Addressing the petascale data challenge using in-situ analytics

Addressing the petascale data challenge using in-situ analytics
复制标题

使用现场分析应对千万级数据挑战

DOI:
10.1145/2110205.2110212
复制
发表时间:
2011
影响因子:
1.8
通讯作者:
M. Parashar
M. Parashar
中科院分区:
计算机科学4区
文献类型:
--
作者:
M. Parashar

文献摘要

被引文献

相似文献

数据管理、处理和分析成本正在迅速主导计算和数据支持的科学,并限制了在高端计算系统上运行的极端规模的高级模拟的潜在影响。本演示探讨了如何使用现场数据分析、传输中数据转换和数据操作来解决千万亿级及以上的数据挑战。具体来说,本演示介绍了作为罗格斯空间项目一部分开发并在 ADIOS 框架内部署的解决方案。
Data management, processing and analysis costs are quickly dominating computational and data-enabled sciences, and are limiting the potential impacts of advanced simulations running at extreme scales on the high-end computing systems. This presentation explores how in-situ data analytics and in-transit data transformation and data manipulation can be used to address these data challenges at petascale and beyond. Specifically, this presentations describes solutions developed as part of the Rutgers Spaces Project and deployed within the ADIOS framework.