Standard

On the Improved Performance of VLPL-GPU Plasma Simulation Code. / Snytnikov, A. V.; Pukhov, A. M.; Lavrentiev, M. M.

In: Lobachevskii Journal of Mathematics, Vol. 46, No. 8, 2025, p. 3815-3821.

Research output: Contribution to journal › Article › peer-review

Harvard

Snytnikov, AV, Pukhov, AM & Lavrentiev, MM 2025, 'On the Improved Performance of VLPL-GPU Plasma Simulation Code', Lobachevskii Journal of Mathematics, vol. 46, no. 8, pp. 3815-3821. https://doi.org/10.1134/S199508022561029X

APA

Snytnikov, A. V., Pukhov, A. M., & Lavrentiev, M. M. (2025). On the Improved Performance of VLPL-GPU Plasma Simulation Code. Lobachevskii Journal of Mathematics, 46(8), 3815-3821. https://doi.org/10.1134/S199508022561029X

Vancouver

Snytnikov AV, Pukhov AM, Lavrentiev MM. On the Improved Performance of VLPL-GPU Plasma Simulation Code. Lobachevskii Journal of Mathematics. 2025;46(8):3815-3821. doi: 10.1134/S199508022561029X

Author

Snytnikov, A. V. ; Pukhov, A. M. ; Lavrentiev, M. M. / On the Improved Performance of VLPL-GPU Plasma Simulation Code. In: Lobachevskii Journal of Mathematics. 2025 ; Vol. 46, No. 8. pp. 3815-3821.

BibTeX

@article{38c6b7db038c40ac9d6b20bac7973163,
title = "On the Improved Performance of VLPL-GPU Plasma Simulation Code",
abstract = "Abstract: The GPU version of Q-VLPL3D code was improved by replacing the FFT Poisson solver by solver from MAGMA library. Also the Particle-In-Cell method implementation based on CUDA surfaces was rewritten using just ordinary GPU memory. This resulted in performance of 1.5 PFLOPS during particle push with Nvidia A100 and 4.5 TFLOPS during electromagnetic field evaluation.",
keywords = "GPU computing, beam-plasma interaction, particle-in-cell method, plasma wakefield",
author = "Snytnikov, {A. V.} and Pukhov, {A. M.} and Lavrentiev, {M. M.}",
note = "Snytnikov, A.V., Pukhov, A.M. & Lavrentiev, M.M. On the Improved Performance of VLPL-GPU Plasma Simulation Code. Lobachevskii J Math 46, 3815–3821 (2025). https://doi.org/10.1134/S199508022561029X",
year = "2025",
doi = "10.1134/S199508022561029X",
language = "English",
volume = "46",
pages = "3815--3821",
journal = "Lobachevskii Journal of Mathematics",
issn = "1995-0802",
publisher = "ФГБУ {"}Издательство {"}Наука{"}",
number = "8",

}

RIS

TY - JOUR

T1 - On the Improved Performance of VLPL-GPU Plasma Simulation Code

AU - Snytnikov, A. V.

AU - Pukhov, A. M.

AU - Lavrentiev, M. M.

N1 - Snytnikov, A.V., Pukhov, A.M. & Lavrentiev, M.M. On the Improved Performance of VLPL-GPU Plasma Simulation Code. Lobachevskii J Math 46, 3815–3821 (2025). https://doi.org/10.1134/S199508022561029X

PY - 2025

Y1 - 2025

N2 - Abstract: The GPU version of Q-VLPL3D code was improved by replacing the FFT Poisson solver by solver from MAGMA library. Also the Particle-In-Cell method implementation based on CUDA surfaces was rewritten using just ordinary GPU memory. This resulted in performance of 1.5 PFLOPS during particle push with Nvidia A100 and 4.5 TFLOPS during electromagnetic field evaluation.

AB - Abstract: The GPU version of Q-VLPL3D code was improved by replacing the FFT Poisson solver by solver from MAGMA library. Also the Particle-In-Cell method implementation based on CUDA surfaces was rewritten using just ordinary GPU memory. This resulted in performance of 1.5 PFLOPS during particle push with Nvidia A100 and 4.5 TFLOPS during electromagnetic field evaluation.

KW - GPU computing

KW - beam-plasma interaction

KW - particle-in-cell method

KW - plasma wakefield

UR - https://www.mendeley.com/catalogue/cbf6f5a5-87a5-30dc-ba5e-546b9b4a3bba/

UR - https://elibrary.ru/item.asp?id=88772142

U2 - 10.1134/S199508022561029X

DO - 10.1134/S199508022561029X

M3 - Article

VL - 46

SP - 3815

EP - 3821

JO - Lobachevskii Journal of Mathematics

JF - Lobachevskii Journal of Mathematics

SN - 1995-0802

IS - 8

ER -

ID: 74217314