Multi-GPU Development of a Neural Networks Based Reconstructor for Adaptive Optics
Joint Authors
de Cos Juez, Francisco Javier
Calvo-Rolle, José Luis
González-Gutiérrez, Carlos
Sánchez-Rodríguez, María Luisa
Source
Issue
Vol. 2018, Issue 2018 (31 Dec. 2018), pp.1-9, 9 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2018-03-28
Country of Publication
Egypt
No. of Pages
9
Main Subjects
Abstract EN
Aberrations introduced by the atmospheric turbulence in large telescopes are compensated using adaptive optics systems, where the use of deformable mirrors and multiple sensors relies on complex control systems.
Recently, the development of larger scales of telescopes as the E-ELT or TMT has created a computational challenge due to the increasing complexity of the new adaptive optics systems.
The Complex Atmospheric Reconstructor based on Machine Learning (CARMEN) is an algorithm based on artificial neural networks, designed to compensate the atmospheric turbulence.
During recent years, the use of GPUs has been proved to be a great solution to speed up the learning process of neural networks, and different frameworks have been created to ease their development.
The implementation of CARMEN in different Multi-GPU frameworks is presented in this paper, along with its development in a language originally developed for GPU, like CUDA.
This implementation offers the best response for all the presented cases, although its advantage of using more than one GPU occurs only in large networks.
American Psychological Association (APA)
González-Gutiérrez, Carlos& Sánchez-Rodríguez, María Luisa& Calvo-Rolle, José Luis& de Cos Juez, Francisco Javier. 2018. Multi-GPU Development of a Neural Networks Based Reconstructor for Adaptive Optics. Complexity،Vol. 2018, no. 2018, pp.1-9.
https://search.emarefa.net/detail/BIM-1134624
Modern Language Association (MLA)
González-Gutiérrez, Carlos…[et al.]. Multi-GPU Development of a Neural Networks Based Reconstructor for Adaptive Optics. Complexity No. 2018 (2018), pp.1-9.
https://search.emarefa.net/detail/BIM-1134624
American Medical Association (AMA)
González-Gutiérrez, Carlos& Sánchez-Rodríguez, María Luisa& Calvo-Rolle, José Luis& de Cos Juez, Francisco Javier. Multi-GPU Development of a Neural Networks Based Reconstructor for Adaptive Optics. Complexity. 2018. Vol. 2018, no. 2018, pp.1-9.
https://search.emarefa.net/detail/BIM-1134624
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1134624