Events

Meluxina: Introduction to OpenACC programming

Luxinnovation Follow

Event
Business
Accounting
Education
Standard
Social networks
Information
Science
Programming
Data
Heritage
Management

tue. 19 Sep.

11h00-16h45

The Luxembourg SuperComputing Competence Center is hosting an online introduction to GPU programming with an OpenACC programming course for half a day. The first part will be dedicated to theory, and the second will focus on hands-on challenges on the MeluXina supercomputer GPU accelerators.
For whom?
Both current or prospective users of large hybrid CPU/GPU clusters and supercomputers, who might develop or accelerate their scientific computing applications using Nvidia GPUs, are encouraged to participate!
What will you learn and how?
Participants from this course will learn GPU programming using the OpenACC programming model, such as compute constructs, loop constructs and data clauses. Furthermore, understanding the GPU architecture and how parallel threads blocks are created and used to parallelise the computational task. Moreover, GPU is an accelerator; hence, there must be a good understanding of memory management between the GPU and CPU, which will also be discussed in detail. Finally, participants will also learn to use the OpenACC programming model to accelerate linear algebra (routines) and iterative solvers on the GPU. Participants will learn theories first and implement the OpenACC programming model with mentors’ guidance later in the hands-on tutorial part.
Learning outcomes
After this course, participants will be able to:
Understanding the GPU architecture (and also the difference between GPU and CPU)

Streaming architecture
Threads blocks
Implement OpenACC programming model

Compute constructs
Loops constructs
Data clauses
Efficient handling of memory management

Host to Device
Unified memory
Apply the OpenACC programming knowledge to accelerate from science and engineering:

Iterative solvers from science and engineering
Vector multiplication, vector addition, etc.
Prerequisites
Priority will be given to users with good experience with C/C++ and/or FORTRAN. No GPU programming knowledge is required; however, knowing the OpenMP programming model is advantageous.