arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.10375physics.comp-phcond-mat.mes-hallcs.DCphysics.optics
收藏

基于分布式GPU的高性能多模式重叠关联重建

High-Performance Multi-Mode Ptychography Reconstruction on Distributed GPUs

Zhihua Dong, Yao-Lung L. Fang, Xiaojing Huang, Hanfei Yan, Sungsoo Ha, Wei Xu, Yong S. Chu, Stuart I. Campbell, Meifeng Lin

摘要:

重叠关联成像是一种新兴的成像技术,能够从具有扩展横向尺寸的样品提供波长受限的空间分辨率。作为扫描显微镜方法,典型的二维图像需要多个数据帧。作为一种基于衍射的成像技术,必须通过迭代重建算法来恢复实空间图像。由于这两个固有方面,重叠关联重建通常是计算密集且耗时的过程,这限制了该方法的吞吐量。我们报告了一个加速版本的多模式差分映射算法的重叠关联重建使用多个分布式GPU。这种方法利用了Python中可用的科学计算包,包括mpi4py和PyCUDA,核心计算功能在CUDA C中实现。我们发现,有趣的是,即使使用MPI集体通信,GPU节点数量的弱缩放仍然可以保持几乎恒定。最重要的是,对于现实的衍射测量,我们观察到的加速范围从$10$到$10^3$的因素取决于数据的大小,这减少了重建时间显着从小时到通常约1分钟,因此是至关重要的实时数据处理和可视化。

英文摘要:

Ptychography is an emerging imaging technique that is able to provide wavelength-limited spatial resolution from specimen with extended lateral dimensions. As a scanning microscopy method, a typical two-dimensional image requires a number of data frames. As a diffraction-based imaging technique, the real-space image has to be recovered through iterative reconstruction algorithms. Due to these two inherent aspects, a ptychographic reconstruction is generally a computation-intensive and time-consuming process, which limits the throughput of this method. We report an accelerated version of the multi-mode difference map algorithm for ptychography reconstruction using multiple distributed GPUs. This approach leverages available scientific computing packages in Python, including mpi4py and PyCUDA, with the core computation functions implemented in CUDA C. We find that interestingly even with MPI collective communications, the weak scaling in the number of GPU nodes can still remain nearly constant. Most importantly, for realistic diffraction measurements, we observe a speedup ranging from a factor of $10$ to $10^3$ depending on the data size, which reduces the reconstruction time remarkably from hours to typically about 1 minute and is thus critical for real-time data processing and visualization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