FAZ: A flexible auto-tuned modular error-bounded compression framework for scientific data

Jinyang Liu; Sheng Di; Kai Zhao; Xin Liang; Zizhong Chen; Franck Cappello

doi:10.1145/3577193.3593721

FAZ: A flexible auto-tuned modular error-bounded compression framework for scientific data

Jinyang Liu
, Sheng Di
, Kai Zhao
, Xin Liang
, Zizhong Chen
, Franck Cappello

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

18 Scopus citations

Abstract

Error-bounded lossy compression has been effective to resolve the big scientific data issue because it has a great potential to significantly reduce the data volume while allowing users to control data distortion based on specified error bounds. However, none of the existing error-bounded lossy compressors can always obtain the best compression quality because of the diverse characteristics of different datasets. In this paper, we develop FAZ, a flexible and adaptive error-bounded lossy compression framework, which projects a fairly high capability of adapting to diverse datasets. FAZ can always keep the compression quality at the best level compared with other state-of-the-art compressors for different datasets. We perform a comprehensive evaluation using 6 real-world scientific applications and 6 other state-of-the-art error-bounded lossy compressors. Experiments show that compared with the other existing lossy compressors, FAZ can improve the compression ratio by up to 120%, 190%, and 75% when setting the same error bound, the same PSNR and the same SSIM, respectively.

Original language	English
Title of host publication	ACM ICS 2023 - Proceedings of the International Conference on Supercomputing
Pages	1-13
Number of pages	13
ISBN (Electronic)	9798400700569
DOIs	https://doi.org/10.1145/3577193.3593721
State	Published - Jun 21 2023
Event	37th ACM International Conference on Supercomputing, ICS 2023 - Orlando, United States Duration: Jun 21 2023 → Jun 23 2023

Publication series

Name	Proceedings of the International Conference on Supercomputing

Conference

Conference	37th ACM International Conference on Supercomputing, ICS 2023
Country/Territory	United States
City	Orlando
Period	6/21/23 → 6/23/23

Bibliographical note

Publisher Copyright:
© 2023 ACM.

Funding

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, Advanced Scientific Computing Research (ASCR), under contract DE-AC02-06CH11357, and supported by the National Science Foundation under Grant OAC-2003709, OAC-2104023 and OAC-2153451. We acknowledge the computing resources provided on Bebop (operated by Laboratory Computing Resource Center at Argonne) and on Theta and JLSE (operated by Argonne Leadership Computing Facility).

Funders	Funder number
National Science Foundation Arctic Social Science Program	OAC-2003709, OAC-2153451, OAC-2104023
U.S. Department of Energy
Office of Science Programs
National Nuclear Security Administration
Advanced Scientific Computing Research	DE-AC02-06CH11357

Keywords

data compression
high performance computing

ASJC Scopus subject areas

General Computer Science

Access to Document

10.1145/3577193.3593721

Cite this

@inproceedings{4d9c857019e045e2bd6fbfd1c79f0f93,

title = "FAZ: A flexible auto-tuned modular error-bounded compression framework for scientific data",

abstract = "Error-bounded lossy compression has been effective to resolve the big scientific data issue because it has a great potential to significantly reduce the data volume while allowing users to control data distortion based on specified error bounds. However, none of the existing error-bounded lossy compressors can always obtain the best compression quality because of the diverse characteristics of different datasets. In this paper, we develop FAZ, a flexible and adaptive error-bounded lossy compression framework, which projects a fairly high capability of adapting to diverse datasets. FAZ can always keep the compression quality at the best level compared with other state-of-the-art compressors for different datasets. We perform a comprehensive evaluation using 6 real-world scientific applications and 6 other state-of-the-art error-bounded lossy compressors. Experiments show that compared with the other existing lossy compressors, FAZ can improve the compression ratio by up to 120\%, 190\%, and 75\% when setting the same error bound, the same PSNR and the same SSIM, respectively.",

keywords = "data compression, high performance computing",

author = "Jinyang Liu and Sheng Di and Kai Zhao and Xin Liang and Zizhong Chen and Franck Cappello",

note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 37th ACM International Conference on Supercomputing, ICS 2023 ; Conference date: 21-06-2023 Through 23-06-2023",

year = "2023",

month = jun,

day = "21",

doi = "10.1145/3577193.3593721",

language = "English",

series = "Proceedings of the International Conference on Supercomputing",

pages = "1--13",

booktitle = "ACM ICS 2023 - Proceedings of the International Conference on Supercomputing",

