Journal of Institute of Control, Robotics and Systems (제어로봇시스템학회논문지)

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지
DOI QR코드

DOI QR Code

GPU Accelerating Methods for Pease FFT Processing

Pease FFT 처리를 위한 GPU 가속 기법

  • Oh, Se-Chang (Dept. of Information and Communication, Sejong Cyber University) ;
  • Joo, Young-Bok (Department of Computer Science & Engineering, Korea University of Technology & Education) ;
  • Kwon, Oh-Young (Department of Computer Science & Engineering, Korea University of Technology & Education) ;
  • Huh, Kyung-Moo (Department of Electronic Engineering, Dankook University)
  • 오세창 (세종사이버대학교 정보통신학과) ;
  • 주영복 (한국기술교육대학교 컴퓨터공학부) ;
  • 권오영 (한국기술교육대학교 컴퓨터공학부) ;
  • 허경무 (단국대학교 전자공학과)
  • Received : 2013.08.20
  • Accepted : 2013.12.12
  • Published : 2014.01.01
Download PDF
⟨ Previous Next ⟩

Abstract

FFT (Fast Fourier Transform) has been widely used in various fields such as image processing, voice processing, physics, astronomy, applied mathematics and so forth. Much research has been conducted due to the importance of the FFT and recently new FFT algorithms using a GPU (Graphics Processing Unit) have been developed for the purpose of much faster processing. In this paper, the new optimal FFT algorithm using the Pease FFT algorithm has been proposed reflecting the hardware configuration of a GPGPU (General Purpose computing of GPU). According to the experiments, the proposed algorithm outperformed by between 3% to 43% compared to the CUFFT algorithm.

Keywords

References

  1. N. K. Govindaraju, B. Lloyd, Y. Dotsenko, B. Smith, and J. Manferdelli, "High performance discrete fourier transforms on graphics processors," Proc. Supercomputing (SC), pp. 1-12, 2008.
  2. F. Franchetti, M. Puschel, Y. Voronenko, S. Chellappa, and J. M. F. Moura, "Discrete fourier transform on multicores," IEEE Signal Processing Magazine, vo1. 26, no. 6, pp. 90-102, 2009. (http://users.ece.cmu.edu/-franzf/ papers/spmag09.pdf) https://doi.org/10.1109/MSP.2009.934155
  3. J. Nickolls, I. Buck, M. Garland, and K. Skadron, "Scalable parallel programming with CUDA," Queue, vol. 6, no. 2, pp. 40-53, Mar/Apr. 2008.
  4. NVIDIA, "GPU Computing SDK," https://developer.nvidia.com/gpu-computing-sdk
  5. V. Volkov and B. Kazian, "Fitting FFT onto the G80 Architecture," CS258 Final Project, UC Berkeley, 2008.
  6. Y. Dotsenko, S. S. Baghsorkhi, B. Lloyd, N. K. Govindaraju, "Auto-tuning of Fast Fourier Transform on Graphics Processors," PPoPP'11. Texas, USA, Feb. 2011.
  7. M. Frigo and S. G. Johnson, "The design and implementation of FFTW3," Proc. of the IEEE, vol. 93, no. 2, pp. 216-231, 2005. (http://www.fftw.org) https://doi.org/10.1109/JPROC.2004.840301
  8. NDVIDA, "CUFFT Library," https://developer.nvidia.com/cufft
  9. J. R. Johnson, "Pease FFT algortihm," Technical Report DU-MCS-98-01, Dept. of Math. and CS., Drexel University, USA, Nov. 1998
  10. D. B. Kirk and Wen-mei W. Hwu, Programming Massively Parallel Processors, Morgan Kaufmann, 2010.
  11. S. Xiao and W.-C. Feng, "Inter-Block GPU communication via fast barrier synchronization," IPDPS, pp. 1-12, Apr. 2010.
  12. http://www.realworldtech.com/fermi/3/
  13. Y. K. Kim, B. Y. Hyeon, Y. W. Cho, and K. S. Seo, "Robust tracking algorithm for moving object using Kalman filter and variable search window technique," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 18, no. 7, pp. 673-679, Jul. 2012. https://doi.org/10.5302/J.ICROS.2012.18.7.673
  14. Y. S. Hwang, H.-W. Kim, T. J. Kim, and J.-M. Lee, "Impulse noise removal of LRF for 3D map building using a hybrid median filter," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 18, no. 10, pp. 970-976, Oct. 2012. https://doi.org/10.5302/J.ICROS.2012.18.10.970