%0 Conference Paper
%A Baumeister, P. F.
%A Rombach, B.
%A Hater, Thorsten
%A Griessbach, S.
%A Hoffmann, L.
%A Bühler, M.
%A Pleiter, D.
%T Strategies for Forward Modelling of Infrared Radiative Transfer on GPUs
%V 32
%C Amsterdam
%I IOS Press
%M FZJ-2018-02040
%B Advances in Parallel Computing
%P 369 - 380
%D 2018
%< Parallel Computing is Everywhere
%X Satellite-based remote sensing in the mid-infrared spectral region can deliver a wealth of information on pressure, temperature, clouds and aerosols, and trace gas concentrations in the atmosphere. Interpreting the satellite measurements requires to solve an inverse modelling problem based on variational methods and a forward model evaluating the radiative transfer equations. As state-of-the-art satellite measurement campaigns require Petascale systems to process the data in due time, graphical processing units are employed for the high-throughput problem of computing the forward model for a given atmospheric state. We explore features of the considered architecture as well as relevant performance signatures of the different implementations to improve our understanding on opportunities for efficient exploitation of GPU-accelerated architectures based on the POWER2processor for this class of applications. Scalability is a key aspect as the application is known to scale well on massively-parallel architectures.
%B Parallel Computing
%C 12 Sep 2017 - 15 Sep 2017, Bologna (Italy)
Y2 12 Sep 2017 - 15 Sep 2017
M2 Bologna, Italy
%F PUB:(DE-HGF)8 ; PUB:(DE-HGF)7
%9 Contribution to a conference proceedingsContribution to a book
%R 10.3233/978-1-61499-843-3-369
%U https://juser.fz-juelich.de/record/844645