A methodology to automatically optimize dynamic memory managers applying grammatical evolution

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@Article{RiscoMartin:2014:JSS,

• author = "Jose L. Risco-Martin and J. Manuel Colmenar and J. Ignacio Hidalgo and Juan Lanchares and Josefa Diaz",
• title = "A methodology to automatically optimize dynamic memory managers applying grammatical evolution",
• journal = "Journal of Systems and Software",
• volume = "91",
• pages = "109--123",
• year = "2014",
• ISSN = "0164-1212",
• DOI = "doi:10.1016/j.jss.2013.12.044",
• URL = "http://www.sciencedirect.com/science/article/pii/S016412121400017X",
• keywords = "genetic algorithms, genetic programming, grammatical evolution, genetic improvement, SBSE, garbage collection, Dynamic memory manager, DMM, Heap, malloc, free, Multi-objective optimisation",
• size = "15 pages",
• abstract = "Modern consumer devices must execute multimedia applications that exhibit high resource use. In order to efficiently execute these applications, the dynamic memory subsystem needs to be optimised. This complex task can be tackled in two complementary ways: optimising the application source code or designing custom dynamic memory management mechanisms. Currently, the first approach has been well established, and several automatic methodologies have been proposed. Regarding the second approach, software engineers often write custom dynamic memory managers from scratch, which is a difficult and error-prone work. This paper presents a novel way to automatically generate custom dynamic memory managers optimizing both performance and memory usage of the target application. The design space is pruned using grammatical evolution converging to the best dynamic memory manager implementation for the target application. Our methodology achieves important improvements (62.55percent and 30.62percent better on average in performance and memory usage, respectively) when its results are compared to five different general-purpose dynamic memory managers.",
• notes = "Critical components of hand written BNF grammar altered by memory block sizes and MaxSize extracted from PIN profile of application. Applications in C++ hmmer, deall, soplex, calculix, gcc/200, gcc/expr2, gcc/c-typeck and Perl split, diff, spamAssasin Aim replace human written customised garbage collectors HMM. Unclear how deals with more than 256 alternatives in BNF production rule. Compare with Kingsley Lee etc. JECO C++ source code.google.com/p/paba",

}

Genetic Programming entries for Jose L Risco-Martin J Manuel Colmenar Jose Ignacio Hidalgo Perez J Lanchares Josefa Diaz Alvarez

Citations