A Spectrum Analysis Algorithm Based on GPU

DOI

10.2991/csece-18.2018.2How to use a DOI?

Keywords

GPU spectrum analysis; parallel computing; mixed base FFT;STFT

Abstract

Considering the requirement of spectrum analysis, the parallel spectrum analysis algorithm is designed for a software radio platform built on the spectrum analyzer, where CPU is the controller and GPU is the baseband processor. The software platform is combined with the GPU processor, making it possible that the data required massive calculation in the RF collector is transferred to the GPU to process, which has the ability of powerful parallel computing. The key part of this paper is the parallel optimization of mixed-radix FFT algorithm and STFT algorithm, in which the data memory and memory allocation are also improved. Results show that the simulation via CUDA programming is superior than CPU processing.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Kunyuan Xu
AU  - Yanhua Jin
AU  - Fangyuan Zhao
AU  - Haoran Ma
PY  - 2018/02
DA  - 2018/02
TI  - A Spectrum Analysis Algorithm Based on GPU
BT  - Proceedings of the 2018 International Conference on Computer Science, Electronics and Communication Engineering (CSECE 2018)
PB  - Atlantis Press
SP  - 5
EP  - 9
SN  - 2352-538X
UR  - https://doi.org/10.2991/csece-18.2018.2
DO  - 10.2991/csece-18.2018.2
ID  - Xu2018/02
ER  -