Besides their original purpose as graphical processing units, GPUs are increasingly deployed in applications that require high computational performance. Moreover, in the context of high performance computing (HPC) one is observing the trend to deploy general purpose GPUs in order to enable the transit from petascale computing to exascale computing. Nonetheless, programming and constructing such architectures remains significant challenge and often a significant bottlenecks for many companies due to its highly specialized nature.
After working for 4 years in the private sector, Jan Lemeire obtained his Doctorate degee in 2007 from Vrije Universiteit Brussel (VUB), Belgium. His PhD research was on applying data mining techniques (based on probabilistic graphical models) for the performance analysis of parallel applications.
Thereafter he continued his work as a part time professor and postdoctoral researcher around GPU computing, performance understanding and prediction, as well as data mining (causal structure learning, hidden state models of dynamic systems). He initiated several projects in these fields and is promoter of 5 doctoral students. He teaches several courses, such as Parallel Systems and Advanced Computer Architecture.
*Jan Lemeire's presentation at Creative Media Days: http://www.slideshare.net/iMinds/iminds-the-conference-jan-lemeire