Distributed Memory Parallelization for Fast Volume Integral Equation

Negi, YK and Viswarupa, V and Balakrishnan, N (2024) Distributed Memory Parallelization for Fast Volume Integral Equation. In: 2024 IEEE International Symposium on Antennas and Propagation and INC/USNCURSI Radio Science Meeting, AP-S/INC-USNC-URSI 2024, 14 July 2024through 19 July 2024, Florence, pp. 2595-2596.

PDF IEEE_ant_pro_soc_int_sym_2024.pdf - Published Version Restricted to Registered users only Download (325kB) | Request a copy

Abstract

In this paper, we show distributed memory parallelization for the Method of Moment fast volume integral equation using the task bucket algorithm. The fast volume integral equation is computed using Adaptive Cross Approximation based multi-level H-Matrix. The near-field and far-field block matrix is distributed using a task bucket. Individual MPI process computes the near and far-field matrices in each task bucket, and after computation, the matrices can be used to compute parallel matrix-vector products for iterative solutions. © 2024 IEEE.

Item Type:	Conference Paper
Publication:	IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to publisher.
Keywords:	Approximation algorithms; Choquet integral; Iterative methods; Matrix algebra, Adaptive cross approximation; Block matrix; Distributed Memory; Far-field; H matrix; Multilevels; Near fields; Near-far; Parallelizations; Volume integral equation, Integral equations
Department/Centre:	Division of Interdisciplinary Sciences > Supercomputer Education & Research Centre
Date Deposited:	16 Nov 2024 13:35
Last Modified:	16 Nov 2024 13:35
URI:	http://eprints.iisc.ac.in/id/eprint/86772

Actions (login required)

View Item