}

Liu, J, Di, S, Zhao, K, Liang, X, Chen, Z & Cappello, F 2023, FAZ: A flexible auto-tuned modular error-bounded compression framework for scientific data. in ACM ICS 2023 - Proceedings of the International Conference on Supercomputing. Proceedings of the International Conference on Supercomputing, pp. 1-13, 37th ACM International Conference on Supercomputing, ICS 2023, Orlando, United States, 6/21/23. https://doi.org/10.1145/3577193.3593721

FAZ: A flexible auto-tuned modular error-bounded compression framework for scientific data. / Liu, Jinyang; Di, Sheng; Zhao, Kai et al.
ACM ICS 2023 - Proceedings of the International Conference on Supercomputing. 2023. p. 1-13 (Proceedings of the International Conference on Supercomputing).

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

TY - GEN

T1 - FAZ

T2 - 37th ACM International Conference on Supercomputing, ICS 2023

AU - Liu, Jinyang

AU - Di, Sheng

AU - Zhao, Kai

AU - Liang, Xin

AU - Chen, Zizhong

AU - Cappello, Franck

PY - 2023/6/21

Y1 - 2023/6/21

N2 - Error-bounded lossy compression has been effective to resolve the big scientific data issue because it has a great potential to significantly reduce the data volume while allowing users to control data distortion based on specified error bounds. However, none of the existing error-bounded lossy compressors can always obtain the best compression quality because of the diverse characteristics of different datasets. In this paper, we develop FAZ, a flexible and adaptive error-bounded lossy compression framework, which projects a fairly high capability of adapting to diverse datasets. FAZ can always keep the compression quality at the best level compared with other state-of-the-art compressors for different datasets. We perform a comprehensive evaluation using 6 real-world scientific applications and 6 other state-of-the-art error-bounded lossy compressors. Experiments show that compared with the other existing lossy compressors, FAZ can improve the compression ratio by up to 120%, 190%, and 75% when setting the same error bound, the same PSNR and the same SSIM, respectively.

AB - Error-bounded lossy compression has been effective to resolve the big scientific data issue because it has a great potential to significantly reduce the data volume while allowing users to control data distortion based on specified error bounds. However, none of the existing error-bounded lossy compressors can always obtain the best compression quality because of the diverse characteristics of different datasets. In this paper, we develop FAZ, a flexible and adaptive error-bounded lossy compression framework, which projects a fairly high capability of adapting to diverse datasets. FAZ can always keep the compression quality at the best level compared with other state-of-the-art compressors for different datasets. We perform a comprehensive evaluation using 6 real-world scientific applications and 6 other state-of-the-art error-bounded lossy compressors. Experiments show that compared with the other existing lossy compressors, FAZ can improve the compression ratio by up to 120%, 190%, and 75% when setting the same error bound, the same PSNR and the same SSIM, respectively.

KW - data compression

KW - high performance computing

UR - https://www.scopus.com/pages/publications/85168425872

UR - https://www.scopus.com/pages/publications/85168425872#tab=citedBy

U2 - 10.1145/3577193.3593721

DO - 10.1145/3577193.3593721

M3 - Conference contribution

AN - SCOPUS:85168425872

T3 - Proceedings of the International Conference on Supercomputing

SP - 1

EP - 13

BT - ACM ICS 2023 - Proceedings of the International Conference on Supercomputing

Y2 - 21 June 2023 through 23 June 2023

ER -

FAZ: A flexible auto-tuned modular error-bounded compression framework for scientific data

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this