Data-Aware Compression for HPC using Machine Learning

Author:

Plehn Julius1,Fuchs Anna1,Kuhn Michael2,Lüttgau Jakob3,Ludwig Thomas4

Affiliation:

1. Universität Hamburg Hamburg, Germany

2. Otto von Guericke University Magdeburg Magdeburg, Germany

3. University of Tennessee Knoxville Knoxville, USA

4. Deutsches Klimarechenzentrum GmbH Hamburg, Germany

Abstract

While compression can provide significant storage and cost savings, its use within HPC applications is often only of secondary concern. This is in part due to the inflexibility of existing approaches where a single compression algorithm has to be used throughout the whole application but also because insights into the behaviour of the algorithms within the context of individual applications are missing.

Publisher

Association for Computing Machinery (ACM)

Subject

Genetics,Animal Science and Zoology

Reference17 articles.

1. Cyan4973. 2020. LZ4 - Extremely fast compression. https://github. com/lz4/lz4 Cyan4973. 2020. LZ4 - Extremely fast compression. https://github. com/lz4/lz4

2. Anna Fuchs. 2019. Enhanced Adaptive Compression in Lustre. https: //wiki.lustre.org/Enhanced_Adaptive_Compression_in_Lustre Anna Fuchs. 2019. Enhanced Adaptive Compression in Lustre. https: //wiki.lustre.org/Enhanced_Adaptive_Compression_in_Lustre

3. Jean-loup Gailly Greg Roelofs and Mark Adler . 2022. OpenSFS Survey March 2021 Results. https://wiki.opensfs.org/images/2/20/OpenSFS_ Survey _Results_March_2021.pdf Jean-loup Gailly Greg Roelofs and Mark Adler. 2022. OpenSFS Survey March 2021 Results. https://wiki.opensfs.org/images/2/20/OpenSFS_ Survey_Results_March_2021.pdf

4. Jean-loup Gailly Greg Roelofs and Mark Adler. 2022. zlib Technical Details. https://zlib.net/zlib_tech.html Jean-loup Gailly Greg Roelofs and Mark Adler. 2022. zlib Technical Details. https://zlib.net/zlib_tech.html

5. The HDF Group. 2018. Release of HDF5--1.10.2 - Newsletter #160. https://www.hdfgroup.org/2018/03/release-of-hdf5--1--10--2- newsletter-160/ The HDF Group. 2018. Release of HDF5--1.10.2 - Newsletter #160. https://www.hdfgroup.org/2018/03/release-of-hdf5--1--10--2- newsletter-160/

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3