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.

Location, current course term

Contact us

Custom

Customized Training (date, location, content, duration)

The course:

Hide detail

• 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

Assumed knowledge:

Basic programming skills in a structured programming language.

Recommended previous course:

GPU Computing (CUDA2)

Recommended subsequent course:

OpenMP and MPI (CUDA4)

Schedule:

1 day (9:00 AM - 5:00 PM )

Education Partner:

Sprinx Systems

Language: