Machine learning for ultrafast X-ray diffraction patterns on large-scale GPU clusters. (May 2015)

• Record Type: Journal Article
• Authors: Ekeberg, Tomas; Engblom, Stefan; Liu, Jing
• Is Part Of: International journal of high performance computing applications. Volume 29:Number 2(2015:Summer)
• Page Start: 233
• Page End: 243
• Publication Date: 2015-05
• Subjects: Expectation–maximization -- X-ray laser diffraction -- GPU cluster -- single-molecule imaging; High performance computing -- Periodicals; Supercomputers -- Periodicals; 004.1105
• DOI: 10.1177/1094342015572030
• Languages: English
• ISSNs: 1094-3420

Abstract

The classical method of determining the atomic structure of complex molecules by analyzing diffraction patterns is currently undergoing drastic developments. Modern techniques for producing extremely bright and coherent X-ray lasers allow a beam of streaming particles to be intercepted and hit by an ultrashort high-energy X-ray beam. Through machine learning methods the data thus collected can be transformed into a three-dimensional volumetric intensity map of the particle itself. The computational complexity associated with this problem is very high such that clusters of data parallel accelerators are required. We have implemented a distributed and highly efficient algorithm for the inversion of large collections of diffraction patterns targeting clusters of hundreds of GPUs. With the expected enormous amount of diffraction data to be produced in the foreseeable future, this is the required scale to approach real-time processing of data at the beam site. Using both real and synthetic data we look at the scaling properties of the application and discuss the overall computational viability of this exciting and novel imaging technique.