Share Email Print
cover

Proceedings Paper

Massively parallelizing the CIMSS IASI radiative transfer model on GPUs
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper 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.

Paper Details

Date Published: 21 September 2011
PDF: 7 pages
Proc. SPIE 8157, Satellite Data Compression, Communications, and Processing VII, 81570G (21 September 2011); doi: 10.1117/12.895302
Show Author Affiliations
Jarno Mielikainen, Univ. of Wisconsin-Madison (United States)
Bormin Huang, Univ. of Wisconsin-Madison (United States)
Allen H.-L. Huang, Univ. of Wisconsin-Madison (United States)


Published in SPIE Proceedings Vol. 8157:
Satellite Data Compression, Communications, and Processing VII
Bormin Huang; Antonio J. Plaza; Carole Thiebaut, Editor(s)

© SPIE. Terms of Use
Back to Top