Title :
Parallel implementation of the steepest descent fast multipole method (SDFMM) on a Beowulf cluster for subsurface sensing applications
Author :
Jiang, D. ; Meleis, W. ; El-Shenawee, M. ; Mizan, E. ; Ashouei, M. ; Rappaport, C.
Author_Institution :
Dept. of Electr. & Comput. Eng., Northeastern Univ., Boston, MA, USA
Abstract :
We present the parallel, MPI-based implementation of the SDFMM computer code using a thirty-two node Intel Pentium-based Beowulf cluster. The SDFMM is a fast algorithm that is a hybridization of the method of moments (MoMs), the fast multipole method (FMM), and the steepest descent integration path (SDP), which is used to solve large-scale linear systems of equations produced in electromagnetic scattering problems. An overall speedup of 7.2 has been achieved on the 32-processor Beowulf cluster and a significant reduced runtime is achieved on the 4-processor 667 MHz Alpha workstation.
Keywords :
application program interfaces; buried object detection; electromagnetic wave scattering; geophysics computing; method of moments; parallel algorithms; physics computing; remote sensing; workstation clusters; 4-processor Alpha workstation; EM scattering problems; Intel Pentium-based Beowulf cluster; MPI-based implementation; SDFMM computer code; electromagnetic scattering problems; fast algorithm; large-scale linear systems of equations; method of moments; parallel implementation; runtime reduction; steepest descent fast multipole method; steepest descent integration path; subsurface sensing applications; thirty two-node cluster; Application software; Clustering algorithms; Concurrent computing; Electromagnetic scattering; Equations; Linear systems; Moment methods; Rough surfaces; Sparse matrices; Surface roughness;
Journal_Title :
Microwave and Wireless Components Letters, IEEE
DOI :
10.1109/7260.975724
