GPU Based Quarter Spectral Correlation Density Function

Scott Marshall, Garrett Vanhoy, Ali Akoglu, Tamal Bose, Bo Ryu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this study we investigate the parallelization of a key feature extraction method called spectral correlation density (SCD) function, which is used in signal classification systems particularly under low signal-to-noise ratio conditions for classifying numerous signals. In order to reduce the computation complexity of the SCD function, we introduce a method called Quarter SCD (QSCD) that allows extracting features of a given signal by processing only quarter of the input signal data. We then parallelize the QSCD by targeting general purpose graphics processing unit (GPU) through architecture specific optimization strategies. We present experimental evaluations on identifying the parallelization configuration for maximizing the efficiency of the program architecture in utilizing the threading power of the GPU architecture. We show that algorithmic and architecture specific optimization strategies result with improving the throughput of the state of the art GPU based Full SCD from 120 signals/second to 2719 signals/second.

Original languageEnglish (US)
Title of host publication2018 Conference on Design and Architectures for Signal and Image Processing, DASIP 2018
PublisherIEEE Computer Society
Pages88-93
Number of pages6
ISBN (Electronic)9781538682371
DOIs
StatePublished - Dec 31 2018
Event12th Conference on Design and Architectures for Signal and Image Processing, DASIP 2018 - Porto, Portugal
Duration: Oct 10 2018Oct 12 2018

Publication series

NameConference on Design and Architectures for Signal and Image Processing, DASIP
Volume2018-October
ISSN (Print)2164-9766

Conference

Conference12th Conference on Design and Architectures for Signal and Image Processing, DASIP 2018
CountryPortugal
CityPorto
Period10/10/1810/12/18

Fingerprint

Probability density function
Feature extraction
Signal to noise ratio
Throughput
Processing
Graphics processing unit

Keywords

  • GPGPU
  • signal classification
  • spectral correlation density

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Marshall, S., Vanhoy, G., Akoglu, A., Bose, T., & Ryu, B. (2018). GPU Based Quarter Spectral Correlation Density Function. In 2018 Conference on Design and Architectures for Signal and Image Processing, DASIP 2018 (pp. 88-93). [8596977] (Conference on Design and Architectures for Signal and Image Processing, DASIP; Vol. 2018-October). IEEE Computer Society. https://doi.org/10.1109/DASIP.2018.8596977

GPU Based Quarter Spectral Correlation Density Function. / Marshall, Scott; Vanhoy, Garrett; Akoglu, Ali; Bose, Tamal; Ryu, Bo.

