GPU-accelerated fast implementation of shortest path algorithm in the noise simulation analysis system

Autor:	Luwen Xu, Pengcheng Chen, Yuxiao Qiu, Anxin Zou
Rok vydání:	2020
Předmět:	Noise Computer science Algorithm Dijkstra's algorithm
Zdroj:	IOP Conference Series: Materials Science and Engineering. 768:072035
ISSN:	1757-899X 1757-8981
DOI:	10.1088/1757-899x/768/7/072035
Popis:	A graphics processing unit (GPU) framework for the computation of the noise level between the noise source and the receiving point in the noise simulation analysis system is presented. The calculation process of the noise level often encounters a problem of slow convergence, and the calculation amount is large due to problems such as weighted point diffusion, transformation of the potential energy matrix, and gradient degradation. To circumvent these limitations, we devise a GPU-accelerated algorithm to calculate the shortest distance between the noise source and the receiving point, which has been shown to perform 11 times faster than the CPU method. Compare test results between GPU method and CPU method in different mesh density scenarios while maintaining their same calculation accuracy.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::9cba755f244337579e85376bacde39bf https://doi.org/10.1088/1757-899x/768/7/072035 Zobrazit plný text záznamu