Login | Register

Accelerated parallel computation of field quantities for the boundary element method applied to stress analysis using multi-core CPUs, GPUs and FPGAs


Accelerated parallel computation of field quantities for the boundary element method applied to stress analysis using multi-core CPUs, GPUs and FPGAs

Gu, Junjie and Zsaki, Attila Michael (2018) Accelerated parallel computation of field quantities for the boundary element method applied to stress analysis using multi-core CPUs, GPUs and FPGAs. Cogent Engineering, 5 (1). pp. 1-21. ISSN 2331-1916

[thumbnail of Zsaki-CogentEngineering-2018.pdf]
Text (application/pdf)
Zsaki-CogentEngineering-2018.pdf - Published Version
Available under License Creative Commons Attribution.

Official URL: http://dx.doi.org/10.1080/23311916.2018.1493713


Computation in engineering and science can often benefit from acceleration due to lengthy calculation times for certain classes of numerical models. This paper, using a practical example drawn from computational mechanics, formulates an accelerated boundary element algorithm that can be run in parallel on multi-core CPUs, GPUs and FPGAs. Although the computation of field quantities, such as displacements and stresses, using boundary elements is specific to mechanics, it can be used to highlight the strengths and weaknesses of using hardware acceleration. After the necessary equations were developed and the algorithmic implementation was summarized, each hardware platform was used to run a set of test cases. Both time-to-solution and relative speedup were used to quantify performance as compared to a serial implementation and to a multi-core implementation as well. Parameters, such as the number of threads in a workgroup and power consumption were considered and recommendations are given concerning the merits of each hardware accelerator.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Building, Civil and Environmental Engineering
Item Type:Article
Authors:Gu, Junjie and Zsaki, Attila Michael
Journal or Publication:Cogent Engineering
  • Concordia Open Access Author Fund
  • Concordia ENCS Faculty Graduate Support program (GSSP)
  • Natural Sciences and Engineering Research Council of Canada’s (NSERC) Discovery Grant program, Concordia University – NSERC Govt. Canada [grant number N01088]
Digital Object Identifier (DOI):10.1080/23311916.2018.1493713
Keywords:accelerated computation; GPU; FPGA; multi-core CPU; numerical stress analysis; OpenCL
ID Code:984120
Deposited By: Krista Alexander
Deposited On:08 Aug 2018 12:36
Last Modified:08 Aug 2018 12:36


Altera Inc. (2014). Altera quartus II. Retrieved from http://dl.altera.com/?edition=pro

Altera Inc. (2015). Altera quartus II – PowerPlay power analyzer tool. Retrieved from http://dl.altera.com/?edition=pro

Arrayfire. (2015). Explaining FP64 performance on GPUs. Retrieved from http://arrayfire.com/explaining-fp64-performance-on-gpus

Bischof, C. (2008). Parallel computing: Architectures, algorithms, and applications. Amsterdam,
The Netherlands: IOS Press.

Brebbia, C. A., & Partridge, P. W. (1992). Boundary elements in fluid dynamics. Netherlands: Springer.

Cooper, C. D., Bardhan, J. P., & Barba, L. A. (2014). A biomolecular electrostatics solver using Python, GPUs and boundary elements that can handle solvent-filled cavities and Stern layers. Computer Physics Communications, 185(3), 720–729. doi:10.1016/j.cpc.2013.10.028

Crouch, S. L., Starfield, A. M., & Rizzo, F. (1983). Boundary element methods in solid mechanics. Journal of Applied Mechanics, 50, 704. doi:10.1115/1.3167130

EVGA, GTX760. (2015). Retrieved from http://www.evga.com/Products/Specs/GPU.aspx?pn=D34D9B88-00D7-4F24-A92D-76ECD7BB6346

Gu, J. (2015). GPU-accelerated boundary element method for stress analysis of underground excavations (Master’s Thesis). Dept. of Building, Civil and Environmental Engineering, Concordia University, Montreal, QC, Canada

Haase, G., Schanz, M., & Vafai, S. (2012). Computing boundary element method’s matrices on GPU, in large-scale scientific computing. In I. Lirkov, S. Margenov, & J. Waśniewski (Eds.), 8th international conference, LSSC 2011, Sozopol, Bulgaria, June 6–10, 2011, Revised Selected Papers (pp. 343–350). Berlin, Heidelberg: Springer Berlin Heidelberg.

Intel. (2015a). OpenCL SDK. Retrieved from https://software.intel.com/en-us/intel-opencl

Intel. (2015b). Intel® Core™ i7-4770K Processor. Retrieved from http://ark.intel.com/products/75123/Intel-Core-i7-4770K-Processor-8M-Cache-up-to-3_90-GHz

Khronos Group. (2014). OpenCL. Retrieved from https://www.khronos.org/opencl/

Kythe, P. K. (1995). An introduction to boundary element methods. Boca Raton, FL: CRC press.

Lee, V. W., Kim, C., Chhugani, J., Deisher, M., Kim, D., Nguyen, A. D., … Singhal, R., 2010, Debunking the 100X GPU vs. CPU myth: an evaluation of throughput computing on CPU and GPU. Proceedings of the 37th annual international symposium on Computer architecture (pp. 451–460). ACM New York, NY, USA. doi:10.1177/1753193410364178

Microsoft. (2012). Visual studio ultimate. Retrieved from https://www.microsoft.com/en-ca/download/details.aspx?id=30682
Molavi Tabrizi, A., Goossens, S., Mehdizadeh Rahimi, A., Cooper, C. D., Knepley, M. G., & Bardhan, J. P. (2017). Extending the solvation-layer interface condition continuum electrostatic model to a linearized Poisson-Boltzmann solvent. Journal of Chemical Theory and Computation, 13(6), 2897–2914. doi:10.1021/acs.jctc.6b00832

NVIDIA. (2013). Tesla K40 GPU Active Accelerator. Retrieved from http://www.nvidia.com/content/PDF/kepler/Tesla-K40-Active-Board-Spec-BD-06949-001_v03.pdf

NVIDIA. (2014). CUDA Toolkit. Retrieved from http://docs.nvidia.com/cuda

Pacheco, P. S. (1997). Parallel programming with MPI. San Francisco, USA: Morgan Kaufmann.

Poljak, D., & Brebbia, C. A. (2005). Boundary element methods for electrical engineers (Advances in electrical engineering and electromagnetics). Ashurst, Southampton: WIT Press.

Starfield, A. M., & Cundall, P. A. (1988). Towards a methodology for rock mechanics modelling. International Journal of Rock Mechanics and Mining Sciences and Geomechanics Abstracts, 25(3), 99–106. doi:10.1016/0148-9062(88)92292-9

Terasic Inc. (2015). DE5-net user manual. Retrieved from http://www.terasic.com.tw/attachment/archive/526/DE5NET_OpenCL.pdf

Torky, A. A., & Rashed, Y. F. (2017). GPU acceleration of the boundary element method for shear-deformable bending of plates. Engineering Analysis with Boundary Elements, 74, 34–48. doi:10.1016/j.enganabound.2016.10.006

Zsaki, A. M. (2011, October 2–6) GPU-accelerated stress analysis in geomechanics. 64th Canadian Geotechnical Conference and 14th Pan-American Conference on Soil Mechanics and Geotechnical Engineering, Toronto, Canada
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top