GA-Based Compiler Parameter Set Tuning

Determining nearly optimal optimization options for modern-day compilers is a combinatorial problem. Added to this, specific to a given application, platform and optimization objective, fine-tuning the parameter set being used by various optimization passes, enhance the complexity further. In this paper, we apply genetic algorithm (GA) to tune compiler parameter set and investigate the impact of fine-tuning the parameter set on the code size. The effectiveness of GA-based parameter tuning mechanism is demonstrated with the benchmark programs from SPEC2006 benchmark suite that there is a significant impact of tuning the parameter values on the code size. Results obtained by the proposed GA-based parameter tuning technique are compared with existing methods and that shows significant performance gains.

[1]  David Black-Schaffer,et al.  Computing systems: research challenges ahead: the HiPEAC Vision 2011/ 2012 , 2011 .

[2]  Michael F. P. O'Boyle,et al.  Method-specific dynamic compilation using logistic regression , 2006, OOPSLA '06.

[3]  Rajeev Wankar,et al.  Tuning the Optimization Parameter Set for Code Size , 2012, MIWAI.

[4]  Peter M. W. Knijnenburg,et al.  Automatic selection of compiler options using non-parametric inferential statistics , 2005, 14th International Conference on Parallel Architectures and Compilation Techniques (PACT'05).

[5]  Michael F. P. O'Boyle,et al.  Using machine learning to focus iterative optimization , 2006, International Symposium on Code Generation and Optimization (CGO'06).

[6]  Keith D. Cooper,et al.  Optimizing for reduced code space using genetic algorithms , 1999, LCTES '99.

[7]  Antonio Martínez-Álvarez,et al.  Multi-objective adaptive evolutionary strategy for tuning compilations , 2014, Neurocomputing.

[8]  Lothar Thiele,et al.  Multi-objective Exploration of Compiler Optimizations for Real-Time Systems , 2010, 2010 13th IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing.