Performance analysis and optimization of three-dimensional FDTD on GPU using roofline model

DOI10.1016/J.CPC.2011.01.025MaRDI QIDQ1943133zbMATH OpenOpenAlexFDO

Authors Ki-Hwan Kim, Kyoungho Kim, Q.-Han Park

Publication date 15 March 2013

Published in Computer Physics Communications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.cpc.2011.01.025

zbMATH Keywords

compute unified device architecture (CUDA)finite-difference time-domain (FDTD)graphics processing unit (GPU)roof-line

Mathematics Subject Classification ID

Numerical algorithms for specific classes of architectures (65Y10) Software, source code, etc. for problems pertaining to optics and electromagnetic theory (78-04) Finite difference methods applied to problems in optics and electromagnetic theory (78M20)

Recommendations

• Parallel 3D finite-difference time-domain method on multi-GPU systems
• A research of GPU accelerating three-dimensional finite-difference time-domain for electromagnetic-field simulation based on OpenCL
• Finite-Difference in Time-Domain Scalable Implementations on CUDA and OpenCL
• Study on acceleration technique for ADI-FDTD algorithm based on GPU
• Parallelization of the finite-difference time-domain method for room acoustics modelling based on CUDA

Cited in

(8)

• Efficient memory access patterns for solving 3D Laplace equation on GPU
• Parallelization of the finite-difference time-domain method for room acoustics modelling based on CUDA
• IMPLEMENTATION OF THE LORENTZ–DRUDE MODEL INCORPORATED FDTD METHOD ON MULTIPLE GPUs FOR PLASMONICS APPLICATIONS
• Parallel 3D finite-difference time-domain method on multi-GPU systems
• Study on acceleration technique for ADI-FDTD algorithm based on GPU
• GPU-accelerated LOBPCG method with inexact null-space filtering for solving generalized eigenvalue problems in computational electromagnetics analysis with higher-order FEM
• Performance analysis of parallelized PSTD-FDTD method for large-scale electromagnetic simulation
• On optimization of finite-difference time-domain (FDTD) computation on heterogeneous and GPU clusters

Describes a project that uses

Uses Software

• CUDA

This page was built for publication: Performance analysis and optimization of three-dimensional FDTD on GPU using roofline model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1943133)