Presentations

Various presentations from conferences, workshops, and other events regarding the NLAFET project and its results are published here.

Overview presentation of the NLAFET project at conferences / workshops

Title of presentation: NLAFET – Parallel Numerical Linear Algebra for Future Extreme-Scale Systems

Besides the named presenters below, several members of the NLAFET consortium team contributed.

  • EXDCI HPC Workshop, Rome, September 29-20. Presentation by Bo Kågström
  • Swedish e-Science Academy, October 14-15, 2015, Arlandastad. Invited presentation by Bo Kågström
  • SIAM Conference on Parallel Processing for Scientific Computing, April 12-15, 2016, Paris. Poster presentation by Bo Kågström, Lennart Edblom, Lars Karlsson, Laura Grigori, Iain Duff, Jonathan Hogg, Jack Dongarra and Nick Higham
  • EASC2016- Exascale Applications & Software Conference, April 24-29, 2016, Stockholm. Presentation by Bo Kågström
  • European HPC Summit week: EXDCI Workshop, May 9-10, 2016, Prague, Czech Republic. Presentation by Bo Kågström and Lennart Edblom
  • Workshop on Batched, Reproducible, and Reduced Precision BLAS, May 18-19, 2016, Univ. of Tennessee, Knoxville, TN. Invited presentation by Bo Kågström
  • IFIP WG 2.5 Workshop on Numerical Software and Scientific Computing, August 4, 2016, Oxford, UK. Invited presentation by Iain Duff

Presentations etc. related to NLAFET, describing NLAFET work

  • SIAM Conference on Parallel Processing for Scientific Computing, April 12-15, 2016, Paris
    Organizing Committee Co-Chair: Laura Grigori, Inria and Université Pierre et Marie Curie, France
    Invited presentation: Scalability of Sparse Direct Codes, Iain Duff, Science & Technology
    Facilities Council, United Kingdom and CERFACS, Toulouse, France
    Minisymposia organization MS60: Advances in Parallel Dense and Sparse Linear Algebra, Jonathan Hogg, Rutherford Appleton Laboratory, United Kingdom and Lars Karlsson, Umeå University, Sweden
    Minisymposia MS60 presentations:

    • The Challenge of Strong Scaling for Direct Methods, Jonathan Hogg, Rutherford Appleton Laboratory, United Kingdom
    • NUMA-Aware Hessenberg Reduction in the Context of the QR Algorithm, Mahmoud Eljammaly, Lars Karlsson, and Bo Kågström, Umeå University, Sweden
    • Low Rank Approximation of Sparse Matrices for LU Factorization Based on Row and Column Permutations, Laura Grigori and Sebastien Cayrols, Inria, France; James W. Demmel, Univ. of California, Berkeley, USA
    • Assessing Recent Sparse Matrix Storage Formats for Parallel Sparse Matrix-Vector Multiplication, Weifeng Liu, Univ. of Copenhagen, Denmark

    Minisymposia MS4 presentation: Enlarged GMRES for Reducing Communication When Solving Reservoir Simulation Problems, Hussam Al Daas, UPMC-Inria-TOTAL, France; Laura Grigori, Inria, France; Pascal Henon, Total E&P, France; Philippe Ricoux, TOTAL SA, France
    Poster presentation: A Standard for a Batched BLAS routines, Pedro Valero-Lara, Univ. of Manchester, UK; Jack J. Dongarra and UK; Stanimire Tomov, Univ. of Tennessee, Knoxville, USA; Mawussi Zounon, Univ. of Manchester, UK

  • Workshop on Batched, Reproducible, and Reduced Precision BLAS, May 18-19, 2016, Univ. of Tennessee, Knoxville, TN
    • Invited seminar: Scalability of sparse direct codes. Iain Duff, Science & Technology Facilities Council, United Kingdom
  • International Supercomputing (ICS) 2016, June 23, 2016, Frankfurt, GermanyWorkshop presentation: Form Follows Function – Software, Algorithms & Application
    Challenges, Jack Dongarra, Univ. of Tennessee, Oak Ridge National Lab, and Univ. of
    Manchester
  • 9th International Workshop on Parallel Matrix Algorithms and Applications (PMAA16), July 6-8, 2016, Bordeaux, France
    Invited presentation: Current Trends in High-Performance Computing and Challenges for the Future, Jack Dongarra, Univ. of Tennessee, Oak Ridge National Lab, and Univ. of Manchester
    Minisymposia presentations – Task-based scientific library on top of runtime system

    • Task-based sparse Cholesky solver on top of runtime system, Florent Lopez, Numerical Analysis Group – STFC Rutherford Appleton Laboratory, UK
    • Towards Highly Parallel and Compute-bound Computation of Selected Eigen-vectors given a Matrix in Schur Form, Lars Karlsson*, Björn Adlerborn, Mahmoud Eljammaly, Carl Christian Kjelgaard Mikkelsen, and Bo Kågström, Umeå University
  • 2016 SIAM Annual Meeting, July 10-15, 2016, Boston, USA
    Minisymposia MS73 – Numerical Linear and Multilinear Algebra, Revisit to the GEMM-Based Level 3 BLAS and Its Impact on High Performance Matrix Computations, Bo Kågström, Umeå University
  • International Congress on Mathematical Software, July 11, 2016, Berlin, Germany
    Invited presentation: An Overview of High-Performance Computing and Changing Rules at Exascale, Jack Dongarra, Univ. of Tennessee, Oak Ridge National Lab, and Univ. of Manchester

Leave a Reply