A Comparison Between CPU and GPU Computing in DNN-Based DoA Estimation

Georgios Kokkinis; Qasim Z. Ahmed; Alistair Sambell; Ioannis P. Chochliouros; Pavlos I. Lazaridis; Zaharias D. Zaharis

doi:10.1007/978-3-031-49421-5_64

A Comparison Between CPU and GPU Computing in DNN-Based DoA Estimation

Georgios Kokkinis, Qasim Z. Ahmed, Alistair Sambell, Ioannis P. Chochliouros, Pavlos I. Lazaridis, Zaharias D. Zaharis

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

Abstract

Deep Learning algorithms have recently become accessible to modern Telecommunication systems due to the advancement in both hardware and software technology. The massively parallel computational tasks of Artificial Intelligence (AI) training are now directly performed in Graphic Processing Units (GPUs), which contain many processing cores. This paper tests the improvement in computing time for Deep Neural Network (DNN) architectures that solve the Direction of Arrival (DoA) estimation problem as a classification task by utilizing the Nvidia CUDA framework. The training and testing data are generated by receiving signal information from a simulated antenna array. The input of the DNN is a 64 × 64 image with two channels, whereas the problem is modelled as a multi-label classification task. The purpose of this research is to observe the acceleration that the GPU provides in the DoA estimation classification problem. The project includes benchmarks from a wide range of computing systems and the results demonstrate the potential of DNN-based DoA estimators as a modern technology that can be deployed on available commercial hardware.

Original language	English
Title of host publication	Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences (UNIfied 2023) - Volume 2
Editors	Andrew D. Ball, Huajiang Ouyang, Jyoti K. Sinha, Zuolu Wang
Publisher	Springer, Cham
Pages	787-796
Number of pages	10
Volume	152
ISBN (Electronic)	9783031494215
ISBN (Print)	9783031494208, 9783031494239
DOIs	https://doi.org/10.1007/978-3-031-49421-5_64
Publication status	Published - 29 May 2024
Event	The UNIfied Conference of DAMAS, InCoME and TEPEN Conferences - Huddersfield, United Kingdom, Huddersfield, United Kingdom Duration: 29 Aug 2023 → 1 Sep 2023 https://unified2023.org/

Publication series

Name	Mechanisms and Machine Science
Publisher	Springer
Volume	152 MMS
ISSN (Print)	2211-0984
ISSN (Electronic)	2211-0992

Conference

Conference	The UNIfied Conference of DAMAS, InCoME and TEPEN Conferences
Abbreviated title	UNIfied 2023
Country/Territory	United Kingdom
City	Huddersfield
Period	29/08/23 → 1/09/23
Internet address	https://unified2023.org/

Access to Document

10.1007/978-3-031-49421-5_64Licence: Unspecified

Cite this

Kokkinis, G., Ahmed, Q. Z., Sambell, A., Chochliouros, I. P., Lazaridis, P. I., & Zaharis, Z. D. (2024). A Comparison Between CPU and GPU Computing in DNN-Based DoA Estimation. In A. D. Ball, H. Ouyang, J. K. Sinha, & Z. Wang (Eds.), Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences (UNIfied 2023) - Volume 2 (Vol. 152, pp. 787-796). (Mechanisms and Machine Science; Vol. 152 MMS). Springer, Cham. https://doi.org/10.1007/978-3-031-49421-5_64

Kokkinis, Georgios ; Ahmed, Qasim Z. ; Sambell, Alistair et al. / A Comparison Between CPU and GPU Computing in DNN-Based DoA Estimation. Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences (UNIfied 2023) - Volume 2. editor / Andrew D. Ball ; Huajiang Ouyang ; Jyoti K. Sinha ; Zuolu Wang. Vol. 152 Springer, Cham, 2024. pp. 787-796 (Mechanisms and Machine Science).

@inproceedings{d1b287e2e2bd42719155e0f48628f1c0,

title = "A Comparison Between CPU and GPU Computing in DNN-Based DoA Estimation",

abstract = "Deep Learning algorithms have recently become accessible to modern Telecommunication systems due to the advancement in both hardware and software technology. The massively parallel computational tasks of Artificial Intelligence (AI) training are now directly performed in Graphic Processing Units (GPUs), which contain many processing cores. This paper tests the improvement in computing time for Deep Neural Network (DNN) architectures that solve the Direction of Arrival (DoA) estimation problem as a classification task by utilizing the Nvidia CUDA framework. The training and testing data are generated by receiving signal information from a simulated antenna array. The input of the DNN is a 64 × 64 image with two channels, whereas the problem is modelled as a multi-label classification task. The purpose of this research is to observe the acceleration that the GPU provides in the DoA estimation classification problem. The project includes benchmarks from a wide range of computing systems and the results demonstrate the potential of DNN-based DoA estimators as a modern technology that can be deployed on available commercial hardware.",

keywords = "Deep Learning (DL), Direction-of-Arrival (DoA), Graphic Processing Unit (GPU), Parallel computing",

author = "Georgios Kokkinis and Ahmed, {Qasim Z.} and Alistair Sambell and Chochliouros, {Ioannis P.} and Lazaridis, {Pavlos I.} and Zaharis, {Zaharias D.}",

note = "Funding Information: This work was partially supported by the European Union through the Horizon 2020 Marie Sk\u0142odowska-Curie Research and Innovation Staff Exchange Programme \u201CResearch collaboration and mobility for beyond 5G future wireless networks (RECOMBINE)\u201D under Grant no. 872857. Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.; The UNIfied Conference of DAMAS, InCoME and TEPEN Conferences, UNIfied 2023 ; Conference date: 29-08-2023 Through 01-09-2023",

