The PhD defence and trial lecture are fully digital and streamed using Zoom. The host of the session will moderate the technicalities while the chair of the defence will moderate the disputation.
Ex auditorio questions: the chair of the defence will invite the audience to ask ex auditorio questions either written or oral. This can be requested by clicking 'Participants -> Raise hand'.
Trial lecture
June 22, 10.00 AM, Zoom
"Applications of machine learning in optimising compilers"
Main research findings
When it comes to human health and computing, time is important because life depends on it. Thus having applications that runs fast, very fast, is essential.
However creating optimized application for complex and powerful hardware is a difficult task that requires huge programming and thinking efforts from programmers and scientists.
In our work, we provide solutions to obtain high performance applied to human heart simulation using the most powerful hardware available while trying to lower the programming effort.
To do so, we have used disruptive programming style (PGAS, Partitioned Global Address Space) and we provide a way to predict obtainable performance.
Contact information to Department: Pernille Adine Nordby