Developing novel design methodologies for both individual processors and whole computing systems.
Research topics
High-level GPU Programming
To exploit the performance potential of massively parallel accelerators like GPUs, expert programmers need to tune their code in low-level languages like OpenCL or Cuda C for the parameters and features of specific GPU platforms and models. This hampers the use of those accelerators by non-GPU experts, as is needed in the domains of artificial intelligence, machine vision, and big data. We focus on the high-level programming language Julia. We build on its meta-programming, just-in-time compilation and strong type inference capabilities, and we redesign, extend and open up compiler interfaces such that the existing JULIA compiler infrastructure and code can be reused as much as possible while still mapping compute kernels into efficient GPU code. The results is code that is equally efficient as Cuda C code, that can be written with an order of magnitude less effort, and does not need to be retuned for specific GPU models.
CGRA: Compiler Techniques for Coarse-Grained Reconfigurable Arrays
KIS: High-Performance Embedded Systems
FLEXWARE: Hardware acceleration of massively parallel applications by exploiting flexible parallel hardware platforms
HOME-MATE: Home-compatible Multimodal Alarm Triggering for Epilepsy
English
Dutch
English
Cookie settings
Ghent University uses cookies on this website. The strictly necessary cookies are required for the proper functioning of the website and cannot be refused. Besides these necessary cookies, Ghent University also uses non-functional cookies such as statistical cookies (CrazyEgg analysis tool, Google, Hotjar, Piwik Pro) and social media cookies (YouTube, Facebook, TikTok). Those non-functional cookies may also be set by third parties, for example to measure site usage or share content on social media. Certain media are only available if you accept the cookies. You can always withdraw your consent via the "Cookie settings" link at the bottom of the webpage. You can read which cookies we use and why in the Cookie Statement.
We will store data in an aggregated form about visitors and their experiences on our website. We use this data to fix bugs and improve the experience for all visitors.
Conversion tracking
We will store data about when you complete certain actions on our website to understand better how you use it. We use this data to improve your experience with our site.
Social media cookies
We will store data to show you our advertisements (only ours) on other websites relevant to your interests.
