This course gives basic to intermediate level knowledge on HIP programming. It starts with a basic introduction to writing GPU applications using HIP. Then, building on this, more advanced topics are introduced. These enable one to write efficient HIP applications, including asynchronous execution with streams, utilizing performance tools and how to write efficient kernels. Finally multi-GPU programming and application designed will be discussed.

Learning outcome:

After the course, the participants will be able to write simple GPU programs, know how to analyse the performance of their GPU programs, and understand how to combine GPUs with MPI.

Prerequisites and content level:

No prior knowledge on GPGPU programming or HIP is required, but the participants are assumed to have a working knowledge of the C++ (or C) programming language and to be familiar with MPI.

The content level of the course is broken down as: beginner's - 0%, intermediate - 60%, advanced - 40%, community-targeted content - 0%.

The event is organised at the CSC Training Facilities located in the premises of CSC at Keilaranta 14, Espoo, Finland. 

Agenda (tentative)

Day 1, Thursday 10.11, 9:00-16:00

• Introduction to GPUs and GPU programming
• Kernels, synchronisation, streams
• Memory allocation/access, unified memory

Day 2, Friday 11.11, 9:00-16:00

• Fortran and HIP
• Kernel optimisation, profiling, and libraries
• Multi-GPU programming
• Application Design

Lecturers: Cristian-Vasile Achim (CSC), Jaro Hokkanen (CSC)

Language: English

This event is ON-PREMISE and the participation is limited to 24. The registration is at a first come, first served basis and it closes on November 3 at 23:59!