Skip to Main Content U.S. Department of Energy
mathematical sciences, Computational Sciences & Mathematics

With multidisciplinary expertise spanning technical pillars of high-performance computing, data science, and computational mathematics, we work toward building computational capabilities that position PNNL as a computing powerhouse. We also focus on enhancing the Science of Computing to achieve high-performance, power-efficient, and reliable computing at extreme scales for a spectrum of scientific endeavors that address significant problems of national interest, especially among PNNL’s core pursuits—energy, the environment, national security, and fundamental science.

A High-Tech Team

John Feo and Antonino Tumeo, from PNNL’s Advanced Computing, Mathematics, and Data Division, are serving as guest editors for a special issue of Computer, the IEEE Computer Society’s flagship magazine, devoted to “Irregular Applications.” The issue will center on exploring solutions for supporting the efficient design, development, and execution of irregular applications and is slated for publication in August 2015. A Call for Papers has been issued that is accessible via the Computing Now website. The submission deadline for papers is Sunday, February 01, 2015.



2014 Key Accomplishments

2014 Key Scientific Accomplishments Report Now Available

The 2014 Key Scientific Accomplishments report in fundamental and computational sciences is now available as a downloadable PDF. This 32-page full-color brochure highlights some of the year's most noteworthy science achievements by Pacific Northwest National Laboratory scientists.



A Shiny, New Graph Query System

As computing tools and expertise used in conducting scientific research continue to expand, so have the enormity and diversity of the data being collected. Scientists from PNNL and NVIDIA Research examined how GEMS, a multilayer software system for semantic graph databases developed at PNNL, could answer queries on science metadata then compared its scaling performance against generated benchmark data sets. They showed that GEMS could answer queries over curated science metadata in seconds and scaled well to larger quantities of data. They also demonstrated that GEMS generally outperformed a custom-hardware solution, indicating the viability of using cheaper, commodity hardware to obtain comparable performance. 



Stretched to the Limit

Xiaohua Hu, a scientist from ACMD Division’s Applied Computational Mathematics and Engineering group, will be a featured speaker at the annual Materials Science & Technology meeting, or MS&T'14. As part of a materials symposium, he will present, “An Integrated Finite Element Framework of Studying Edge Cracking during Stretching of Previous Trimmed Sheets,” describing an integrated manufacturing process simulation framework developed to predict trimmed edge tensile stretchability of aluminum alloy sheets primarily used for automotive paneling. The work is the result of a longtime ongoing collaboration between Ford Motor Company and PNNL and is funded by DOE’s Office of Energy Efficiency & Renewable Energy Vehicle Technologies program.



Fueled by Algorithms

By reexamining existing classical graph algorithms to exploit the power and efficiency of modern computers, scientists from Simula Research Laboratory, University of Bergen, Purdue University, and PNNL explored the maximum bipartite matching problem. Their first-of-its-kind work incorporated modern multi-core computers—an area not previously explored for this problem—and provided a new parallel version of the push-relabel algorithm for bipartite graph matching that works well for shared memory computing systems. Their work also included a thorough examination of algorithmic performance, showing viable and improved scaling on various multi-core machines.



Advanced Computing, Mathematics, and Data

Collaborations

Seminar Series

Fundamental & Computational Sciences

Research highlights

View All ACMDD Highlights

Subscribe

RSS Feed RSS feed logo

Follow Us

  • YouTube Facebook Flickr TwitThis LinkedIn

Contacts