GPU Computing (CUDA2)

Programming, Programming - other

This course introduces GPU computing on NVIDIA graphics cards, covering GPU hardware, architecture and the design of parallel algorithms. It presents practical use of CUDA, OpenCL and OpenACC, and performance considerations for real applications.

The course is theory-focused, emphasizing GPU procedures, best practices and optimization patterns. Topics include synchronization, matrix multiplication, textures, CUDA-specific features, libraries and profiling. Delivered in Czech or English with partner Sprinx Systems.

THIS TRAINING COURSE WILL HELP YOU:

  • Understand CUDA, OpenCL and OpenACC concepts
  • Design and implement parallel algorithms for GPUs
  • Apply GPU optimization patterns and best practices
  • Use profiling tools and CUDA libraries for tuning

WHO SHOULD ATTEND?

  • Software developers working on compute-intensive code
  • HPC and scientific computing engineers
  • Algorithm designers and performance engineers
  • Anyone planning to optimize apps for NVIDIA GPUs

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
  • CUDA memory types
  • CUDA kernels
  • CUDA compute capabilities
  • Basic techniques and best practices
  • Synchronization
  • Matrix multiplication
  • Textures in CUDA
  • CUDA-specific features
  • Profiling in CUDA
  • Libraries for CUDA
  • CUDA and programming languages
Prerequisites:
Basic programming skills in a structured programming language.
Recommended previous course:
Introduction to CUDA (CUDA1)
Recommended follow-up course:
GPU Computing – Practical Lab (CUDA3)
Schedule:
2 days (9:00-17:00)
Training Partner:
Sprinx Systems

Training and learning environment