NUMERICAL LIBRARY USAGE IN BEM

Krzysztof Król

k.krol@pollub.pl
Lublin University of Technology, Institute of Electronics and Information Technology (Poland)

Maciej Pańczyk


Lublin University of Technology, Institute of Computer Science (Poland)

Abstract

Numerical library usage effectively reduce computation time and facilitate code programming. There are modified versions of popular BLAS and LAPACK libraries, dedicated to multi-core and distributed programming respectively PBLAS and SCALAPACK. Currently, a similar development applies to the GPU programming in two major implementations of GPGPU: NVIDIA CUDA and Kronos / ATI OpenCL. In the same time hybrid CPU-GPU versions of these libraries are intensively developed, a good example of that is MAGMA. This paper will present the effects of some of those libraries implementation used to solve the two-dimensional planar capacitor model by the boundary element method with constant boundary elements.


Keywords:

MEB, numerical libraries, CUDA, OpenCL

Labaki J., Ferreira L., Otávio S., Mesquita E.: Constant Boundary Elements on graphics hardware: a GPU-CPU complementary implementation, J. Braz. Soc. Mech. Sci. & Eng., vol. 33, 4/2011, pp. 475-482.
  Google Scholar

Sanders J. Kandrot E.: CUDA by Example: An Introduction to General-Purpose GPU Programming, Addison-Wesley, 2011.
  Google Scholar

Scarpino M.: OpenCl in Action: How to Accelerate Graphics and Computations;Manning Publications co., NY 2012.
  Google Scholar

Sikora J.: Boundary Element Method for Impedance and Optical Tomography, Oficyna Wydawnicza Politechniki Warszawskiej, Warszawa 2007.
  Google Scholar

Stpiczyński, P., Potiopa, J.: Solving a kind of boundary-value problem for ordinary differential equations using Fermi - the next generation CUDA computing architecture. J. Comp. Applied Mathematics 236, 3/2011, p. 384-393.
  Google Scholar

AMD OpenCL Zone: http://developer.amd.com/resources/heterogeneous-computing/opencl-zone, 2013.
  Google Scholar

BLAS Homepage: http://www.netlib.org/blas, 2013.
  Google Scholar

CULA Programmer’s guide: http://www.culatools.com/cula_dense_programmers_guide, 2013.
  Google Scholar

LAPACK Homepage: http://www.netlib.org/lapack, 2013.
  Google Scholar

KHRONOS OpenCL home page: http://www.khronos.org/opencl, 2013.
  Google Scholar

NVIDIA CUDA Developer Zone: http://developer.nvidia.com, 2013.
  Google Scholar


Published
2014-09-26

Cited by

Król, K., & Pańczyk, M. (2014). NUMERICAL LIBRARY USAGE IN BEM. Informatyka, Automatyka, Pomiary W Gospodarce I Ochronie Środowiska, 4(3), 46–49. https://doi.org/10.5604/20830157.1121359

Authors

Krzysztof Król 
k.krol@pollub.pl
Lublin University of Technology, Institute of Electronics and Information Technology Poland

Authors

Maciej Pańczyk 

Lublin University of Technology, Institute of Computer Science Poland

Statistics

Abstract views: 150
PDF downloads: 69