%0 Conference Proceedings
%T Algorithms of the Combination of Compiler Optimization Options for Automatic Performance Tuning
%+ Universitas Gadjah Mada
%A Suprapto, .
%A Wardoyo, Retantyo
%Z Part 1: Information and Communication Technology- Eurasia Conference (ICT-EurAsia)
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 1st International Conference on Information and Communication Technology (ICT-EurAsia)
%C Yogyakarta, Indonesia
%Y David Hutchison
%Y Takeo Kanade
%Y Madhu Sudan
%Y Demetri Terzopoulos
%Y Doug Tygar
%Y Moshe Y. Vardi
%Y Gerhard Weikum
%Y Khabib Mustofa
%Y Erich J. Neuhold
%Y A Min Tjoa
%Y Edgar Weippl
%Y Ilsun You
%Y Josef Kittler
%Y Jon M. Kleinberg
%Y Friedemann Mattern
%Y John C. Mitchell
%Y Moni Naor
%Y Oscar Nierstrasz
%Y C. Pandu Rangan
%Y Bernhard Steffen
%I Springer
%3 Information and Communicatiaon Technology
%V LNCS-7804
%P 91-100
%8 2013-03-25
%D 2013
%R 10.1007/978-3-642-36818-9_10
%K Compiler optimization
%K optimization options
%K performance
%K orchestration algorithm
%K exhaustive search
%K batch elimination
%K iterative elimination
%K combined elimination
%K optimization space exploration
%K statistical selection
%Z Computer Science [cs]
%Z Humanities and Social Sciences/Library and information sciencesConference papers
%X It is very natural when people compile their programs, they would require a compiler that gives the best program performance. Even though today’s compiler have reached the point in which they provide the users a large number of options, however, because of the unavailability of program input data and insufficient knowledge of the target architecture; it can still seriously limit the accuracy of compile-time performance models. Thus, the problem is how to choose the best combination of optimization options provided by compiler for a given program or program section. This gives rise the requirement of an orchestration algorithm that fast and effective to search for the best optimization combination for a program.There have been several algorithms developed, such as Exhaustive Search (ES); Batch Elimination (BE); Iterative Elimination (IE); Combined Elimination (CE); Optimization Space Exploration (OSE); and Statistical Selection (SS). Based on those of algorithms, in this paper we proposed Heuristics Elimination (HE) algorithm, a simple algorithm that was mostly inspired by OSE with some differences. The HE algorithm uses a heuristic approach by applying genetic algorithm to find the best combination of compiler’s optimization options. It is unlike OSE, however, this proposed algorithm starts from a set of some possible combinations randomly selected, then they are iteratively refined by some genetic operators to find one optimal combination (as the solution).
%G English
%Z TC 5
%Z TC 8
%2 https://inria.hal.science/hal-01480222/document
%2 https://inria.hal.science/hal-01480222/file/978-3-642-36818-9_10_Chapter.pdf
%L hal-01480222
%U https://inria.hal.science/hal-01480222
%~ SHS
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-TC5
%~ IFIP-TC8
%~ IFIP-ICT-EURASIA
%~ IFIP-LNCS-7804