One Computer Science MSc thesis to be presented on 14 March

Friday, 14 March there will be a master thesis presentation in Computer Science at Lund University, Faculty of Engineering.

The presentation will take place in E:2116.

Note to potential opponents: Register as an opponent to the presentation of your choice by sending an email to the examiner for that presentation (firstname.lastname@cs.lth.se). Do not forget to specify the presentation you register for! Note that the number of opponents may be limited (often to two), so you might be forced to choose another presentation if you register too late. Registrations are individual, just as the oppositions are! More instructions are found on this page.

09:15-10:00 in E:2116

Presenter: Emma Jansson
Title: Enabling Profile Guided Optimizations (PGO) for Graphics
Examiner: Christoph Reichenbach
Supervisors: Jonas Skeppstedt (LTH), Tobias Gutzmann (Arm Sweden AB)

This master thesis presents an implementation for enabling profile-guided optimizatins (PGO) for mobile phone GPUs. The implementation adapts LLVM's existing PGO infrastructure to serve the architectural differences between CPUs and GPUs.

By analyzing how PGO functions in LLVM/Clang for CPUs, needed adaptations were identified to fit the GPU architecture. A major difference include GPUs not being able to allocate their own memory, requiring modifications to where profile counters and function data are stored. For this, a new compiler pass have been developed to collect function data, while the GPU driver handles storing of profile counters, and writes the profile data file that is given back to the compiler.

Evaluation of exposing the collected PGO data to existing compiler passes shows valuable performance improvements, with up to 3.74% fewer clock cycles and 6.32% fewer message instructions between threads. This proves that enabling PGO for graphics can lead to better performing GPUs.

Link to popular science summary: To be uploaded