372
IRUS Total
Downloads
  Altmetric

Accelerated finite element elastodynamic simulations using the GPU

File Description SizeFormat 
paperSubmitted.pdfAccepted version1.65 MBAdobe PDFView/Open
Title: Accelerated finite element elastodynamic simulations using the GPU
Authors: Huthwaite, P
Item Type: Journal Article
Abstract: An approach is developed to perform explicit time domain finite element simulations of elastodynamic problems on the graphical processing unit, using Nvidiaʼs CUDA. Of critical importance for this problem is the arrangement of nodes in memory, allowing data to be loaded efficiently and minimising communication between the independently executed blocks of threads. The initial stage of memory arrangement is partitioning the mesh; both a well established ‘greedy’ partitioner and a new, more efficient ‘aligned’ partitioner are investigated. A method is then developed to efficiently arrange the memory within each partition. The software is applied to three models from the fields of non-destructive testing, vibrations and geophysics, demonstrating a memory bandwidth of very close to the cardʼs maximum, reflecting the bandwidth-limited nature of the algorithm. Comparison with Abaqus, a widely used commercial CPU equivalent, validated the accuracy of the results and demonstrated a speed improvement of around two orders of magnitude. A software package, Pogo, incorporating these developments, is released open source, downloadable from http://www.pogo-fea.com/ to benefit the community.
Issue Date: 15-Jan-2014
Date of Acceptance: 9-Oct-2013
URI: http://hdl.handle.net/10044/1/28160
DOI: 10.1016/j.jcp.2013.10.017
ISSN: 0021-9991
Publisher: Elsevier
Start Page: 687
End Page: 707
Journal / Book Title: Journal of Computational Physics
Volume: 257
Issue: Part A
Copyright Statement: © 2013, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/
Keywords: Science & Technology
Technology
Physical Sciences
Computer Science, Interdisciplinary Applications
Physics, Mathematical
Computer Science
Physics
COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS
PHYSICS, MATHEMATICAL
Finite element
Ultrasound
Elastodynamic
Graphical processing unit
GPU
WAVE-PROPAGATION
GRAPHICS PROCESSORS
MESH GENERATION
FEM
IMPLEMENTATION
ALGORITHMS
DIFFERENCE
SOLVERS
CUDA
FDTD
Science & Technology
Technology
Physical Sciences
Computer Science, Interdisciplinary Applications
Physics, Mathematical
Computer Science
Physics
Finite element
Ultrasound
Elastodynamic
Graphical processing unit
GPU
WAVE-PROPAGATION
MESH GENERATION
FEM
SOLVERS
IMPLEMENTATION
DIFFERENCE
01 Mathematical Sciences
02 Physical Sciences
09 Engineering
Applied Mathematics
Publication Status: Published
Appears in Collections:Mechanical Engineering
Faculty of Engineering