Extreme Event Analysis in Next Generation Simulation Architectures

Extreme Event Analysis in Next Generation Simulation Architectures
复制标题

下一代仿真架构中的极端事件分析

DOI:
10.1007/978331958667015
复制
发表时间:
2017
期刊:
High Performance Computing. ISC 2017. Lecture Notes in Computer Science
影响因子:
--
通讯作者:
Burns, R.
Burns, R.
中科院分区:
--
文献类型:
--
作者:
Hamilton, S.;Lindstrom, P.;Patchett, J.;Meneveau, C.;Burns, R.

文献摘要

参考文献

被引文献

相似文献

数值模拟带来了挑战,因为它们生成了PB级的数据,必须在模拟过程中提取和减少。我们展示了一个无缝集成的湍流流体动力学模拟的特征提取。模拟产生的数量级为每时间步6 TB。为了分析和存储这些数据,我们提取速度数据从强涡流区域的膨胀体积,也存储数据的有损压缩表示。两者都将数据减少一个或多个数量级。我们从传输中的用户检查点提取数据,而它们驻留在临时突发缓冲区SSD存储中。通过这种方式,分析和压缩算法被设计为满足特定的时间限制,因此它们不会干扰模拟计算。我们的研究结果表明,我们可以在湍流的世界级直接数值模拟运行时进行特征提取,并收集有意义的科学数据用于存档和事后分析。
Numerical simulations present challenges because they generate petabyte-scale data that must be extracted and reduced during the simulation. We demonstrate a seamless integration of feature extraction for a simulation of turbulent fluid dynamics. The simulation produces on the order of 6 TB per timestep. In order to analyze and store this data, we extract velocity data from a dilated volume of the strong vortical regions and also store a lossy compressed representation of the data. Both reduce data by one or more orders of magnitude. We extract data from user checkpoints in transit while they reside on temporary burst buffer SSD stores. In this way, analysis and compression algorithms are designed to meet specific time constraints so they do not interfere with simulation computations. Our results demonstrate that we can perform feature extraction on a world-class direct numerical simulation of turbulence while it is running and gather meaningful scientific data for archival and post analysis.
极端事件分析
DOI: 10.1007/0-8176-4459-8_9
发表时间: 1985
影响因子: 2.5
作者:
R. L. Heathcote
通讯作者: R. L. Heathcote
原型亿亿级存储堆栈上的无抖动协同处理
DOI: 10.1109/msst.2012.6232382
发表时间: 2012
期刊: 012 IEEE 28th Symposium on Mass Storage Systems and Technologies (MSST)
影响因子: --
作者:
John Bent;Sorin Faibish;J. Ahrens;G. Grider;J. Patchett;P. Tzelnic;J. Woodring
通讯作者: J. Woodring
Petascale 可视化:方法和初步结果
DOI: 10.1109/ultravis.2008.5154060
发表时间: 2008
期刊: 2008 Workshop on Ultrascale Visualization
影响因子: --
作者:
J. Ahrens;Li;B. Nouanesengsy;J. Patchett;A. McPherson
通讯作者: A. McPherson
DOI: 10.2140/camcos.2016.11.37
发表时间: 2016
期刊: 012 IEEE 28th Symposium on Mass Storage Systems and Technologies (MSST)
影响因子: --
作者:
P. Bremer;A. Gruber;Janine Bennett;A. Gyulassy;H. Kolla;Jacqueline H. Chen;R. Grout
通讯作者: R. Grout