Title :
Parallelization of a finite element code for 3D scattering
Author :
Chatterjee, A. ; Volakis, J.L. ; Windheiser, D. ; Hao, E.
Author_Institution :
Michigan Univ., Ann Arbor, MI, USA
fDate :
June 28 1993-July 2 1993
Abstract :
The authors present the implementation details of a FE-ABC (finite-element absorbing boundary condition) code and describe the numerical considerations involved in optimizing this code. The linear equation solver and the sparse matrix generation were parallelized on the KSR1 (Kendall Square Research) shared-address space distributed-cache architecture with substantial speedup. Benchmarking was also done on the CM-5 (Connection Machine) with encouraging results. The parallel version of the FE-ABC code was run for a 1.5/spl lambda/ /spl times/ 1/spl lambda/ /spl times/ 1/spl lambda/ pec inlet and the monostatic radar cross section compared with measured data for HH-polarization.<>
Keywords :
boundary-value problems; cache storage; distributed memory systems; electromagnetic wave scattering; finite element analysis; parallel programming; performance evaluation; radar cross-sections; sparse matrices; 3D scattering; HH-polarization; absorbing boundary condition; benchmarking; finite element code; linear equation solver; monostatic radar cross section; parallelization; shared-address space distributed-cache architecture; sparse matrix generation; Computer architecture; Electromagnetic fields; Electromagnetic radiation; Electromagnetic scattering; Equations; Finite element methods; Laboratories; Linear systems; Sparse matrices; Vectors;
Conference_Titel :
Antennas and Propagation Society International Symposium, 1993. AP-S. Digest
Conference_Location :
Ann Arbor, MI, USA
Print_ISBN :
0-7803-1246-5
DOI :
10.1109/APS.1993.385344