year = "2024",

month = may,

day = "29",

doi = "10.1007/978-3-031-49421-5_64",

language = "English",

isbn = "9783031494208",

volume = "152",

series = "Mechanisms and Machine Science",

publisher = "Springer, Cham",

pages = "787--796",

editor = "Ball, {Andrew D.} and Huajiang Ouyang and Sinha, {Jyoti K.} and Zuolu Wang",

booktitle = "Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences (UNIfied 2023) - Volume 2",

address = "Switzerland",

url = "https://unified2023.org/",

}

Kokkinis, G, Ahmed, QZ, Sambell, A, Chochliouros, IP, Lazaridis, PI & Zaharis, ZD 2024, A Comparison Between CPU and GPU Computing in DNN-Based DoA Estimation. in AD Ball, H Ouyang, JK Sinha & Z Wang (eds), Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences (UNIfied 2023) - Volume 2. vol. 152, Mechanisms and Machine Science, vol. 152 MMS, Springer, Cham, pp. 787-796, The UNIfied Conference of DAMAS, InCoME and TEPEN Conferences, Huddersfield, United Kingdom, 29/08/23. https://doi.org/10.1007/978-3-031-49421-5_64

A Comparison Between CPU and GPU Computing in DNN-Based DoA Estimation. / Kokkinis, Georgios; Ahmed, Qasim Z.; Sambell, Alistair et al.

Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences (UNIfied 2023) - Volume 2. ed. / Andrew D. Ball; Huajiang Ouyang; Jyoti K. Sinha; Zuolu Wang. Vol. 152 Springer, Cham, 2024. p. 787-796 (Mechanisms and Machine Science; Vol. 152 MMS).

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

TY - GEN

T1 - A Comparison Between CPU and GPU Computing in DNN-Based DoA Estimation

AU - Kokkinis, Georgios

AU - Ahmed, Qasim Z.

AU - Sambell, Alistair

AU - Chochliouros, Ioannis P.

AU - Lazaridis, Pavlos I.

AU - Zaharis, Zaharias D.

N1 - Funding Information: This work was partially supported by the European Union through the Horizon 2020 Marie Sk\u0142odowska-Curie Research and Innovation Staff Exchange Programme \u201CResearch collaboration and mobility for beyond 5G future wireless networks (RECOMBINE)\u201D under Grant no. 872857. Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

PY - 2024/5/29

Y1 - 2024/5/29

N2 - Deep Learning algorithms have recently become accessible to modern Telecommunication systems due to the advancement in both hardware and software technology. The massively parallel computational tasks of Artificial Intelligence (AI) training are now directly performed in Graphic Processing Units (GPUs), which contain many processing cores. This paper tests the improvement in computing time for Deep Neural Network (DNN) architectures that solve the Direction of Arrival (DoA) estimation problem as a classification task by utilizing the Nvidia CUDA framework. The training and testing data are generated by receiving signal information from a simulated antenna array. The input of the DNN is a 64 × 64 image with two channels, whereas the problem is modelled as a multi-label classification task. The purpose of this research is to observe the acceleration that the GPU provides in the DoA estimation classification problem. The project includes benchmarks from a wide range of computing systems and the results demonstrate the potential of DNN-based DoA estimators as a modern technology that can be deployed on available commercial hardware.

AB - Deep Learning algorithms have recently become accessible to modern Telecommunication systems due to the advancement in both hardware and software technology. The massively parallel computational tasks of Artificial Intelligence (AI) training are now directly performed in Graphic Processing Units (GPUs), which contain many processing cores. This paper tests the improvement in computing time for Deep Neural Network (DNN) architectures that solve the Direction of Arrival (DoA) estimation problem as a classification task by utilizing the Nvidia CUDA framework. The training and testing data are generated by receiving signal information from a simulated antenna array. The input of the DNN is a 64 × 64 image with two channels, whereas the problem is modelled as a multi-label classification task. The purpose of this research is to observe the acceleration that the GPU provides in the DoA estimation classification problem. The project includes benchmarks from a wide range of computing systems and the results demonstrate the potential of DNN-based DoA estimators as a modern technology that can be deployed on available commercial hardware.

KW - Deep Learning (DL)

KW - Direction-of-Arrival (DoA)

KW - Graphic Processing Unit (GPU)

KW - Parallel computing

UR - http://www.scopus.com/inward/record.url?scp=85195588122&partnerID=8YFLogxK

UR - https://doi.org/10.1007/978-3-031-49421-5

U2 - 10.1007/978-3-031-49421-5_64

DO - 10.1007/978-3-031-49421-5_64

M3 - Conference contribution

AN - SCOPUS:85195588122

SN - 9783031494208

SN - 9783031494239

VL - 152

T3 - Mechanisms and Machine Science

SP - 787

EP - 796

BT - Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences (UNIfied 2023) - Volume 2

A2 - Ball, Andrew D.

A2 - Ouyang, Huajiang

A2 - Sinha, Jyoti K.

A2 - Wang, Zuolu

PB - Springer, Cham

T2 - The UNIfied Conference of DAMAS, InCoME and TEPEN Conferences

Y2 - 29 August 2023 through 1 September 2023

ER -

Kokkinis G, Ahmed QZ, Sambell A, Chochliouros IP, Lazaridis PI, Zaharis ZD. A Comparison Between CPU and GPU Computing in DNN-Based DoA Estimation. In Ball AD, Ouyang H, Sinha JK, Wang Z, editors, Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences (UNIfied 2023) - Volume 2. Vol. 152. Springer, Cham. 2024. p. 787-796. (Mechanisms and Machine Science). Epub 2024 May 28. doi: 10.1007/978-3-031-49421-5_64

A Comparison Between CPU and GPU Computing in DNN-Based DoA Estimation

Abstract

Publication series

Conference

Access to Document

Other files and links

Cite this