Performance of a massively parallel higher-order method of moments code using thousands of CPUs and its applications

Yu Zhang; Zhongchao Lin; Xunwang Zhao; Tapan K. Sarkar

doi:10.1109/TAP.2014.2361135

Performance of a massively parallel higher-order method of moments code using thousands of CPUs and its applications

Yu Zhang, Zhongchao Lin, Xunwang Zhao, Tapan K. Sarkar

Department of Electrical Engineering & Computer Science

Research output: Contribution to journal › Article › peer-review

29 Scopus citations

Abstract

The efficiency of a parallel higher-order method of moments is illustrated using up to 4096 CPU cores on a supercomputer. The scattering problems solved include the analysis from two full scale airplanes and the radiation problems include performance of a microstrip patch phased array antenna mounted on an airplane. Both the scattering and radiation problems are simulated to demonstrate the efficiency of the algorithm implementation. Numerical results show that one can achieve above 60% efficiency when the used memory to the total memory ratio is larger than 15%, and the time can reach a theoretical value between O(N²) and O(N³), where N is the number of unknowns. Due to its high efficiency, the algorithm is able to accurately solve large complex electromagnetic problems including composite and multiscale structures.

Original language	English (US)
Article number	6915702
Pages (from-to)	6317-6324
Number of pages	8
Journal	IEEE Transactions on Antennas and Propagation
Volume	62
Issue number	12
DOIs	https://doi.org/10.1109/TAP.2014.2361135
State	Published - Dec 1 2014

Keywords

Antenna radiation patterns
Moment methods
Parallel algorithms
Phased array
Scanning antennas

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.1109/TAP.2014.2361135

Cite this

@article{6947c130df88464aaf20e9b3b450c388,

title = "Performance of a massively parallel higher-order method of moments code using thousands of CPUs and its applications",

abstract = "The efficiency of a parallel higher-order method of moments is illustrated using up to 4096 CPU cores on a supercomputer. The scattering problems solved include the analysis from two full scale airplanes and the radiation problems include performance of a microstrip patch phased array antenna mounted on an airplane. Both the scattering and radiation problems are simulated to demonstrate the efficiency of the algorithm implementation. Numerical results show that one can achieve above 60% efficiency when the used memory to the total memory ratio is larger than 15%, and the time can reach a theoretical value between O(N2) and O(N3), where N is the number of unknowns. Due to its high efficiency, the algorithm is able to accurately solve large complex electromagnetic problems including composite and multiscale structures.",

keywords = "Antenna radiation patterns, Moment methods, Parallel algorithms, Phased array, Scanning antennas",

author = "Yu Zhang and Zhongchao Lin and Xunwang Zhao and Sarkar, {Tapan K.}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.",

year = "2014",

month = dec,

day = "1",

doi = "10.1109/TAP.2014.2361135",

language = "English (US)",

volume = "62",

pages = "6317--6324",

journal = "IEEE Transactions on Antennas and Propagation",

issn = "0018-926X",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "12",

}

TY - JOUR

T1 - Performance of a massively parallel higher-order method of moments code using thousands of CPUs and its applications

AU - Zhang, Yu

AU - Lin, Zhongchao

AU - Zhao, Xunwang

AU - Sarkar, Tapan K.

PY - 2014/12/1

Y1 - 2014/12/1

N2 - The efficiency of a parallel higher-order method of moments is illustrated using up to 4096 CPU cores on a supercomputer. The scattering problems solved include the analysis from two full scale airplanes and the radiation problems include performance of a microstrip patch phased array antenna mounted on an airplane. Both the scattering and radiation problems are simulated to demonstrate the efficiency of the algorithm implementation. Numerical results show that one can achieve above 60% efficiency when the used memory to the total memory ratio is larger than 15%, and the time can reach a theoretical value between O(N2) and O(N3), where N is the number of unknowns. Due to its high efficiency, the algorithm is able to accurately solve large complex electromagnetic problems including composite and multiscale structures.

AB - The efficiency of a parallel higher-order method of moments is illustrated using up to 4096 CPU cores on a supercomputer. The scattering problems solved include the analysis from two full scale airplanes and the radiation problems include performance of a microstrip patch phased array antenna mounted on an airplane. Both the scattering and radiation problems are simulated to demonstrate the efficiency of the algorithm implementation. Numerical results show that one can achieve above 60% efficiency when the used memory to the total memory ratio is larger than 15%, and the time can reach a theoretical value between O(N2) and O(N3), where N is the number of unknowns. Due to its high efficiency, the algorithm is able to accurately solve large complex electromagnetic problems including composite and multiscale structures.

KW - Antenna radiation patterns

KW - Moment methods

KW - Parallel algorithms

KW - Phased array

KW - Scanning antennas

UR - http://www.scopus.com/inward/record.url?scp=84913584092&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84913584092&partnerID=8YFLogxK

U2 - 10.1109/TAP.2014.2361135

DO - 10.1109/TAP.2014.2361135

M3 - Article

AN - SCOPUS:84913584092

SN - 0018-926X

VL - 62

SP - 6317

EP - 6324

JO - IEEE Transactions on Antennas and Propagation

JF - IEEE Transactions on Antennas and Propagation

IS - 12

M1 - 6915702

ER -

Performance of a massively parallel higher-order method of moments code using thousands of CPUs and its applications

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this