APPLICATION OF GPU PARALLEL COMPUTING FOR ACCELERATION OF FINITE ELEMENT METHOD BASED 3D RECONSTRUCTION ALGORITHMS IN ELECTRICAL CAPACITANCE TOMOGRAPHY
Abstract
With the increasing complexity and scale of industrial processes their visualization is becoming increasingly important. Especially popular are non-invasive methods, which do not interfere directly with the process. One of them
is the 3D Electrical Capacitance Tomography. It possesses however a serious flaw - in order to obtain a fast and accurate visualization requires application of computationally intensive algorithms. Especially non-linear reconstruction using Finite Element Method is a multistage, complex numerical task, requiring many linear algebra transformations on very large data sets. Such process, using traditional CPUs can take, depending on the used meshes, up to several hours. Consequently it is necessary to develop new solutions utilizing GPGPU (General Purpose Computations on Graphics Processing Units) techniques to accelerate the reconstruction algorithm. With the developed hybrid parallel computing architecture, based on sparse matrices, it is possible to perform tomographic calculations much faster using GPU and CPU simultaneously, both with Nvidia CUDA and OpenCL.
References
R. Wajman, R. Banasiak, Ł. Mazurkiewicz, T.
Dyakowski, D. Sankowski, Spatial imaging with 3D
capacitance measurements, Measurement Science
and Technology, Vol. 17, No. 8, pp. 2113-2118, ,
August 2006
M. Soleimani, Three-dimensional electrical capacitance
tomography imaging, Insight, Non-
Destructive Testing and Condition Monitoring, Vol.
, No. 10, pp. 613-617, 2006
W. Warsito, L-S. Fan, Development of 3-
Dimensional Electrical Capacitance Tomography
Based on Neural Network Multi-criterion Optimization
Image Reconstruction, proc. of 3rd
World Congress on Industrial Process Tomography
(Banff), pp. 942-947, 2003
M. Soleimani, C.N. Mitchell, R. Banasiak, R. Wajman,
A. Adler, Four-dimensional electrical capacitance
tomography imaging using experimental data,
Progress In Electromagnetics Research-PIER, Vol.
, pp. 171-186, 2009
W.Q. Yang, L. Peng, Image reconstruction algorithms
for electrical capacitance tomography, Institute
of Physics Publishing, 2002
R. Wajman, R. Banasiak, Ł. Mazurkiewicz, T.
Dyakowski, D. Sankowski, Spatial imaging with 3D
capacitance measurements, Measurement Science
and Technology, Vol. 17, No. 8, pp. 2113-2118, 2006
J. Sikora, Podstawy Metody Elementów Sko´nczonych:
Zagadnienia potencjalne, Wydawnictwo
IEL, 2008
M. Geveler, D. Ribbrock, D. G oddeke, P. Zajac, S.
Turek, Efficient Finite Element Geometric Multigrid
Solvers for Unstructured Grids on GPUs, Proceedings
of the The Second International Conference on
Parallel, Distributed, Grid and Cloud Computing
for Engineering (PARENG 2011), Ajaccio, Corsica,
France, 2011
J.W. Ruge, K. St uben, Algebraic Multigrid, Multigrid
Methods (Frontier in Applied Mathematics),
Society for industrial Mathematics, Ch. 4, pp. 73 -
, 1994
W.H. Press, S.A. Teukolsky, W.T. Vetterling, B.P.
Flannery, Numerical recipses in C++, Second Edition,
The Press Syndicate of the University of Cambridge,
D. Michels, Sparse-Matrix-CG-Solver in CUDA,
Proceedings of CESCG 2011: The 15th Central European
Seminar on Computer Graphics, 2011
B.D. Kirk, Programming Massively Parallel Processors:
A Hands-on Approach, San Francisco,
Morgan Kaufmann, 2010
M. Herlihy, The Art of Multiprocessor Programming,
San Francisco, Morgan Kaufmann, 2008
