GPU Computing – Practical Lab (CUDA3)

Programming, Programming - other

This practical course complements the prior theoretical training by focusing on hands-on use of CUDA for GPU programming. You will practice parallel algorithms, memory models and kernel design while learning performance-aware development and debugging techniques.

The lab is delivered in Czech or English and runs with industry partner Sprinx Systems, offering guided exercises on profiling, libraries and performance tuning. Emphasis is on practical debugging, optimization methods and real code examples for GPU workloads.

THIS TRAINING COURSE WILL HELP YOU:

  • Implement CUDA kernels and memory strategies
  • Develop and optimize parallel algorithms
  • Use CUDA profiling and debugging tools
  • Integrate CUDA libraries into projects

WHO SHOULD ATTEND?

  • Software developers working on high-performance code
  • Engineers needing GPU-accelerated computations
  • Researchers or students familiar with C/C++
  • Performance engineers and system architects

COURSE LOCATION AND AVAILABLE DATES



Public courses are usually delivered in Czech, but this course is also available in English. We can arrange private training for your team online, at your premises or in our classrooms, and tailor the content to your needs.

For groups of around 4 or more participants, private training can already be comparable in price to booking individual places on a public course. Send us your requirements and we’ll recommend the best format and provide an exact quote.

Request training in English

Course content:

Hide details
  • Introduction to CUDA technology
  • CUDA memory types
  • CUDA kernel programming
  • CUDA compute capabilities
  • Fundamental practices and principles
  • Synchronization
  • Matrix multiplication
  • Textures in CUDA
  • CUDA advanced features
  • Profiling in CUDA
  • CUDA libraries
  • CUDA and programming languages
Prerequisites:
Basic programming skills in a structured programming language.
Recommended previous course:
GPU Computing (CUDA2)
Recommended follow-up course:
OpenMP and MPI (CUDA4)
Schedule:
1 day (9:00-17:00)
Training Partner:
Sprinx Systems

Training and learning environment