Performance evaluation of SAR image reconstruction on CPUs and GPUs

Fisnik Kraja, Alin Murarasu, Georg Acher, Arndt Bode

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Future space applications will demand for architectures with High Performance Computing (HPC) capabilities. In this scope, on-board computer designers will have to select between different technologies and designs, the most reliable and most efficient ones in terms of performance and power consumption. In this paper, we investigate the behavior of an Image Reconstruction Algorithm on high performance multi-core CPUs and many-core GPUs. It turns out that SAR applications can profit much more from the architecture and the capabilities of many-core GPUs than from modern multi-core CPUs. We give some remarks on how these types of HPC components can be integrated on future space-based on-board computing platforms. Throughout the paper, we illustrate by comparison the advantages and disadvantages of using GPUs over CPUs for SAR Applications. Other than this, we explain the programming and parallelization paradigms applied to the SAR application to increase its performance and efficiency on CPUs and GPUs respectively.

Original languageEnglish
Title of host publication2012 IEEE Aerospace Conference
DOIs
StatePublished - 2012
Event2012 IEEE Aerospace Conference - Big Sky, MT, United States
Duration: 3 Mar 201210 Mar 2012

Publication series

NameIEEE Aerospace Conference Proceedings
ISSN (Print)1095-323X

Conference

Conference2012 IEEE Aerospace Conference
Country/TerritoryUnited States
CityBig Sky, MT
Period3/03/1210/03/12

Fingerprint

Dive into the research topics of 'Performance evaluation of SAR image reconstruction on CPUs and GPUs'. Together they form a unique fingerprint.

Cite this