Ninth INFN International School on: "Architectures, tools and methodologies for developing efficient large scale scientific computing applications" ESC17 - Bertinoro (Forlì-Cesena) Italy 22-28 October 2017

Europe/Rome
Bertinoro

Bertinoro

Hands-on material
Pictures
    • Registration and Welcome
    • 20:30
      Welcome Dinner
    • Session 1
      • 1
        Welcome and introduction
        Speaker: Mauro Morandin (INFN - Padova)
        Slides
      • 2
        Computer Architecture evolution and the performance challenge
        Speaker: Vincenzo Innocente (CERN)
        Slides
      • 10:30
        Coffee break
      • 3
        Computer Architecture evolution and the performance challenge
        Speaker: Vincenzo Innocente (CERN)
      • 4
        Hands-on environment checkout
        Speaker: Dr Francesco Giacomini (CNAF)
      • 12:30
        Lunch break
      • 5
        Efficient C++ programming and memory management
        Speaker: Dr Francesco Giacomini (CNAF)
        Slides
      • 6
        Efficient C++ programming and memory management
        Speaker: Dr Francesco Giacomini (CNAF)
      • 15:30
        Coffee break
      • 7
        Efficient C++ programming and memory management
        Speaker: Dr Francesco Giacomini (CNAF)
      • 8
        Consolidation
      • 9
        Students lightning presentations
        Slides
    • 19:30
      Dinner
    • Session 2
      • 10
        Efficient C++ programming and memory management
        Speaker: Dr Francesco Giacomini (CNAF)
      • 11
        Efficient C++ programming and memory management
        Speaker: Dr Francesco Giacomini (CNAF)
      • 10:00
        Coffee break
      • 12
        Efficient C++ programming and memory management
        Speaker: Francesco Giacomini (CNAF)
      • 13
        Efficient C++ programming and memory management
        Speaker: Francesco Giacomini (CNAF)
      • 14
        Consolidation
      • 13:30
        Lunch break
      • 15
        Introduction to parallel computing (basic concepts)
        Speaker: Dr Tim Mattson (Intel)
        Slides
      • 16
        Introduction to parallel computing with OpenMP
        Speaker: Dr Tim Mattson (Intel)
      • 16:30
        Coffee break
      • 17
        Parallel Performance concepts using OpenMP
        Speaker: Dr Tim Mattson (Intel)
      • 18
        Students lightning presentations
        Slides
    • 19:30
      Dinner
    • Session 3
      • 19
        Efficient C++ programming and memory management
        Speaker: Francesco Giacomini (CNAF)
        Slides
      • 20
        Efficient C++ programming and memory management
        Speaker: Francesco Giacomini (CNAF)
      • 10:00
        Coffee break
      • 21
        A "Hands-on" introduction to OpenMP
        Speaker: Dr Tim Mattson (Intel)
      • 22
        A "Hands-on" introduction to OpenMP
        Speaker: Dr Tim Mattson (Intel)
      • 23
        Consolidation
      • 13:00
        Lunch break
      • 14:00
        Visit of the Interfaith Museum
      • 24
        Working with OpenMP: Performance Optimization
        Speaker: Dr Tim Mattson (Intel)
      • 16:15
        Coffee break
      • 25
        Working with OpenMP: Debugging Applications
        Speaker: Dr Tim Mattson (Intel)
      • 26
        Consolidation
    • 19:30
      Dinner
    • Session 4
      • 27
        Efficient floating-point computation and vectorization
        Speaker: Vincenzo Innocente (CERN)
        Slides
      • 28
        Efficient floating-point computation and vectorization
        Speaker: Vincenzo Innocente (CERN)
      • 10:00
        Coffee break
      • 29
        Efficient floating-point computation and vectorization
        Speaker: Vincenzo Innocente (CERN)
        1
      • 30
        Consolidation
      • 31
        GPUs and the Heterogeneous programming problem
        Speaker: Dr Tim Mattson (Intel)
        Slides
      • 13:00
        Lunch
      • 32
        GPU programming with OpenCL: Ideas and the host program
        Speaker: Dr Tim Mattson (Intel)
        Slides
      • 33
        Consolidation
      • 16:15
        Coffee break
      • 34
        Consolidation
      • 35
        From HPC to Deep Learning, a short journey on modern techniques
        Software design of legacy high-performance computing (HPC) applications is heavily influenced by the frequent changes on the architectures. The classic CPU-based approach with communication libraries is not sufficient to scale beyond the limit of Amdahl law and Dennard scaling. Silicon manufacturers design alternative architectures and programming models to overcome this limitation, leading to systems with hidden complexity. In this seminar are presented a variety of possible scalable configurations and details of usability of each one, with specific attention to NVIDIA software tools. A second part of the talk is dedicated to the intriguing emerging technique of deep learning (DL). Two aspects of DL are shown in detail: 1) it is a new technology which allows to create fast-simulation software, 2) DL changes completely the paradigm of programming, moving the developer to a much higher abstraction layer, away from the hardware details.
        Speaker: Piero Altoè (NVIDIA)
    • 20:00
      Social dinner
    • Sessione di venerdi'
      • 36
        Programming GPUs with OpenCL: Kernel programs
        Speaker: Dr Tim Mattson (Intel)
      • 37
        Using GPUs with other programming models
        Speaker: Dr Tim Mattson (Intel)
        Slides
      • 10:00
        Coffee break Bertinoro

        Bertinoro

      • 38
        GPGPU epilog
        Slides
      • 39
        Cluster Computing with MPI
        Speaker: Dr Tim Mattson (Intel)
        Slides
      • 40
        Consolidation
      • 13:00
        Lunch Bertinoro

        Bertinoro

      • 41
        The 10 core constructs every MPI programmer should know
        Speaker: Dr Tim Mattson (Intel)
      • 42
        Geometric decomposition and MPI
        Speaker: Dr Tim Mattson (Intel)
      • 16:30
        Coffee break Bertinoro

        Bertinoro

      • 43
        Information
        Speaker: Mauro Morandin (PD)
      • 44
        Consolidation
      • 45
        Surviving the Red Queen’s Race: A guide for the perplexed programmer
        The Red Queen’s race is an important hypothesis in evolutionary biology raised to explain the impact of competition on the rate of evolution. I submit that it is an excellent analogy for the hardware chaos we are now facing. The question is, what can programmers do to survive as the hardware literally changes underneath them? In this talk we will look at trends in hardware and explore some of the approaches being used by software developers to cope.
        Speaker: Dr Tim Mattson (Intel)
        Slides
      • 19:30
        Guitar Cocktail Piazza Libertà 8 (Bar La Colonna)

        Piazza Libertà 8

        Bar La Colonna

    • 20:30
      Dinner Via Roma 29 (Osteria della Serafina)

      Via Roma 29

      Osteria della Serafina

    • Session 9
      • 46
        Students feedback
      • 47
        Final examination
      • 11:00
        Coffee break
      • 48
        Delivery of certificates of attendance
      • 12:00
        Lunch
      • 49
        Shuttle departure (to Forli' railway station)