TY  - CONF
AU  - Baumeister, P. F.
AU  - Rombach, B.
AU  - Hater, Thorsten
AU  - Griessbach, S.
AU  - Hoffmann, L.
AU  - Bühler, M.
AU  - Pleiter, D.
TI  - Strategies for Forward Modelling of Infrared Radiative Transfer on GPUs
VL  - 32
CY  - Amsterdam
PB  - IOS Press
M1  - FZJ-2018-02040
T2  - Advances in Parallel Computing
SP  - 369 - 380
PY  - 2018
AB  - 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.
T2  - Parallel Computing
CY  - 12 Sep 2017 - 15 Sep 2017, Bologna (Italy)
Y2  - 12 Sep 2017 - 15 Sep 2017
M2  - Bologna, Italy
LB  - PUB:(DE-HGF)8 ; PUB:(DE-HGF)7
DO  - DOI:10.3233/978-1-61499-843-3-369
UR  - https://juser.fz-juelich.de/record/844645
ER  -