lattice Boltzmann simulations, ParCDF special session on LBM, Barcelona, Spain, May 2011.

2010

  • M. Wittmann, T. Zeiser: Partitioning for lattice Boltzmann solver, LBM Day, Bochum, Germany, 30. November, 2010.
  • G. Wellein, G. Hager, T. Zeiser, M. Wittmann, H. Fehske: Efficient temporal blocking for stencil computations by multicore-aware wavefront parallelization. 33rd Annual IEEE International Computer Software and Applications Conference (COMPSAC 2009), Best Paper Award, Seattle (WA, USA), 20-24. July 2010.
  • M. Wittmann, G. Hager, G. Wellein: Multicore-aware parallel temporal blocking of stencil codes for shared and distributed memory, LSPP10, the Workshop on Large-Scale Parallel Processing at IPDPS 2010, Atlanta, Georgia, USA, 23. April, 2010.
  • M. Wittmann, G. Hager: A Pipelined, Multicore-aware Approach to Parallel Temporal Blocking of Stencil Codes for Shared and Distributed Memory, Facing the Multicore-Challenge, Heidelberg, Germany, 19. March, 2010.

2009

  • G. Wellein, G. Hager, T. Zeiser, H. Fehske, M. Wittmann, J. Habich, J. Treibig: Enabling temporal blocking for stencil computations by multicore-aware wavefront parallelization. CSE Seminar, UC Berkeley and Lawrence Berkeley National Laboratory, Berkeley, CA, USA, 15. May 2009.

2015

  • M. Wittmann, T. Zeiser, G. Hager, G. Wellein: Modeling and analyzing performance for highly optimized propagation steps of the lattice Boltzmann method on sparse lattices, (2015), Version 2, submitted to ISC’16, arXiv:1410.0412.
  • M. Wittmann, T. Zeiser, G. Hager, G. Wellein: Short Note on Costs of Floating Point Operations on current x86-64 Architectures: Denormals, Overflow, Underflow, and Division by Zero, (2015) arXiv:1506.03997.

2014

  • M. Wittmann, T. Zeiser, G. Hager, G. Wellein: Modeling and analyzing performance for highly optimized propagation steps of the lattice Boltzmann method on sparse lattices, (2014), Version 1, arXiv:1410.0412v1.
  • T. Guess, T. Heidig, B. N. Vu, F. Wein, M. Wittmann, T. Zeiser: Performance-Optimierung des Lattice-Boltzmann-Lösers im Verbundprojekt OptiLBM, (2014) Quartl No. 70.

2013

  • M. Wittmann, G. Hager, T. Zeiser, G. Wellein: Asynchronous MPI for the Masses, (2013) arXiv:1302.4280.

2010

  • M. Wittmann, G. Hager: Optimizing ccNUMA locality for task-parallel execution under OpenMP and TBB on multicore-based systems, (2010) arXiv:1101.0093v1.

2009

  • M. Wittmann, G. Hager: A Proof of Concept for Optimizing Task Parallelism by Locality Queues, (2009) arXiv:0902.1884.