@inproceedings{09300687c4a24af799f3712815bd70fd,
title = "An Asynchronous Parallel Implementation of Multilevel Fast Multipole Algorithm on GPU Cluster for 3D Electromagnetic Scattering Problems",
abstract = "This paper presents a CPU/GPU asynchronous computing pattern based improved parallel multilevel fast multipole algorithm (MLFMA) for 3D electromagnetic scattering problems on GPU Cluster. In the presented parallel implementation, the matrix assembly process of the MLFMA is decomposed into CPU execution and GPU execution two parts. The former is performed on CPU using OpenMP multi-threading programming model, while the latter is performed on GPU with CUDA programming model. The execution time between the two parts is overlapped by using the feature of asynchronous execution between CPU and GPU. The performance of the proposed parallel implementation is investigated in terms of accuracy and efficiency. Numerical results show that, with the proposed parallel approach, over 10% speed-up can be attained, compared with the original parallel implementation.",
keywords = "Asynchronous Computing, CUDA, Multilevel fast multipole algorithm, OpenMP, scattering",
author = "Xi, {Rong Ping} and He, {We Jia} and Yang, {Ming Lin} and Sheng, {Xin Qing}",
note = "Publisher Copyright: {\textcopyright} 2021 Applied Computational Electromagnetics Society (ACES).; 4th International Applied Computational Electromagnetics Society Symposium in China, ACES-China 2021 ; Conference date: 28-07-2021 Through 31-07-2021",
year = "2021",
month = jul,
day = "28",
doi = "10.23919/ACES-China52398.2021.9581392",
language = "English",
series = "2021 International Applied Computational Electromagnetics Society Symposium, ACES-China 2021, Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2021 International Applied Computational Electromagnetics Society Symposium, ACES-China 2021, Proceedings",
address = "United States",
}