You are here

Energy-Efficient Computational Chemistry: Comparison of x86 and ARM Systems

TitleEnergy-Efficient Computational Chemistry: Comparison of x86 and ARM Systems
Publication TypeJournal Article
Year of Publication2015
AuthorsKeipert, K, Mitra, G, Sunriyal, V, Leang, SS, Sosonkina, M, Rendell, AP, Gordon, MS
JournalJournal of Chemical Theory and Computation
Volume11
Pagination5055-5061
Date Published11
Type of ArticleArticle
ISBN Number1549-9618
Accession NumberWOS:000364614000001
Keywordsapproximation, basis, distributed data interface, gaussian-type, molecular-orbital methods, organic-molecules
Abstract

The computational efficiency and energy-to-solution of several applications using the GAMESS quantum chemistry suite of codes is evaluated for 32-bit and 64-bit ARM-based computers, and compared to an x86 machine. The x86 system completes all benchmark computations more quickly than either ARM system and is the best choice to minimize time to solution. The ARM64 and ARM32 computational performances are similar to each other for Hartree-Fock and density functional theory energy calculations. However, for memory-intensive second-order perturbation theory energy and gradient computations the lower ARM32 read/write memory bandwidth results in computation times as much as 86% longer than on the ARM164 systern. The ARM32 system is more energy efficient than the x86 and ARM64 CPUs for all benchmarked methods, while the ARM64 CPU is more energy efficient than the x86 CPU for some core counts and molecular sizes.

DOI10.1021/acs.jctc.5b00713
Custom 1

Not AL