Fixed-PSNR Lossy Compression for Scientific Data

Dingwen Tao; Sheng Di; Xin Liang; Zizhong Chen; Franck Cappello

doi:10.1109/CLUSTER.2018.00048

Fixed-PSNR Lossy Compression for Scientific Data

Dingwen Tao
, Sheng Di
, Xin Liang
, Zizhong Chen
, Franck Cappello

Producción científica: Conference contribution › revisión exhaustiva

23 Citas (Scopus)

Resumen

Error-controlled lossy compression has been studied for years because of extremely large volumes of data being produced by today's scientific simulations. None of existing lossy compressors, however, allow users to fix the peak signal-to-noise ratio (PSNR) during compression, although PSNR has been considered as one of the most significant indicators to assess compression quality. In this paper, we propose a novel technique providing a fixed-PSNR lossy compression for scientific data sets. We implement our proposed method based on the SZ lossy compression framework and release the code as an open-source toolkit. We evaluate our fixed-PSNR compressor on three realworld high-performance computing data sets. Experiments show that our solution has a high accuracy in controlling PSNR, with an average deviation of 0.1 ~ 5.0 dB on the tested data sets.

Idioma original	English
Título de la publicación alojada	Proceedings - 2018 IEEE International Conference on Cluster Computing, CLUSTER 2018
Páginas	314-318
Número de páginas	5
ISBN (versión digital)	9781538683194
DOI	https://doi.org/10.1109/CLUSTER.2018.00048
Estado	Published - oct 29 2018
Evento	2018 IEEE International Conference on Cluster Computing, CLUSTER 2018 - Belfast, United Kingdom Duración: sept 10 2018 → sept 13 2018

Serie de la publicación

Nombre	Proceedings - IEEE International Conference on Cluster Computing, ICCC
Volumen	2018-September
ISSN (versión impresa)	1552-5244

Conference

Conference	2018 IEEE International Conference on Cluster Computing, CLUSTER 2018
País/Territorio	United Kingdom
Ciudad	Belfast
Período	9/10/18 → 9/13/18

Nota bibliográfica

Publisher Copyright:
© 2018 IEEE.

Financiación

ACKNOWLEDGE This research was supported by the Exascale Computing Project (ECP), Project Number: 17-SC-20-SC, a collaborative effort of two DOE organizations – the Office of Science and the National Nuclear Security Administration, responsible for the planning and preparation of a capable exascale ecosystem, including software, applications, hardware, advanced system engineering and early testbed platforms, to support the nation’s exascale computing imperative. The material was supported by the U.S. Department of Energy, Office of Science, under contract DE-AC02-06CH11357,and supported by the National Science Foundation under Grant No. 1619253. We gratefully acknowledge the computing resources provided on Bebop, a high-performance computing cluster operated by the Laboratory Computing Resource Center at Argonne National Laboratory.

Financiadores	Número del financiador
National Science Foundation Arctic Social Science Program	1619253
U.S. Department of Energy Oak Ridge National Laboratory U.S. Department of Energy National Science Foundation National Energy Research Scientific Computing Center	DE-AC02-06CH11357
Office of Science Programs
National Nuclear Security Administration

ASJC Scopus subject areas

Software
Signal Processing
Hardware and Architecture

Acceder al documento

10.1109/CLUSTER.2018.00048

Otros archivos y enlaces

Citar esto

@inproceedings{731decfba2164b99853b6b7972fbb044,

title = "Fixed-PSNR Lossy Compression for Scientific Data",

abstract = "Error-controlled lossy compression has been studied for years because of extremely large volumes of data being produced by today's scientific simulations. None of existing lossy compressors, however, allow users to fix the peak signal-to-noise ratio (PSNR) during compression, although PSNR has been considered as one of the most significant indicators to assess compression quality. In this paper, we propose a novel technique providing a fixed-PSNR lossy compression for scientific data sets. We implement our proposed method based on the SZ lossy compression framework and release the code as an open-source toolkit. We evaluate our fixed-PSNR compressor on three realworld high-performance computing data sets. Experiments show that our solution has a high accuracy in controlling PSNR, with an average deviation of 0.1 \textasciitilde{} 5.0 dB on the tested data sets.",

keywords = "Lossy compression, PSNR, Scientific data",

author = "Dingwen Tao and Sheng Di and Xin Liang and Zizhong Chen and Franck Cappello",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE International Conference on Cluster Computing, CLUSTER 2018 ; Conference date: 10-09-2018 Through 13-09-2018",

year = "2018",

month = oct,

day = "29",

doi = "10.1109/CLUSTER.2018.00048",

language = "English",

series = "Proceedings - IEEE International Conference on Cluster Computing, ICCC",

pages = "314--318",

booktitle = "Proceedings - 2018 IEEE International Conference on Cluster Computing, CLUSTER 2018",

