In this paper the results of the acceleration of computations involved in analysing electromagnetic problems by means of the finite element method (FEM), obtained with graphics processors (GPU), are presented. A 4.7-fold acceleration was achieved thanks to the massive parallelization of the most time-consuming steps of FEM, namely finite-element matrix-generation and the solution of a sparse system of linear equations with the...

This letter proposes a novel projection technique for accelerating Finite Element Method simulations. The algorithm is based on the Second-order Arnoldi Method for Passive Order Reduction (SAPOR). It involves generation of two projection bases and thanks to this it is applicable to the systems of equations, which contain the quadratic frequency-dependence in the input term, that arise when projection is applied locally in the selected...

This paper presents an efficient technique for fast generation of sparse systems of linear equations arising in computational electromagnetics in a finite element method using higher order elements. The proposed approach employs a graphics processing unit (GPU) for both numerical integration and matrix assembly. The performance results obtained on a test platform consisting of a Fermi GPU (1x Tesla C2075) and a CPU (2x twelve-core...

The Spectral Finite Element Technique (SFEM) has Several Applications in the Sciences, Engineering, and Mathematics, which will be Covered in this Review Article. The Spectral Finite Element Method (SFEM) is a Variant of the Traditional Finite Element Method FEM that Makes use of Higher Order Basis Functions (FEM). One of the most Fundamental Numerical Techniques Employed in the Numerical Simulation is the SFEM, which Outperforms...

A novel technique of incorporating macromodels into finite element electromagnetic analysis of waveguide components is presented. Macromodels are generated by using a model order reduction algorithm (ENOR), which results in significant decrease of the number of variables, that describe the computational region. Proposed technique allows for using a few independent macromodels as well as to duplicating one macromodel in many subregions...