Spherical interpolation over graphic processing units

Fei Ye; Xuan Shi; Shaowen Wang; Yan Liu; Su Yeon Han

doi:10.1145/2070770.2070777

Spherical interpolation over graphic processing units

Fei Ye, Xuan Shi, Shaowen Wang, Yan Liu, Su Yeon Han

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Spatial interpolation is a widely used GIS function for estimating values at locations where observed values are not available or adequate. One popular method for spatial interpolation is inverse distance weighted, which calculates estimated values based on a weighted sum of the values of a number of nearest neighbors that have observed values. This research focuses on solving a large-scale interpolation problem with a global coverage based on the inverse distance weighted method. Specifically, spherical distance is calculated instead of normal Euclidean distance commonly used in GIS software, which is necessary to find correct neighbors in the regions along the 180° longitude and in the polar areas. The computation of the global-scale interpolation based on spherical distance is intensive especially for achieving high-resolution results. This paper introduces how to accelerate such computation by exploiting massive parallelism provided by Graphic Processing Units (GPUs) with significant improvement of computational performance reported.

Original language	English (US)
Title of host publication	Proceedings of the ACM SIGSPATIAL 2nd International Workshop on High Performance and Distributed Geographic Information Systems, ACM SIGSPATIAL HPDGIS 2011
Pages	38-41
Number of pages	4
DOIs	https://doi.org/10.1145/2070770.2070777
State	Published - Dec 19 2011
Event	ACM SIGSPATIAL 2nd International Workshop on High Performance and Distributed Geographic Information Systems, ACM SIGSPATIAL HPDGIS 2011 - Chicago, IL, United States Duration: Nov 1 2011 → Nov 1 2011

Other

Other	ACM SIGSPATIAL 2nd International Workshop on High Performance and Distributed Geographic Information Systems, ACM SIGSPATIAL HPDGIS 2011
Country	United States
City	Chicago, IL
Period	11/1/11 → 11/1/11

Keywords

graphic processing units
high performance computing
inverse distance weighted
spatial interpolation

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Computer Networks and Communications
Information Systems

Access to Document

10.1145/2070770.2070777

Fingerprint Dive into the research topics of 'Spherical interpolation over graphic processing units'. Together they form a unique fingerprint.

Cite this

Spherical interpolation over graphic processing units. / Ye, Fei; Shi, Xuan; Wang, Shaowen; Liu, Yan; Han, Su Yeon.

Proceedings of the ACM SIGSPATIAL 2nd International Workshop on High Performance and Distributed Geographic Information Systems, ACM SIGSPATIAL HPDGIS 2011. 2011. p. 38-41.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Ye, F, Shi, X, Wang, S, Liu, Y & Han, SY 2011, Spherical interpolation over graphic processing units. in Proceedings of the ACM SIGSPATIAL 2nd International Workshop on High Performance and Distributed Geographic Information Systems, ACM SIGSPATIAL HPDGIS 2011. pp. 38-41, ACM SIGSPATIAL 2nd International Workshop on High Performance and Distributed Geographic Information Systems, ACM SIGSPATIAL HPDGIS 2011, Chicago, IL, United States, 11/1/11. https://doi.org/10.1145/2070770.2070777

@inproceedings{f65872b77595459a93fe2b1233093e4c,

title = "Spherical interpolation over graphic processing units",

abstract = "Spatial interpolation is a widely used GIS function for estimating values at locations where observed values are not available or adequate. One popular method for spatial interpolation is inverse distance weighted, which calculates estimated values based on a weighted sum of the values of a number of nearest neighbors that have observed values. This research focuses on solving a large-scale interpolation problem with a global coverage based on the inverse distance weighted method. Specifically, spherical distance is calculated instead of normal Euclidean distance commonly used in GIS software, which is necessary to find correct neighbors in the regions along the 180° longitude and in the polar areas. The computation of the global-scale interpolation based on spherical distance is intensive especially for achieving high-resolution results. This paper introduces how to accelerate such computation by exploiting massive parallelism provided by Graphic Processing Units (GPUs) with significant improvement of computational performance reported.",

keywords = "graphic processing units, high performance computing, inverse distance weighted, spatial interpolation",

author = "Fei Ye and Xuan Shi and Shaowen Wang and Yan Liu and Han, {Su Yeon}",

year = "2011",

month = dec,

day = "19",

doi = "10.1145/2070770.2070777",

language = "English (US)",

isbn = "9781450310406",

pages = "38--41",

booktitle = "Proceedings of the ACM SIGSPATIAL 2nd International Workshop on High Performance and Distributed Geographic Information Systems, ACM SIGSPATIAL HPDGIS 2011",

note = "ACM SIGSPATIAL 2nd International Workshop on High Performance and Distributed Geographic Information Systems, ACM SIGSPATIAL HPDGIS 2011 ; Conference date: 01-11-2011 Through 01-11-2011",

}

TY - GEN

T1 - Spherical interpolation over graphic processing units

AU - Ye, Fei

AU - Shi, Xuan

AU - Wang, Shaowen

AU - Liu, Yan

AU - Han, Su Yeon

PY - 2011/12/19

Y1 - 2011/12/19

N2 - Spatial interpolation is a widely used GIS function for estimating values at locations where observed values are not available or adequate. One popular method for spatial interpolation is inverse distance weighted, which calculates estimated values based on a weighted sum of the values of a number of nearest neighbors that have observed values. This research focuses on solving a large-scale interpolation problem with a global coverage based on the inverse distance weighted method. Specifically, spherical distance is calculated instead of normal Euclidean distance commonly used in GIS software, which is necessary to find correct neighbors in the regions along the 180° longitude and in the polar areas. The computation of the global-scale interpolation based on spherical distance is intensive especially for achieving high-resolution results. This paper introduces how to accelerate such computation by exploiting massive parallelism provided by Graphic Processing Units (GPUs) with significant improvement of computational performance reported.

AB - Spatial interpolation is a widely used GIS function for estimating values at locations where observed values are not available or adequate. One popular method for spatial interpolation is inverse distance weighted, which calculates estimated values based on a weighted sum of the values of a number of nearest neighbors that have observed values. This research focuses on solving a large-scale interpolation problem with a global coverage based on the inverse distance weighted method. Specifically, spherical distance is calculated instead of normal Euclidean distance commonly used in GIS software, which is necessary to find correct neighbors in the regions along the 180° longitude and in the polar areas. The computation of the global-scale interpolation based on spherical distance is intensive especially for achieving high-resolution results. This paper introduces how to accelerate such computation by exploiting massive parallelism provided by Graphic Processing Units (GPUs) with significant improvement of computational performance reported.

KW - graphic processing units

KW - high performance computing

KW - inverse distance weighted

KW - spatial interpolation

UR - http://www.scopus.com/inward/record.url?scp=83455177057&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=83455177057&partnerID=8YFLogxK

U2 - 10.1145/2070770.2070777

DO - 10.1145/2070770.2070777

M3 - Conference contribution

AN - SCOPUS:83455177057

SN - 9781450310406

SP - 38

EP - 41

BT - Proceedings of the ACM SIGSPATIAL 2nd International Workshop on High Performance and Distributed Geographic Information Systems, ACM SIGSPATIAL HPDGIS 2011

T2 - ACM SIGSPATIAL 2nd International Workshop on High Performance and Distributed Geographic Information Systems, ACM SIGSPATIAL HPDGIS 2011

Y2 - 1 November 2011 through 1 November 2011

ER -