The presence of graphics processors (GPUs) in supercomputers constantly increased in the past decade. Finite-difference time-domain (FDTD) and discontinuous Galerkin time-domain (DGTD) are traditionally used on GPUs for their scalability; however, the limitations of past hardware required particular care in the implementation to obtain good performance. In this work, we discuss an implementation of DGTD for Maxwell's equations on modern GPUs, and we assess its performance on the simulation of an electrostatic discharge.

Electrostatic discharge simulation using a {GPU}-accelerated {DGTD} solver targeting modern graphics processors / Cicuttin, Matteo; Royer, Anthony; Binde, Peter; Geuzaine, Christophe. - In: IEEE TRANSACTIONS ON MAGNETICS. - ISSN 0018-9464. - ELETTRONICO. - 58:9(2022), pp. 1-4. [10.1109/tmag.2022.3179309]

Electrostatic discharge simulation using a {GPU}-accelerated {DGTD} solver targeting modern graphics processors

Matteo Cicuttin;
2022

Abstract

The presence of graphics processors (GPUs) in supercomputers constantly increased in the past decade. Finite-difference time-domain (FDTD) and discontinuous Galerkin time-domain (DGTD) are traditionally used on GPUs for their scalability; however, the limitations of past hardware required particular care in the implementation to obtain good performance. In this work, we discuss an implementation of DGTD for Maxwell's equations on modern GPUs, and we assess its performance on the simulation of an electrostatic discharge.
File in questo prodotto:
File Dimensione Formato  
Electrostatic Discharge Simulation Using a GPU-Accelerated DGTD Solver Targeting Modern Graphics Processors.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.16 MB
Formato Adobe PDF
1.16 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2978985