A fast scalable implementation of the two-dimensional triangular Discrete Element Method on a GPU platform

Zhang, Lin; Quigley, Steven F.; Chan, A. H. C.

doi:10.1016/j.advengsoft.2012.10.006

Cited by 30 publications

(14 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The GPU implementation of FDEM was presented by Zhang et al (2013). The GPU parallelization of the coupled FEM/DEM approach (CDEM) was described by Wang et al (2013).…”

Section: Introductionmentioning

confidence: 99%

Space decomposition based parallelization solutions for the combined finite–discrete element method in 2D

Lukas

D'Albano

Munjiza

2014

Journal of Rock Mechanics and Geotechnical Engineering

View full text Add to dashboard Cite

a b s t r a c tThe combined finiteediscrete element method (FDEM) belongs to a family of methods of computational mechanics of discontinua. The method is suitable for problems of discontinua, where particles are deformable and can fracture or fragment. The applications of FDEM have spread over a number of disciplines including rock mechanics, where problems like mining, mineral processing or rock blasting can be solved by employing FDEM. In this work, a novel approach for the parallelization of two-dimensional (2D) FDEM aiming at clusters and desktop computers is developed. Dynamic domain decomposition based parallelization solvers covering all aspects of FDEM have been developed. These have been implemented into the open source Y2D software package and have been tested on a PC cluster. The overall performance and scalability of the parallel code have been studied using numerical examples. The results obtained confirm the suitability of the parallel implementation for solving large scale problems.

show abstract

“…The GPU implementation of FDEM was presented by Zhang et al (2013). The GPU parallelization of the coupled FEM/DEM approach (CDEM) was described by Wang et al (2013).…”

Section: Introductionmentioning

confidence: 99%

Space decomposition based parallelization solutions for the combined finite–discrete element method in 2D

Lukas

D'Albano

Munjiza

2014

Journal of Rock Mechanics and Geotechnical Engineering

View full text Add to dashboard Cite

show abstract

“…In recent years, the computer performance has significantly improved, and the parallel computing has developed rapidly, which provides methods to enhance the efficiency of the engineering simulations. For use on a single computer, parallel strategies include the multi‐thread and CPU‐GPU heterogeneous computing , which have been widely used to improve the calculation speed of various numerical methods, for example, the finite element method (FEM) , boundary element method , distinct lattice spring model (DLSM) , discontinuous Galerkin method , DEM and so on. These applications have achieved significant results.…”

Section: Introductionmentioning

confidence: 99%

“…Zhao et al used both OpenMP and GPU to parallelise the DLSM code and found that the speedup factors were 4.68 for a quad‐core PC and 23.10 for a NVIDIA Geforce GTX580 GPU. Zhang et al presented a design for a two‐dimensional triangle DEM solver using the CUDA technique, which achieved a speedup factor of approximately 80. Wang et al parallelised the continuum‐based DEM on a GPU with CUDA, and the speedup factors ranged from approximately 100 to 400.…”

Section: Introductionmentioning

confidence: 99%

Investigation of highly efficient algorithms for solving linear equations in the discontinuous deformation analysis method

Sheng

Zhang

et al. 2015

Num Anal Meth Geomechanics

View full text Add to dashboard Cite

Large-scale engineering computing using the discontinuous deformation analysis (DDA) method is timeconsuming, which hinders the application of the DDA method. The simulation result of a typical numerical example indicates that the linear equation solver is a key factor that affects the efficiency of the DDA method. In this paper, highly efficient algorithms for solving linear equations are investigated, and two modifications of the DDA programme are presented. The first modification is a linear equation solver with high efficiency. The block Jacobi (BJ) iterative method and the block conjugate gradient with Jacobi preprocessing (Jacobi-PCG) iterative method are introduced, and the key operations are detailed, including the matrix-vector product and the diagonal matrix inversion. Another modification consists of a parallel linear equation solver, which is separately constructed based on the multi-thread and CPU-GPU heterogeneous platforms with OpenMP and CUDA, respectively. The simulation results from several numerical examples using the modified DDA programme demonstrate that the Jacobi-PCG is a better iterative method for largescale engineering computing and that adoptive parallel strategies can greatly enhance computational efficiency. Figure 17. Parallel speedup factor of the discontinuous deformation analysis models with multi-thread and CPU-GPU platforms. 484X. FU ET AL.

show abstract

“…Parallelization procedures utilize hardware in similar fashion: concurrent job execution on many processor cores working on a specific part of the domain with communication in-between. The usage of graphics processing units (GPUs) for both the DEM [32] and 2D coupled FEM/DEM [33] analysis has been explored. The GPU parallelization of the coupled FEM/DEM approach (CDEM) was described by Wang et al [33].…”

Section: Gpu Based Parallel Fdem For Analysis Of Cable Structuresmentioning

confidence: 99%

GPU based parallel FDEM for analysis of cable structures

2018

JCE

View full text Add to dashboard Cite

GPU based parallel FDEM for analysis of cable structuresA combined finite-discrete element method, adapted for the analysis of a parallel cable element model using graphic cards, is presented in the paper. The basic objective is to speed up sequential computation time by one or two orders of magnitude. Paralelni model kabela za grafičke kartice baziran na metodi konačno diskretnih elemenata U radu je prikazana adaptacija kombinirane metode konačno diskretnih elemenata za paralelni model kabelskog elementa pomoću grafičkih kartica. Osnovni cilj je ubrzanje proračunskog vremena serijskog koda za jedan ili dva reda veličine. Razvijeno rješenje je implementirano unutar slobodno dostupnog FDEM Y koda. Mjerenje performansi razvijenog rješenja kao i diskusija o tome prikazani su na jednostavnim primjerima. In der Arbeit wird die Anpassung der kombinierten Methode der finiten diskreten Elemente für ein paralleles Kabelmodell anhand von Grafikkarten dargestellt. Der Schwerpunkt lag dabei auf der Beschleunigung der Berechnungszeit des Seriencodes um eine oder zwei Größenordnungen. Die entwickelte Lösung wurde innerhalb der frei zugänglichen FDEM Y Codes integriert. An einfachen Beispielen wurden die Messung der Leistungen der entwickelten Lösung sowie entsprechende Diskussionen dargestellt.

show abstract

A fast scalable implementation of the two-dimensional triangular Discrete Element Method on a GPU platform

Cited by 30 publications

References 15 publications

Space decomposition based parallelization solutions for the combined finite–discrete element method in 2D

Space decomposition based parallelization solutions for the combined finite–discrete element method in 2D

Investigation of highly efficient algorithms for solving linear equations in the discontinuous deformation analysis method

GPU based parallel FDEM for analysis of cable structures

Contact Info

Product

Resources

About