}

Tao, D, Di, S, Liang, X, Chen, Z & Cappello, F 2018, Fixed-PSNR Lossy Compression for Scientific Data. En Proceedings - 2018 IEEE International Conference on Cluster Computing, CLUSTER 2018., 8514891, Proceedings - IEEE International Conference on Cluster Computing, ICCC, vol. 2018-September, pp. 314-318, 2018 IEEE International Conference on Cluster Computing, CLUSTER 2018, Belfast, United Kingdom, 9/10/18. https://doi.org/10.1109/CLUSTER.2018.00048

Fixed-PSNR Lossy Compression for Scientific Data. / Tao, Dingwen; Di, Sheng; Liang, Xin et al.
Proceedings - 2018 IEEE International Conference on Cluster Computing, CLUSTER 2018. 2018. p. 314-318 8514891 (Proceedings - IEEE International Conference on Cluster Computing, ICCC; Vol. 2018-September).

Producción científica: Conference contribution › revisión exhaustiva

TY - GEN

T1 - Fixed-PSNR Lossy Compression for Scientific Data

AU - Tao, Dingwen

AU - Di, Sheng

AU - Liang, Xin

AU - Chen, Zizhong

AU - Cappello, Franck

PY - 2018/10/29

Y1 - 2018/10/29

N2 - Error-controlled lossy compression has been studied for years because of extremely large volumes of data being produced by today's scientific simulations. None of existing lossy compressors, however, allow users to fix the peak signal-to-noise ratio (PSNR) during compression, although PSNR has been considered as one of the most significant indicators to assess compression quality. In this paper, we propose a novel technique providing a fixed-PSNR lossy compression for scientific data sets. We implement our proposed method based on the SZ lossy compression framework and release the code as an open-source toolkit. We evaluate our fixed-PSNR compressor on three realworld high-performance computing data sets. Experiments show that our solution has a high accuracy in controlling PSNR, with an average deviation of 0.1 ~ 5.0 dB on the tested data sets.

AB - Error-controlled lossy compression has been studied for years because of extremely large volumes of data being produced by today's scientific simulations. None of existing lossy compressors, however, allow users to fix the peak signal-to-noise ratio (PSNR) during compression, although PSNR has been considered as one of the most significant indicators to assess compression quality. In this paper, we propose a novel technique providing a fixed-PSNR lossy compression for scientific data sets. We implement our proposed method based on the SZ lossy compression framework and release the code as an open-source toolkit. We evaluate our fixed-PSNR compressor on three realworld high-performance computing data sets. Experiments show that our solution has a high accuracy in controlling PSNR, with an average deviation of 0.1 ~ 5.0 dB on the tested data sets.

KW - Lossy compression

KW - PSNR

KW - Scientific data

UR - https://www.scopus.com/pages/publications/85057270840

UR - https://www.scopus.com/pages/publications/85057270840#tab=citedBy

U2 - 10.1109/CLUSTER.2018.00048

DO - 10.1109/CLUSTER.2018.00048

M3 - Conference contribution

AN - SCOPUS:85057270840

T3 - Proceedings - IEEE International Conference on Cluster Computing, ICCC

SP - 314

EP - 318

BT - Proceedings - 2018 IEEE International Conference on Cluster Computing, CLUSTER 2018

T2 - 2018 IEEE International Conference on Cluster Computing, CLUSTER 2018

Y2 - 10 September 2018 through 13 September 2018

ER -

Fixed-PSNR Lossy Compression for Scientific Data

Resumen

Serie de la publicación

Conference

Nota bibliográfica

Financiación

ASJC Scopus subject areas

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto