Weekly outline

  • General

    Lecturer: Prof. G. Wellein (gerhard.wellein@fau.de), Martensstr. 1, Room 01.131. Phone -28136
    Location: RZ 2.037 - e-Studio, second floor RRZE building (Martensstr. 1)

    Time: Monday, 16:00-17:30

    Credits: 5 ECTS credits. This requires two talks and a written seminar report.

    Possible topics can be found in the intro talk (see below).


    • Christie Louis Alappat (christie.alappat@fau.de), RRZE, Room 1.132-113, Phone -20800
    • Faisal Shahzad (faisal.shahzad@fau.de), RRZE, Room 1.025-113, Phone -28911
    • Georg Hager (georg.hager@fau.de), RRZE, Room 1.130-113, Phone -28973
    • Julian Hammer (julian.hammer@fau.de), RRZE, Room 1.033-113, Phone -20101
    • Jan Eitzinger (jan.eitzinger@fau.de), RRZE, Room 1.025-113, Phone -28911
    • Thomas Röhl (thomas.roehl@fau.de), RRZE, Room 1.132-113, Phone -20800
    • Dominik Ernst (dominik.ernst@fau.de), RRZE, Room 1.033-113, Phone -20101

  • 15 October - 21 October

    First seminar: October 15, 16:00 s.t. (i.e., we will start at 4 p.m. sharp!)

  • 22 October - 28 October

    • Assignment of seminar topics (please make up your mind)
    • Jan Laukemann: Automated Instruction Stream Throughput Prediction for Intel and AMD Microarchitectures. Test talk for the PMBS2018 workshop presentation @ SC18 (via video conference)

    • 29 October - 4 November

      Julia Baumgärtner: Semi-box-stencil. Slides

      • 5 November - 11 November

        Thomas Gruber (RRZE HPC group): Proper benchmarking for performance analysis. Slides

        Students are strongly encouraged to visit this talk because we already know this stuff...

        • 12 November - 18 November

          No seminar this week. To compensate, Prof. Meier from the Pattern Recognition Lab will give a tutorial on Machine Learning and Deep Learning on November 26.

          • 19 November - 25 November

            No talks today.

            This is Q&A day - meet your advisors after 4pm to discuss the current state of your work.

            • 26 November - 2 December

              16:00-19:00: Prof. Andreas Meier, FAU Pattern Recognition Lab, will give an introduction and tutorial on deep learning.

              Deep learning lecture at FAU video portal: https://www.video.uni-erlangen.de/course/id/662

              • 3 December - 9 December

                16:00 s.t.:

                Christie Louis Alappat: Modeling the performance of temporally blocked stencil codes

                • This week

                  10 December - 16 December

                  16:00 s.t.:

                  Ayesha Afzal: Investigating idle waves in HPC - first results.

                  • 17 December - 23 December

                    Guest talk, 16:00 (s.t.):

                    Hartwig Anzt, Karlsruhe Institute of Technology: Towards a modular precision ecosystem

                    Abstract: Over the last years, we have observed a growing mismatch between the arithmetic performance of processors in terms of the number of floating point operations per second (FLOPS) on the one side, and the memory performance in terms of how fast data can be brought into the computational elements (memory bandwidth) on the other side. As a result, more and more applications can utilize only a fraction of the available compute power as they are waiting for the required data. With memory operations being the primary energy consumer, data access is pivotal also in the resource balance and the battery life of mobile devices. In this I will introduce a disruptive paradigm change with respect to how scientific data is stored and processed in computing applications. The goal is to 1) radically decouple the data storage format from the processing format; 2) design a "modular precision ecosystem'' that allows for more flexibility in terms of customized data access; 3) develop algorithms and applications that dynamically adapt data access accuracy to the numerical requirements.
                    • 14 January - 20 January

                      16:00 s.t.:

                      Mehdi Rezaiepour: Sparse MVM on NEC Aurora Tsubasa. (First seminar talk)