Semantic Scholar Open Access 2025 3 sitasi

LAMMPS-KOKKOS: Performance Por table Molecular Dynamics Across Exascale Architectures

A. Johansson Evan Weinberg Christian Trott Megan J. McCarthy Stan Moore

Abstrak

Since its inception in 1995, LAMMPS has grown to be a world-class molecular dynamics code, with thousands of users, over one million lines of code, and multi-scale simulation capabilities. We discuss how LAMMPS has adapted to the modern heterogeneous computing landscape by integrating the Kokkos performance portability library into the existing C++ code. We investigate performance portability of simple pairwise, many-body reactive, and machine-learned force-field interatomic potentials. We present results on GPUs across different vendors and generations, and analyze performance trends, probing FLOPS throughput, memory bandwidths, cache capabilities, and thread-atomic operation performance. Finally, we demonstrate strong scaling on three exascale machines – OLCF Frontier, ALCF Aurora, and NNSA El Capitan – as well as on the CSCS Alps supercomputer, for the three potentials.CCS Concepts• General and reference→Performance; • Software and its engineering→Ultra-large-scale systems; • Computing methodologies→Parallel algorithms; Massively parallel algorithms; Distributed algorithms; Machine learning; Molecular simulation.

Topik & Kata Kunci

Penulis (5)

A

A. Johansson

E

Evan Weinberg

C

Christian Trott

M

Megan J. McCarthy

S

Stan Moore

Format Sitasi

Johansson, A., Weinberg, E., Trott, C., McCarthy, M.J., Moore, S. (2025). LAMMPS-KOKKOS: Performance Por table Molecular Dynamics Across Exascale Architectures. https://doi.org/10.1145/3731599.3767498

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber doi.org/10.1145/3731599.3767498
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Total Sitasi
Sumber Database
Semantic Scholar
DOI
10.1145/3731599.3767498
Akses
Open Access ✓