Insights for exascale IO APIs from building a petascale IO API

J. Lofstead, R. Ross
{"title":"Insights for exascale IO APIs from building a petascale IO API","authors":"J. Lofstead, R. Ross","doi":"10.1145/2503210.2503238","DOIUrl":null,"url":null,"abstract":"Near the dawn of the petascale era, IO libraries had reached a stability in their function and data layout with only incremental changes being incorporated. The shift in technology, particularly the scale of parallel file systems and the number of compute processes, prompted revisiting best practices for optimal IO performance. Among other efforts like PLFS, the project that led to ADIOS, the ADaptable IO System, was motivated by both the shift in technology and the historical requirement, for optimal IO performance, to change how simulations performed IO depending on the platform. To solve both issues, the ADIOS team, along with consultation with other leading IO experts, sought to build a new IO platform based on the assumptions inherent in the petascale hardware platforms. This paper helps inform the design of future IO platforms with a discussion of lessons learned as part of the process of designing and building ADIOS.","PeriodicalId":371074,"journal":{"name":"2013 SC - International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","volume":"26 4","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"25","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 SC - International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2503210.2503238","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 25

Abstract

Near the dawn of the petascale era, IO libraries had reached a stability in their function and data layout with only incremental changes being incorporated. The shift in technology, particularly the scale of parallel file systems and the number of compute processes, prompted revisiting best practices for optimal IO performance. Among other efforts like PLFS, the project that led to ADIOS, the ADaptable IO System, was motivated by both the shift in technology and the historical requirement, for optimal IO performance, to change how simulations performed IO depending on the platform. To solve both issues, the ADIOS team, along with consultation with other leading IO experts, sought to build a new IO platform based on the assumptions inherent in the petascale hardware platforms. This paper helps inform the design of future IO platforms with a discussion of lessons learned as part of the process of designing and building ADIOS.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
从构建千兆级IO API获得百亿亿级IO API的见解
在千兆级(peascale)时代即将到来之际,IO库在功能和数据布局方面已经达到了稳定,只有增量更改被纳入。技术的转变,特别是并行文件系统的规模和计算进程的数量,促使人们重新审视最佳IO性能的最佳实践。在PLFS等其他努力中,ADIOS(可适应IO系统)项目的发展受到技术转变和历史要求的推动,以实现最佳IO性能,改变模拟如何根据平台执行IO。为了解决这两个问题,ADIOS团队与其他领先的IO专家协商,试图建立一个基于千兆级硬件平台固有假设的新IO平台。本文通过讨论作为设计和构建ADIOS过程一部分的经验教训,有助于为未来IO平台的设计提供信息。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Distributed-memory parallel algorithms for generating massive scale-free networks using preferential attachment model Enabling comprehensive data-driven system management for large computational facilities There goes the neighborhood: Performance degradation due to nearby jobs A distributed dynamic load balancer for iterative applications Predicting application performance using supervised learning on communication features
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1