Health & Environmental Research Online (HERO)


Print Feedback Export to File
7013819 
Journal Article 
A Multi-GPU Accelerated Parallel Domain Decomposition One-Step Leapfrog ADI-FDTD 
Liu, S; Zou, Bin; Zhang, L; Ren, S; , 
2020 
IEEE Antennas and Wireless Propagation Letters
ISSN: 1548-5757 
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC 
PISCATAWAY 
19 
5 
816-820 
WOS:000535611900020 
In this letter, a multi-GPU accelerated one-step leapfrog alternative-direction-implicit finite-difference time-domain (ADI-FDTD) based on parallel SPIKE tridiagonal systems solver is presented. Through our algorithm simplification and execution optimization, online computation and data exchange between GPUs of the SPIKE solver is dramatically reduced. In the simulation experiment, the bistatic RCS of the benchmark model calculated by the proposed method is consistent with the solutions given by one-step leapfrog ADI-FDTD based on Thomas tridiagonal systems solver and Yee's FDTD. Compared with the single-GPU-based implementation, the multi-GPU accelerated one-step leapfrog ADI-FDTD solver can achieve 3.94x speedups at most when executed at a workstation with 4 GPUs. 
Graphics processing units; Finite difference methods; Time-domain analysis; Acceleration; Parallel processing; Matrix decomposition; Manganese; Alternative-direction-implicit finite-difference time-domain (ADI-FDTD); FDTD; general purpose graphics processing unit; leapfrog