Exportar Publicação

A publicação pode ser exportada nos seguintes formatos: referência da APA (American Psychological Association), referência do IEEE (Institute of Electrical and Electronics Engineers), BibTeX e RIS.

Exportar Referência (APA) 
Martins do Rosário, V. , Silva, A. F. Da, Camacho, T. A. S., Breternitz, M., Borin, E. & napoli, O. O. (2021). Smart selection of optimizations in dynamic compilers. Concurrency and Computation: Practice and Experience. 33 (18)
Exportar Referência (IEEE) 
V. M. Rosario et al.,  "Smart selection of optimizations in dynamic compilers", in Concurrency and Computation: Practice and Experience, vol. 33, no. 18, 2021
Exportar BibTeX 
@article{rosario2021_1775859516328,
	author = "Martins do Rosário, V.  and Silva, A. F. Da and Camacho, T. A. S. and Breternitz, M. and Borin, E. and napoli, O. O.",
	title = "Smart selection of optimizations in dynamic compilers",
	journal = "Concurrency and Computation: Practice and Experience",
	year = "2021",
	volume = "33",
	number = "18",
	doi = "10.1002/cpe.6089",
	url = "https://onlinelibrary.wiley.com/journal/15320634"
}
Exportar RIS 
TY  - JOUR
TI  - Smart selection of optimizations in dynamic compilers
T2  - Concurrency and Computation: Practice and Experience
VL  - 33
IS  - 18
AU  - Martins do Rosário, V. 
AU  - Silva, A. F. Da
AU  - Camacho, T. A. S.
AU  - Breternitz, M.
AU  - Borin, E.
AU  - napoli, O. O.
PY  - 2021
SN  - 1532-0626
DO  - 10.1002/cpe.6089
UR  - https://onlinelibrary.wiley.com/journal/15320634
AB  - Dynamic compilers perform compilation and generation of target code during runtime, implying that the compilation time is added into the program runtime. Thus, to build a high-performing dynamic compilation system, it is crucial to be able to generate high-quality code and, at the same time, have a small compilation cost. In this article, we present an approach that uses machine learning to select sequences of optimization for dynamic compilation that considers both code quality and compilation overhead. Our approach starts by training a model, offline, with a knowledge bank of those sequences with low overhead and high-quality code generation capability using a genetic heuristic. Then, this bank is used to guide the smart selection of optimizations sequences for the compilation of code fragments during the emulation of an application. We evaluate the proposed strategy in two LLVM-based dynamic binary translators, namely OI-DBT and HQEMU, and show that these two translators can achieve average speedups of 1.26x and 1.15x in MiBench and Spec Cpu benchmarks, respectively.
ER  -