20 September 2011 Massively parallelizing the CIMSS IASI radiative transfer model on GPUs
Author Affiliations +
Abstract
We have developep a Graphics Processing Unit (GPU)-based high-performance radiative transfer model (RTM) for the Infrared Atmospheric Sounding Interferometer (IASI). We propose two different types of GPU RTMs. The first one, processes one profile at a time. The second proposed GPU RTM processes more than one profile at a time in order to gain a significant speedup compared to the case of processing one profile at a time. Using single-profile processing, we reached 364x speedup for 1 GPU and 1455x speedup for all 4 GPUs. Both with respect to the original CPU-based single-threaded Fortran code. Similarly, using multi-profile processing, to compute 10 IASI radiance spectra simultaneously on a GPU, we reached 756x speedup for 1 GPU and 3024x speedup for all 4 GPUs. The significant 3024x speedup means that the proposed GPU-based high-performance forward model is able to compute one day's amount of 1,296,000 IASI spectra within 6 minutes.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jarno Mielikainen, Bormin Huang, Allen H.-L. Huang, "Massively parallelizing the CIMSS IASI radiative transfer model on GPUs", Proc. SPIE 8157, Satellite Data Compression, Communications, and Processing VII, 81570G (20 September 2011); doi: 10.1117/12.895302; https://doi.org/10.1117/12.895302
PROCEEDINGS
7 PAGES


SHARE
Back to Top