2018 Conference on Design and Architectures for Signal and Image Processing, DASIP 2018. IEEE Computer Society, 2018. p. 88-93 8596977 (Conference on Design and Architectures for Signal and Image Processing, DASIP; Vol. 2018-October).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Marshall, S, Vanhoy, G, Akoglu, A, Bose, T & Ryu, B 2018, GPU Based Quarter Spectral Correlation Density Function. in 2018 Conference on Design and Architectures for Signal and Image Processing, DASIP 2018., 8596977, Conference on Design and Architectures for Signal and Image Processing, DASIP, vol. 2018-October, IEEE Computer Society, pp. 88-93, 12th Conference on Design and Architectures for Signal and Image Processing, DASIP 2018, Porto, Portugal, 10/10/18. https://doi.org/10.1109/DASIP.2018.8596977
Marshall S, Vanhoy G, Akoglu A, Bose T, Ryu B. GPU Based Quarter Spectral Correlation Density Function. In 2018 Conference on Design and Architectures for Signal and Image Processing, DASIP 2018. IEEE Computer Society. 2018. p. 88-93. 8596977. (Conference on Design and Architectures for Signal and Image Processing, DASIP). https://doi.org/10.1109/DASIP.2018.8596977
Marshall, Scott ; Vanhoy, Garrett ; Akoglu, Ali ; Bose, Tamal ; Ryu, Bo. / GPU Based Quarter Spectral Correlation Density Function. 2018 Conference on Design and Architectures for Signal and Image Processing, DASIP 2018. IEEE Computer Society, 2018. pp. 88-93 (Conference on Design and Architectures for Signal and Image Processing, DASIP).
@inproceedings{f18896d15bf846538836d033d1179092,
title = "GPU Based Quarter Spectral Correlation Density Function",
abstract = "In this study we investigate the parallelization of a key feature extraction method called spectral correlation density (SCD) function, which is used in signal classification systems particularly under low signal-to-noise ratio conditions for classifying numerous signals. In order to reduce the computation complexity of the SCD function, we introduce a method called Quarter SCD (QSCD) that allows extracting features of a given signal by processing only quarter of the input signal data. We then parallelize the QSCD by targeting general purpose graphics processing unit (GPU) through architecture specific optimization strategies. We present experimental evaluations on identifying the parallelization configuration for maximizing the efficiency of the program architecture in utilizing the threading power of the GPU architecture. We show that algorithmic and architecture specific optimization strategies result with improving the throughput of the state of the art GPU based Full SCD from 120 signals/second to 2719 signals/second.",
keywords = "GPGPU, signal classification, spectral correlation density",
author = "Scott Marshall and Garrett Vanhoy and Ali Akoglu and Tamal Bose and Bo Ryu",
year = "2018",
month = "12",
day = "31",
doi = "10.1109/DASIP.2018.8596977",
language = "English (US)",
series = "Conference on Design and Architectures for Signal and Image Processing, DASIP",
publisher = "IEEE Computer Society",
pages = "88--93",
booktitle = "2018 Conference on Design and Architectures for Signal and Image Processing, DASIP 2018",

}

TY - GEN

T1 - GPU Based Quarter Spectral Correlation Density Function

AU - Marshall, Scott

AU - Vanhoy, Garrett

AU - Akoglu, Ali

AU - Bose, Tamal

AU - Ryu, Bo

PY - 2018/12/31

Y1 - 2018/12/31

N2 - In this study we investigate the parallelization of a key feature extraction method called spectral correlation density (SCD) function, which is used in signal classification systems particularly under low signal-to-noise ratio conditions for classifying numerous signals. In order to reduce the computation complexity of the SCD function, we introduce a method called Quarter SCD (QSCD) that allows extracting features of a given signal by processing only quarter of the input signal data. We then parallelize the QSCD by targeting general purpose graphics processing unit (GPU) through architecture specific optimization strategies. We present experimental evaluations on identifying the parallelization configuration for maximizing the efficiency of the program architecture in utilizing the threading power of the GPU architecture. We show that algorithmic and architecture specific optimization strategies result with improving the throughput of the state of the art GPU based Full SCD from 120 signals/second to 2719 signals/second.

AB - In this study we investigate the parallelization of a key feature extraction method called spectral correlation density (SCD) function, which is used in signal classification systems particularly under low signal-to-noise ratio conditions for classifying numerous signals. In order to reduce the computation complexity of the SCD function, we introduce a method called Quarter SCD (QSCD) that allows extracting features of a given signal by processing only quarter of the input signal data. We then parallelize the QSCD by targeting general purpose graphics processing unit (GPU) through architecture specific optimization strategies. We present experimental evaluations on identifying the parallelization configuration for maximizing the efficiency of the program architecture in utilizing the threading power of the GPU architecture. We show that algorithmic and architecture specific optimization strategies result with improving the throughput of the state of the art GPU based Full SCD from 120 signals/second to 2719 signals/second.

KW - GPGPU

KW - signal classification

KW - spectral correlation density

UR - http://www.scopus.com/inward/record.url?scp=85061378419&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061378419&partnerID=8YFLogxK

U2 - 10.1109/DASIP.2018.8596977

DO - 10.1109/DASIP.2018.8596977

M3 - Conference contribution

T3 - Conference on Design and Architectures for Signal and Image Processing, DASIP

SP - 88

EP - 93

BT - 2018 Conference on Design and Architectures for Signal and Image Processing, DASIP 2018

PB - IEEE Computer Society

ER -