[ONLINE] Performance Analysis of GPU enabled HPC applications @ IT4Innovations

Karina Pešatová (VŠB Technical University Ostrava, IT4Innovations)


Learn about multiple GPU programming models and choose the one that best fits your needs. This tutorial will cover an introduction to GPU programming using OpenACC, OpenMP, CUDA C. Throughout the tutorial, you will learn how to analyse GPU enabled applications using Nsight tools.


beginner, intermediate




Basic experience with C/C++ or Fortran. No GPU programming knowledge is required.
This event has limited capacity, so please make sure that prerequisites are met before applying. You will be receiving an acceptance email with details on how to participate by July 12, 2021.


Gunter Roth (NVIDIA), Giuseppe Fiameni (NVIDIA), Mozhgan Kabiri Chimeh (NVIDIA)

Radim Vavřík (IT4Innovations)



We thank NVIDIA for their support.

The tutorial is partially supported by The Ministry of Education, Youth and Sports from the Large Infrastructures for Research, Experimental Development and Innovations project “e-Infrastruktura CZ – LM2018140”, partially by the PRACE-6IP project - the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 823767.


    • 9:00 AM 9:15 AM
    • 9:15 AM 9:30 AM
      Connecting to a cluster
    • 9:30 AM 10:00 AM
      Introduction to GPU computing: Introduction to GPU computing (lecture)
    • 10:00 AM 11:45 AM
      Directive Based Programming with OpenMP and OpenACC on GPU (lecture and lab)
    • 11:45 AM 12:30 PM
      CUDA C Programming (lecture and lab)
    • 12:30 PM 1:30 PM
    • 1:30 PM 2:00 PM
      CUDA C Programming – continued (Lab)
    • 2:00 PM 4:00 PM
      Dive into Nsight Profiling tool (Lecture)

      Using Nsight System and Compute to profile HPC applications
      Using Nsight System to profile Deep learning applications

    • 9:00 AM 12:00 PM
      Challenge : hands on
    • 12:00 PM 12:30 PM
      Wrap up and QA