Accelerating a ray launching model using GPU with CUDA

Zhuangzhuang Dai, Robert J. Watson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The high computational cost of accurate deterministic wave propagation models often prevent them from being used in channel modelling. In this work, we present our experience of attempts to accelerate our 2.5D ray launching model using GPUs (Graphic Processing Units), which continue to grow in popularity due to their vast computation capability. At the heart of this trial is an implementation of a ray-surface intersection detection function, which was found to be the bottleneck of serial CPU computation, using NVIDIA's CUDA (Compute Unified Device Architecture). Various optimization efforts are made to obtain the best overall performance. The intersection detection function executes seven times faster on a large urban scenario after acceleration on a modest laptop GPU. This paper details the implementation of the CUDA-based intersection detection function and presents the acceleration results for different simulated environments.

Original languageEnglish
Title of host publicationProceedings of 12th European Conference on Antennas and Propagation (EuCAP), 2018
PublisherIET
Publication statusPublished - 1 Jan 2018
Event12th European Conference on Antennas and Propagation, EuCAP 2018 - London, UK United Kingdom
Duration: 9 Apr 201813 Apr 2018

Conference

Conference12th European Conference on Antennas and Propagation, EuCAP 2018
CountryUK United Kingdom
CityLondon
Period9/04/1813/04/18

Keywords

  • GPU
  • Propagation modelling acceleration
  • Ray-tracing

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Dai, Z., & Watson, R. J. (2018). Accelerating a ray launching model using GPU with CUDA. In Proceedings of 12th European Conference on Antennas and Propagation (EuCAP), 2018 IET.

Accelerating a ray launching model using GPU with CUDA. / Dai, Zhuangzhuang; Watson, Robert J.

Proceedings of 12th European Conference on Antennas and Propagation (EuCAP), 2018. IET, 2018.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Dai, Z & Watson, RJ 2018, Accelerating a ray launching model using GPU with CUDA. in Proceedings of 12th European Conference on Antennas and Propagation (EuCAP), 2018. IET, 12th European Conference on Antennas and Propagation, EuCAP 2018, London, UK United Kingdom, 9/04/18.
Dai Z, Watson RJ. Accelerating a ray launching model using GPU with CUDA. In Proceedings of 12th European Conference on Antennas and Propagation (EuCAP), 2018. IET. 2018
Dai, Zhuangzhuang ; Watson, Robert J. / Accelerating a ray launching model using GPU with CUDA. Proceedings of 12th European Conference on Antennas and Propagation (EuCAP), 2018. IET, 2018.
@inproceedings{9da03b5afb49454daf5e75f34cbcbbea,
title = "Accelerating a ray launching model using GPU with CUDA",
abstract = "The high computational cost of accurate deterministic wave propagation models often prevent them from being used in channel modelling. In this work, we present our experience of attempts to accelerate our 2.5D ray launching model using GPUs (Graphic Processing Units), which continue to grow in popularity due to their vast computation capability. At the heart of this trial is an implementation of a ray-surface intersection detection function, which was found to be the bottleneck of serial CPU computation, using NVIDIA's CUDA (Compute Unified Device Architecture). Various optimization efforts are made to obtain the best overall performance. The intersection detection function executes seven times faster on a large urban scenario after acceleration on a modest laptop GPU. This paper details the implementation of the CUDA-based intersection detection function and presents the acceleration results for different simulated environments.",
keywords = "GPU, Propagation modelling acceleration, Ray-tracing",
author = "Zhuangzhuang Dai and Watson, {Robert J.}",
year = "2018",
month = "1",
day = "1",
language = "English",
booktitle = "Proceedings of 12th European Conference on Antennas and Propagation (EuCAP), 2018",
publisher = "IET",

}

TY - GEN

T1 - Accelerating a ray launching model using GPU with CUDA

AU - Dai, Zhuangzhuang

AU - Watson, Robert J.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The high computational cost of accurate deterministic wave propagation models often prevent them from being used in channel modelling. In this work, we present our experience of attempts to accelerate our 2.5D ray launching model using GPUs (Graphic Processing Units), which continue to grow in popularity due to their vast computation capability. At the heart of this trial is an implementation of a ray-surface intersection detection function, which was found to be the bottleneck of serial CPU computation, using NVIDIA's CUDA (Compute Unified Device Architecture). Various optimization efforts are made to obtain the best overall performance. The intersection detection function executes seven times faster on a large urban scenario after acceleration on a modest laptop GPU. This paper details the implementation of the CUDA-based intersection detection function and presents the acceleration results for different simulated environments.

AB - The high computational cost of accurate deterministic wave propagation models often prevent them from being used in channel modelling. In this work, we present our experience of attempts to accelerate our 2.5D ray launching model using GPUs (Graphic Processing Units), which continue to grow in popularity due to their vast computation capability. At the heart of this trial is an implementation of a ray-surface intersection detection function, which was found to be the bottleneck of serial CPU computation, using NVIDIA's CUDA (Compute Unified Device Architecture). Various optimization efforts are made to obtain the best overall performance. The intersection detection function executes seven times faster on a large urban scenario after acceleration on a modest laptop GPU. This paper details the implementation of the CUDA-based intersection detection function and presents the acceleration results for different simulated environments.

KW - GPU

KW - Propagation modelling acceleration

KW - Ray-tracing

UR - http://www.scopus.com/inward/record.url?scp=85057313094&partnerID=8YFLogxK

M3 - Conference contribution

BT - Proceedings of 12th European Conference on Antennas and Propagation (EuCAP), 2018

PB - IET

ER -