Thesis supervisor: Tamás Kozsik
Location of studies (in Hungarian): ELTE Faculty of Informatics Abbreviation of location of studies: ELTE
Description of the research topic:
It is worthwhile to take advantage of the hierarchy of rapidly developing parallel architectures (vector instruction sets, graphical processors, many-core architectures, clusters) to solve computation-intensive tasks. However, effective implementation and optimization of algorithms for these tools is a task requiring advanced programming skills, which is often unavailable.
The candidate's task is to examine automated transformation and optimization of dense arithmetic tasks (such as linear algebraic calculations) on modern parallel hardware devices. The aim of the research is to create language tools and transformation rules that can deliver performance-critical tasks with reduced development time without significant loss in efficiency.
Required language skills: English Number of students who can be accepted: 2
Login
