High-Performance Parallel and Stream Processing of X-ray Microdiffraction Data on Multicores

被引：4

作者：

Bauer, Michael A. ^{[1
]}

Biem, Alain ^{[2
]}

McIntyre, Stewart ^{[1
]}

Tamura, Nobumichi ^{[3
]}

Xie, Yuzhen ^{[1
]}

机构：

[1] Univ Western Ontario, London, ON, Canada

[2] IBM Res, Yorktown Hts, NY USA

[3] Advanced Light Source, Lawrence Berkeley Natl Lab, Berkeley, CA 94720 USA

来源：

HIGH PERFORMANCE COMPUTING SYMPOSIUM 2011 | 2012年 / 341卷

关键词：

D O I：

10.1088/1742-6596/341/1/012025

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

We present the design and implementation of a high-performance system for processing synchrotron X-ray microdiffraction (XRD) data in IBM InfoSphere Streams on multicore processors. We report on the parallel and stream processing techniques that we use to harvest the power of clusters of multicores to analyze hundreds of gigabytes of synchrotron XRD data in order to reveal the microtexture of polycrystalline materials. The timing to process one XRD image using one pipeline is about ten times faster than the best C program at present. With the support of InfoSphere Streams platform, our software is able to be scaled up to operate on clusters of multi-cores for processing multiple images concurrently. This system provides a high-performance processing kernel to achieve near real-time data analysis of image data from synchrotron experiments.

引用

页数：10

共 14 条

[1]

Advanced Light Source, 2010, ADV LIGHT SOURC X RA

[2]

Advanced Photon Source, 2009, ADV PHOT SOURC 3D X

[3] Quantitative characterization of electromigration-induced plastic deformation in Al(0.5wt%Cu) interconnect [J].