Faculty of Information Technology, BUT

Publication Details

Branch Predictor On-line Evolutionary System

SLANÝ Karel. Branch Predictor On-line Evolutionary System. In: 2008 Genetic and Evolutionary Computation Conference GECCO. New York: Association for Computing Machinery, 2008, pp. 1643-1648. ISBN 978-1-60558-131-6.
Czech title
Systém predikce skoků založený na evoluci v reálném čase
Type
conference paper
Language
english
Authors
Slaný Karel, Ing. (DCSY FIT BUT)
Keywords
branch prediction, finite automata predictors

Abstract
In this work a branch prediction system which utilizes evolutionary techniques is introduced. It allows the predictor to adapt to the executed code and thus to improve its performance on the fly. Experiments with the predictor system were performed and the results display how various parameters can impact its performance on various executed code. It is evident that a one-level predictor can be evolved whose performance is better than comparable predictors of the same class. The dynamic prediction system predicts with a relative high accuracy and outperforms any static predictor of the same class.

Published
2008
Pages
1643-1648
Proceedings
2008 Genetic and Evolutionary Computation Conference GECCO
Conference
Genetic and Evolutionary Computation Conference, Atlanta, US
ISBN
978-1-60558-131-6
Publisher
Association for Computing Machinery
Place
New York, US
BibTeX
@INPROCEEDINGS{FITPUB8666,
   author = "Karel Slan\'{y}",
   title = "Branch Predictor On-line Evolutionary System",
   pages = "1643--1648",
   booktitle = "2008 Genetic and Evolutionary Computation Conference GECCO",
   year = 2008,
   location = "New York, US",
   publisher = "Association for Computing Machinery",
   ISBN = "978-1-60558-131-6",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/8666"
}
Files
Back to top