A virtualized software based on the NVIDIA cuFFT library for image denoising: performance analysis

Ardelio Galletti; Livia Marcellino; Raffaele Montella; Vincenzo Santopietro; Sokol Kosta

doi:10.1016/j.procs.2017.08.310

A virtualized software based on the NVIDIA cuFFT library for image denoising: performance analysis

Ardelio Galletti, Livia Marcellino, Raffaele Montella, Vincenzo Santopietro, Sokol Kosta

Research output: Contribution to journal › Conference article in Journal › Research › peer-review

1 Citation (Scopus)

173 Downloads (Pure)

Abstract

Abstract Generic Virtualization Service (GVirtuS) is a new solution for enabling GPGPU on Virtual Machines or low powered devices. This paper focuses on the performance analysis that can be obtained using a GPGPU virtualized software. Recently, GVirtuS has been extended in order to support CUDA ancillary libraries with good results. Here, our aim is to analyze the applicability of this powerful tool to a real problem, which uses the NVIDIA cuFFT library. As case study we consider a simple denoising algorithm, implementing a virtualized GPU-parallel software based on the convolution theorem in order to perform the noise removal procedure in the frequency domain. We report some preliminary tests in both physical and virtualized environments to study and analyze the potential scalability of such an algorithm.

Original language	English
Journal	Procedia Computer Science
Volume	113
Pages (from-to)	496 - 501
Number of pages	6
ISSN	1877-0509
DOIs	https://doi.org/10.1016/j.procs.2017.08.310
Publication status	Published - 17 Sept 2017
Event	The 8th International Conference on Emerging Ubiquitous Systems and Pervasive Networks (EUSPN 2017) / The 7th International Conference on Current and Future Trends of Information and Communication Technologies in Healthcare (ICTH-2017) / Affiliated Workshops - Lund, Sweden Duration: 18 Sept 2017 → 20 Sept 2017

Conference

Conference	The 8th International Conference on Emerging Ubiquitous Systems and Pervasive Networks (EUSPN 2017) / The 7th International Conference on Current and Future Trends of Information and Communication Technologies in Healthcare (ICTH-2017) / Affiliated Workshops
Country/Territory	Sweden
City	Lund
Period	18/09/2017 → 20/09/2017

Access to Document

10.1016/j.procs.2017.08.310

Open access articleFinal published version, 383 KBLicence: CC BY-NC-ND 4.0

http://www.sciencedirect.com/science/article/pii/S1877050917317209Licence: CC BY-NC-ND 4.0

AUB Link

Search for the material in Aalborg University Library's search engine

1 Citations
1 Article in proceeding

Enabling the CUDA Unified Memory model in Edge, Cloud and HPC offloaded GPU kernels
Montella, R., Di Luccio, D., De Vita, C. G., Mellone, G., Lapegna, M., Laccetti, G., Kosta, S. & Giunta, G., 2022, Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022. Fazio, M., Panda, D. K., Prodan, R., Cardellini, V., Kantarci, B., Rana, O. & Villari, M. (eds.). IEEE Signal Processing Society, p. 834-841 8 p. (Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022).
Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review
1 Citation (Scopus)

Cite this

@inproceedings{c20dc748d06941c8ab3c08cbb429181b,

title = "A virtualized software based on the NVIDIA cuFFT library for image denoising: performance analysis",

abstract = "Abstract Generic Virtualization Service (GVirtuS) is a new solution for enabling GPGPU on Virtual Machines or low powered devices. This paper focuses on the performance analysis that can be obtained using a GPGPU virtualized software. Recently, GVirtuS has been extended in order to support CUDA ancillary libraries with good results. Here, our aim is to analyze the applicability of this powerful tool to a real problem, which uses the NVIDIA cuFFT library. As case study we consider a simple denoising algorithm, implementing a virtualized GPU-parallel software based on the convolution theorem in order to perform the noise removal procedure in the frequency domain. We report some preliminary tests in both physical and virtualized environments to study and analyze the potential scalability of such an algorithm.",

keywords = "image denoising",

author = "Ardelio Galletti and Livia Marcellino and Raffaele Montella and Vincenzo Santopietro and Sokol Kosta",

year = "2017",

month = sep,

day = "17",

doi = "10.1016/j.procs.2017.08.310",

language = "English",

volume = "113",

pages = "496 -- 501",

journal = "Procedia Computer Science",

issn = "1877-0509",

publisher = "Elsevier",

note = "The 8th International Conference on Emerging Ubiquitous Systems and Pervasive Networks (EUSPN 2017) / The 7th International Conference on Current and Future Trends of Information and Communication Technologies in Healthcare (ICTH-2017) / Affiliated Workshops ; Conference date: 18-09-2017 Through 20-09-2017",

}

TY - GEN

T1 - A virtualized software based on the NVIDIA cuFFT library for image denoising

T2 - The 8th International Conference on Emerging Ubiquitous Systems and Pervasive Networks (EUSPN 2017) / The 7th International Conference on Current and Future Trends of Information and Communication Technologies in Healthcare (ICTH-2017) / Affiliated Workshops

AU - Galletti, Ardelio

AU - Marcellino, Livia

AU - Montella, Raffaele

AU - Santopietro, Vincenzo

AU - Kosta, Sokol

PY - 2017/9/17

Y1 - 2017/9/17

N2 - Abstract Generic Virtualization Service (GVirtuS) is a new solution for enabling GPGPU on Virtual Machines or low powered devices. This paper focuses on the performance analysis that can be obtained using a GPGPU virtualized software. Recently, GVirtuS has been extended in order to support CUDA ancillary libraries with good results. Here, our aim is to analyze the applicability of this powerful tool to a real problem, which uses the NVIDIA cuFFT library. As case study we consider a simple denoising algorithm, implementing a virtualized GPU-parallel software based on the convolution theorem in order to perform the noise removal procedure in the frequency domain. We report some preliminary tests in both physical and virtualized environments to study and analyze the potential scalability of such an algorithm.

AB - Abstract Generic Virtualization Service (GVirtuS) is a new solution for enabling GPGPU on Virtual Machines or low powered devices. This paper focuses on the performance analysis that can be obtained using a GPGPU virtualized software. Recently, GVirtuS has been extended in order to support CUDA ancillary libraries with good results. Here, our aim is to analyze the applicability of this powerful tool to a real problem, which uses the NVIDIA cuFFT library. As case study we consider a simple denoising algorithm, implementing a virtualized GPU-parallel software based on the convolution theorem in order to perform the noise removal procedure in the frequency domain. We report some preliminary tests in both physical and virtualized environments to study and analyze the potential scalability of such an algorithm.

KW - image denoising

U2 - 10.1016/j.procs.2017.08.310

DO - 10.1016/j.procs.2017.08.310

M3 - Conference article in Journal

SN - 1877-0509

VL - 113

SP - 496

EP - 501

JO - Procedia Computer Science

JF - Procedia Computer Science

Y2 - 18 September 2017 through 20 September 2017

ER -

A virtualized software based on the NVIDIA cuFFT library for image denoising: performance analysis

Abstract

Conference

Access to Document

AUB Link

Fingerprint

Research output

Enabling the CUDA Unified Memory model in Edge, Cloud and HPC offloaded GPU kernels

Cite this