MeluXina: Introduction to GPU Programming Using OpenACC

21 April 2026 - Online

Register now
The Luxembourg SuperComputing Competence Center will host a half-day online course introducing OpenACC for Heterogeneous Computing. The course will be divided into two parts: the first will cover theoretical concepts, while the second will focus on practical, hands-on challenges using the MeluXina supercomputer.

About the  Event

📅 21 April 2026
🕙 from 1:00 PM to 5:00 PM 

📢  Important: Limited spots!
Who should attend?
This course is ideal for current and prospective users of large hybrid CPU/GPU clusters and supercomputers who develop or parallelize scientific computing applications leveraging the power of GPUs. 

What will you learn and how?
Participants in this course will learn GPU programming using the OpenACC programming model, covering the following:
  • Compute constructs, loop constructs, and data clauses. 
  • GPU architecture and how parallel thread blocks are created and used to parallelize computational tasks. 
  • Memory management between the GPU and CPU, with a detailed discussion on best practices. 
  • Accelerating linear algebra routines and iterative solvers using the OpenACC programming model. 
The course includes theoretical lessons followed by hands-on sessions guided by experienced mentors.

Learning outcomes
By the end of the course, participants will be able to: 

      1.  Understand GPU Architecture 
                  - Learn the differences between GPUs and CPUs
                  - Grasp concepts such as streaming architecture and thread blocks

      2.  Implement the OpenACC Programming Model 
                  - Apply compute constructs, loop constructs, and data clauses

      3.  Efficiently Handle Memory Management 
                  - Manage host-to-device and device-to-host memory transfers
                  - Utilize unified memory

      4.  Apply OpenACC Programming Knowledge 
                  - Accelerate examples from science and engineering
                  - Work on tasks such as iterative solvers, vector multiplication, and vector addition

Prerequisites 
Priority will be given to participants with experience in C/C++ or FORTRAN. No prior GPU programming knowledge is required, but familiarity with the OpenMP programming model is advantageous.

GPU Compute Resource 
Participants will be granted access to the MeluXina supercomputer during the session. For more information about MeluXina, please refer to the MeluXina overview and the MeluXina Getting Started Guide.

Agenda


This half-day course will be conducted online in Central European Time (CET). All communication will take place via Zoom, Slack, and email. 

Schedule 
- 1:00 PM – 1:45 PM: Lecture Part 1 
- 1:45 PM – 2:00 PM: Break 
- 2:00 PM – 2:45 PM: Lecture Part 2 
- 2:45 PM – 3:00 PM: Break 
- 3:00 PM – 4:45 PM: Hands-on Lab 
- 4:45 PM – 5:00 PM: Q&A 

Date: April 21st, 2026 - 1:00 PM – 5:00 PM CET 
Important: Limited spots available!

Contact person for more information
Ezhilmathi KRISHNASAMY
ezhilmathi.krishnasamy@uni.lu

Initiated and managed by

component teaserparticipants not found

component teasercontacts not found