GSGP-CUDA: A CUDA framework for Geometric Semantic Genetic Programming

Trujillo, L., Muñoz Contreras, J. M., Hernandez, D. E., Castelli, M., & Tapia, J. J. (2022). GSGP-CUDA — A CUDA framework for Geometric Semantic Genetic Programming. SoftwareX, 18, 1-7. [101085]. https://doi.org/10.1016/j.softx.2022.101085 -------------------------------Funding Information: We thank Perla Juárez-Smith for her help implementing some of the source code used in this software. We also thank the Tecnológico Nacional de México/IT de Tijuana and CITEDI-IPN for their administrative and technical assistance in the development of this work. This research was partially supported by national funds through FCT (Fundação para a Ciência e a Tecnologia), Portugal by the projects GADgET ( DSAIPA/DS/0022/2018 ) and AICE ( DSAIPA/DS/0113/2019 ). Mauro Castelli acknowledges the financial support from the Slovenian Research Agency (research core funding No. P5-0410 ). Funding for this work was also provided by TecNM (Mexico) 2020 through the research project “Resolución de múltiples problemas de aprendizaje supervisado de manera simultánea con programación genética”.Geometric Semantic Genetic Programming (GSGP) is a state-of-the-art machine learning method based on evolutionary computation. GSGP performs search operations directly at the level of program semantics, which can be done more efficiently than operating at the syntax level like most GP systems. Efficient implementations of GSGP in C++ exploit this fact, but not to its full potential. This paper presents GSGP-CUDA, the first CUDA implementation of GSGP and the most efficient, which exploits the intrinsic parallelism of GSGP using GPUs. Results show speedups greater than 1, 000× relative to the state-of-the-art sequential implementation, during the model training process. Additionally, our implementation allows the user to seamlessly make inferences over new data through the best evolved model, opening the possibility of using GSGP on Big Data problems.publishersversionpublishe