SAR doppler center frequency parameters estimation parallel optimization based on multi-core ARM NEON technology

Shiwen Xing; Yizhuang Xie; Liang Chen; Bingyi Li

SAR doppler center frequency parameters estimation parallel optimization based on multi-core ARM NEON technology

Shiwen Xing
, Yizhuang Xie
, Liang Chen
, Bingyi Li

信息与电子学院

Beijing Institute of Technology

科研成果: 会议稿件 › 论文 › 同行评审

摘要

Obtaining Doppler center frequency parameters estimation (DCFPE) with low time consumption is a great challenge in synthetic aperture radar (SAR) imaging system. In order to get DCFPE in real time, this paper adopts three parallel acceleration implementation methods-SIMD parallelism, multi-issue parallelism and multi-core parallelism-according to the characteristics of DCFPE algorithm. To verify the efficiency of the proposed methods, the paper builds the ARM embedded Linux system on multi-core ARM Cortex-A9 platform and uses assembly programming language to implement DCFPE algorithm in a 16384*16384 64-bit SAR imaging process. The experiment shows that DCFPE can be accelerated by more than 50% on average with an acceptable accuracy of the result.

源语言	英语
出版状态	已出版 - 2017
活动	2017 International Conference on Radar Systems, Radar 2017 - Belfast, 英国期限: 23 10月 2017 → 26 10月 2017

会议

会议	2017 International Conference on Radar Systems, Radar 2017
国家/地区	英国
市	Belfast
时期	23/10/17 → 26/10/17

其它文件与链接

链接到 Scopus 的出版物

引用此

@conference{4b1686d3e82743e2b541e8cee5bc372d,

title = "SAR doppler center frequency parameters estimation parallel optimization based on multi-core ARM NEON technology",

abstract = "Obtaining Doppler center frequency parameters estimation (DCFPE) with low time consumption is a great challenge in synthetic aperture radar (SAR) imaging system. In order to get DCFPE in real time, this paper adopts three parallel acceleration implementation methods-SIMD parallelism, multi-issue parallelism and multi-core parallelism-according to the characteristics of DCFPE algorithm. To verify the efficiency of the proposed methods, the paper builds the ARM embedded Linux system on multi-core ARM Cortex-A9 platform and uses assembly programming language to implement DCFPE algorithm in a 16384*16384 64-bit SAR imaging process. The experiment shows that DCFPE can be accelerated by more than 50\% on average with an acceptable accuracy of the result.",

keywords = "ARM NEON, Doppler center frequency parameters estimation (DCFPE), Parallel optimization, SAR imaging",

author = "Shiwen Xing and Yizhuang Xie and Liang Chen and Bingyi Li",

note = "Publisher Copyright: {\textcopyright} 2017 Institution of Engineering and Technology. All rights reserved.; 2017 International Conference on Radar Systems, Radar 2017 ; Conference date: 23-10-2017 Through 26-10-2017",

year = "2017",

language = "English",

}

TY - CONF

T1 - SAR doppler center frequency parameters estimation parallel optimization based on multi-core ARM NEON technology

AU - Xing, Shiwen

AU - Xie, Yizhuang

AU - Chen, Liang

AU - Li, Bingyi

PY - 2017

Y1 - 2017

N2 - Obtaining Doppler center frequency parameters estimation (DCFPE) with low time consumption is a great challenge in synthetic aperture radar (SAR) imaging system. In order to get DCFPE in real time, this paper adopts three parallel acceleration implementation methods-SIMD parallelism, multi-issue parallelism and multi-core parallelism-according to the characteristics of DCFPE algorithm. To verify the efficiency of the proposed methods, the paper builds the ARM embedded Linux system on multi-core ARM Cortex-A9 platform and uses assembly programming language to implement DCFPE algorithm in a 16384*16384 64-bit SAR imaging process. The experiment shows that DCFPE can be accelerated by more than 50% on average with an acceptable accuracy of the result.

AB - Obtaining Doppler center frequency parameters estimation (DCFPE) with low time consumption is a great challenge in synthetic aperture radar (SAR) imaging system. In order to get DCFPE in real time, this paper adopts three parallel acceleration implementation methods-SIMD parallelism, multi-issue parallelism and multi-core parallelism-according to the characteristics of DCFPE algorithm. To verify the efficiency of the proposed methods, the paper builds the ARM embedded Linux system on multi-core ARM Cortex-A9 platform and uses assembly programming language to implement DCFPE algorithm in a 16384*16384 64-bit SAR imaging process. The experiment shows that DCFPE can be accelerated by more than 50% on average with an acceptable accuracy of the result.

KW - ARM NEON

KW - Doppler center frequency parameters estimation (DCFPE)

KW - Parallel optimization

KW - SAR imaging

UR - https://www.scopus.com/pages/publications/85048668209

M3 - Paper

AN - SCOPUS:85048668209

T2 - 2017 International Conference on Radar Systems, Radar 2017

Y2 - 23 October 2017 through 26 October 2017

ER -

SAR doppler center frequency parameters estimation parallel optimization based on multi-core ARM NEON technology

摘要

会议

其它文件与链接

学术指纹

引用此