English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Molecular dynamics simulations, an indispensable research tool incomputational chemistry and materials science, consume a significant portion ofthe supercomputing cycles around the world. We focus on multi-body potentialsand aim at achieving performance portability. Compared with well-studied pairpotentials, multibody potentials deliver increased simulation accuracy but aretoo complex for effective compiler optimization. Because of this, achievingcross-platform performance remains an open question. By abstracting from targetarchitecture and computing precision, we develop a vectorization schemeapplicable to both CPUs and accelerators. We present results for the Tersoffpotential within the molecular dynamics code LAMMPS on several architectures,demonstrating efficiency gains not only for computational kernels, but also forlarge-scale simulations. On a cluster of Intel Xeon Phi's, our optimized solveris between 3 and 5 times faster than the pure MPI reference.

The Vectorization of the Tersoff Multi-Body Potential: An Exercise in Performance Portability