Fast compiler optimisation evaluation using code-feature based performance prediction

Performance tuning is an important and time consuming task which may have to be repeated for each new application and platform. Although iterative optimisation can automate this process, it still requires many executions of dierent versions of the program. As execution time is frequently the limiting factor in the number of versions or transformed programs that can be considered, what is needed is a mechanism that can automatically predict the performance of a modied program without actually having to run it. This paper presents a new machine learning based technique to automatically predict the speedup of a modied program using a performance model based on the code features of the tuned programs. Unlike previous approaches it does not require any prior learning over a benchmark suite. Furthermore, it can be used to predict the performance of any tuning and is not restricted to a prior seen transformation space. We show that it can deliver predictions with a high correlation coecient ...

• Type: Conference
• Year: 2007
• Where: CF
• Authors: Christophe Dubach, John Cavazos, Björn Franke, Grigori Fursin, Michael F. P. O'Boyle, Olivier Temam
• Keywords: Applied Computing, CF 2007, Machine Learning, Modied Program, Performance