The real-time TDDFT code “Quantum Dissipative Dynamics” on a GPU
Dinh PM, Heraud J, Estaña A, Vincendon M, Reinhard PG, Suraud E (2024)
Publication Type: Journal article
Publication year: 2024
Journal
Book Volume: 295
Article Number: 108947
DOI: 10.1016/j.cpc.2023.108947
Abstract
We present the second release of the real-time time-dependent density functional theory code “Quantum Dissipative Dynamics” (QDD). It augments the first version [1] by a parallelization on a GPU coded with CUDA fortran. The extension focuses on the dynamical part only because this is the most time consuming part when applying the QDD code. The performance of the new GPU implementation as compared to OpenMP parallelization has been tested and checked on a couple of small sodium clusters and small covalent molecules. OpenMP parallelization allows a speed-up by one order of magnitude in average, as compared to a sequential computation. The use of a GPU permits a gain of an additional order of magnitude. The performance gain outweighs even the larger energy consumption of a GPU. The impressive speed-up opens the door for more demanding applications, not affordable before.
Authors with CRIS profile
Involved external institutions
France (FR)How to cite
APA:
Dinh, P.M., Heraud, J., Estaña, A., Vincendon, M., Reinhard, P.-G., & Suraud, E. (2024). The real-time TDDFT code “Quantum Dissipative Dynamics” on a GPU. Computer Physics Communications, 295. https://dx.doi.org/10.1016/j.cpc.2023.108947
MLA:
Dinh, P. M., et al. "The real-time TDDFT code “Quantum Dissipative Dynamics” on a GPU." Computer Physics Communications 295 (2024).
BibTeX: Download