The Use of Different Strategies of Search Space Reduction in Mitigation of Optimization Selection Problem
Nilton Queiroz Junior$^{1}$, Anderson Faustino da Silva$^{1}$
$^{1}$Universidade Estadual de Maringa. Maringá - PR Brazil
email: niltonlqjr@gmail.com, andersonfaustino@gmail.com

Schedule:Mon 19th@18:15, Room: D

Compiler optimizations are transformations that are applied on the source code to improve its performance. Many times its a complex task to choose which optimizations set must be used, so, usually there are chosen optimization levels given by the compiler. However, these optimization levels are not always good enough for all programs. Thus, it is needed to search for sets to improve specific programs. Currently the Best10 algorithm is one of the best algorithms to mitigate the optimizations selection problem. This algorithm requires one reduced search space to infer which are the optimization sets that must be applied during the compilation of programs. This work presents the impact of the use of different search space creation strategies used by the Best10 algorithm. The results shows that sophisticated strategies do not always provide the best results.

BibTex

@InProceedings{CLEI-2015:144453,
	author 		= {Nilton Queiroz Junior and Anderson Faustino da Silva},
	title 		= {The Use of Different Strategies of Search Space Reduction in Mitigation of Optimization Selection Problem},
	booktitle 	= {2015 XLI Latin American Computing Conference (CLEI)},
	pages 		= {181--192},
	year 		= {2015},
	editor 		= {Hector Cancela and Alex Cuadros-Vargas and Ernesto Cuadros-Vargas},
	address 	= {Arequipa-Peru},
	month 		= {October},
	organization 	= {CLEI},
	publisher 	= {CLEI},
	url 		= {http://clei.org/clei2015/144453},
	isbn 		= {978-1-4673-9143-6},
	}