DOE OSTI · 1564037
Performance Modeling of Vectorized SNAP Inter-Atomic Potentials on CPU Architectures.
Abstract
SNAP potentials are inter-atomic potentials for molecular dynamics that enable simulations at accuracy levels comparable to density functional theory(DFT) at a fraction of the cost. As such, SNAP scales to on the order of 10 4 — 10 6 atoms. In this work, we explore CPU optimization of potentials computation using SIMD. We note that efficient use of SIMD is non-obvious as the application features an irregular iteration space for various potential terms, necessitating use of SIMD across atoms in a cross matrix, batched fashion. We present a preliminary analytic model to determine the correct batch size for several CPU architectures across several vendors, and show end-to-end speedups between 1.66x and 3.22x compared to the original.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Blanco, Mark P., Kim, Kyungjoo. 2019-09-23. Performance Modeling of Vectorized SNAP Inter-Atomic Potentials on CPU Architectures.. https://doi.org/10.2172/1564037
Cite the original work for its findings. Save a collection to share your selection of sources.