Application of Parallel Processing Techniques to Satellite Ocean Color Data Processing

Jae-Moo Heo^*, Hyun Yang^**, Young-Je Park^***, Hee-Jeong Han^****

^*First author, Researcher at National Institute of Environmental Research, Korea, jaemoo@korea.kr

^**Senior Research Scientist at Korea Ocean Satellite Center, Korea Institute of Ocean Science and Technology, Korea, yanghyun@kiost.ac.kr

^***Principal Research Scientist at Korea Ocean Satellite Center, Korea Institute of Ocean Science and Technology, Korea, youngjepark@kiost.ac.kr

^****Corresponding author, Principal research specialist at Korea Ocean Satellite Center, Korea Institute of Ocean Science and Technology, Korea, han77@kiost.ac.kr

© Copyright 2021 Korea Maritime Institute. This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Received: Oct 30, 2020; Revised: Nov 21, 2020; Accepted: Dec 20, 2020

Published Online: Dec 31, 2020

ABSTRACT

Recent advances demand that remote-sensing satellites efficiently process massive amounts of ocean color data. This paper compares the open multi-processing (OpenMP), the open computing language (OpenCL), the Message Passing Interface (MPI), the hybrid MPI/OpenMP, and the hybrid MPI/OpenCL in the parallel implementation of ocean color processing algorithms using data from the Geostationary Ocean Color Imager (GOCI), which is the first ocean color remote sensor operated in geostationary orbit. Since 2010, GOCI has observed ocean color around the Korean Peninsula and has generated hundreds of terabytes of big data. When any of the data-processing algorithms are updated, all preexisting data is required to be reprocessed, which can take hundreds of days because GOCI data are currently processed sequentially. Therefore, we attempted to develop an efficient parallel processing methodology for GOCI data. We tested well-known GOCI data-processing algorithms, like the chlorophyll (CHL) and total suspended solid (TSS) concentration estimation algorithms, using a cluster system. This cluster uses the Red Hat Linux operating system with two Intel Xeon 8-core processors (CPU), an AMD Radeon HD 7970 (GPU), and InfiniBand 4x QDR (network). As a result of this study we were able to improve the GOCI ocean color algorithms' processing speeds for OpenMP, OpenCL, MPI, hybrid MPI/OpenMP, and hybrid MPI/OpenCL by 3.92, 2.56, 2.51 3.27, and 2.05 times, respectively, than that of when we run the data sequentially. Moreover, we confirmed that the OpenMP programming model is the most useful for real-time processing GOCI data, which involves large amounts of input data and relatively simple formulas. Also, the vast number of computational nodes helps reduce the time taken to reprocess all data.

Keywords: OpenMP; OpenCL; MPI; GOCI; parallel programming; ocean color data processing; satellite; big data