AMD GPU architecture and application porting
In this workshop you will get an overview of the new AMD GPU architecture. We will discuss its performance, usability and programmability and with the assisted demos and hands-on exercises we provide you with the knowledge and tools to start working with your own code on AMD GPUs.
Unfortunately, this meeting will not take place due to the measures regarding the corona virus. We are investigating how and in what form we can still organize the meeting, online or later in the year. We will inform you as soon as we know more.
SURF likes to be close to our members and keeps abreast of new technologies that they use for research. This workshop aims to cultivate the interest in the new Advanced Micro Devices (AMD) GPU architecture and it's use.
This workshop is primarily aimed at application developers, HPC support for researchers and programmers who want to catch a glimpse of the new AMD GPU architectures.
The working language is English.
If you would like your application to be considered during the workshop, then please send the link of the online code repository to email@example.com.
- Knowledge of programming languages such as C / C ++ / Python or FORTRAN
- Basic experience with programming GPU devices
- Basic experience working with Linux-based server machines
Introduction to AMD GPU architecture and the software ecosystem
Hands-on Performance analysis for the GPU node
Experience with porting for the next generation of GPU architectures
Programming models and tools for porting applications on AMD GPUs
Hands-on part 1: Proof of concept applications
Hands-on part 2: Analysis and porting of selected user applications
Read more about the preventive measures that SURF is taking with regard to coronavirus / COVID-19.