전기전자학회논문지 (Journal of IKEEE)

  • 제24권3호
  • /
  • Pages.797-802
  • /
  • 2020
  • /
  • 1226-7244(pISSN)
  • /
  • 2288-243X(eISSN)
한국전기전자학회 (Institute of Korean Electrical and Electronics Engineers)
권호 표지
DOI QR코드

DOI QR Code

공유 메모리 기반 시스토릭 어레이 FFT 프로세서 설계 및 구현

Design and Implementation Systolic Array FFT Processor Based on Shared Memory

  • Jeong, Dongmin (School of Electronics and Information Engineering, Korea Aerospace University) ;
  • Roh, yunseok (School of Electronics and Information Engineering, Korea Aerospace University) ;
  • Son, Hanna (School of Electronics and Information Engineering, Korea Aerospace University) ;
  • Jung, Yongchul (School of Electronics and Information Engineering, Korea Aerospace University) ;
  • Jung, Yunho (School of Electronics and Information Engineering, Korea Aerospace University)
  • 투고 : 2020.09.05
  • 심사 : 2020.09.21
  • 발행 : 2020.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 base-4 시스토릭 어레이 FFT 프로세서에서 사용되는 여러 메모리를 하나의 메모리로 공유함으로써 기존 보다 작은 메모리 면적의 FFT 프로세서의 설계 및 구현 결과를 제시한다. 메모리를 공유하여 면적이 줄어드는 장점이 생겼으며, 데이터의 입출력이 하나의 메모리에서 진행되므로 데이터의 흐름이 단순해졌다. 제시한 FFT 프로세서를 FPGA 디바이스 상에서 구현 및 검증하였으며, 구현 결과 4096-point FFT 기준 51,855개의 CLB LUT, 29,712개의 CLB registers, 8개의 block RAM tile과 450개의 DSP로 구현되었고, 최대 동작 주파수는 150MHz 인 것을 확인했으며 특히, 기존 base-4 시스토릭 어레이 구조 대비 메모리 면적이 65% 감소 가능함을 확인하였다.

In this paper, we presents the design and implementation results of the FFT processor, which supports 4096 points of operation with less memory by sharing several memory used in the base-4 systolic array FFT processor into one memory. Sharing memory provides the advantage of reducing the area, and also simplifies the flow of data as I/O of the data progresses in one memory. The presented FFT processor was implemented and verified on the FPGA device. The implementation resulted in 51,855 CLB LUTs, 29,712 CLB registers, 8 block RAM tiles and 450 DSPs, and confirmed that the memory area could be reduced by 65% compared to the existing base-4 systolic array structure.

키워드

참고문헌

  1. P. K. Meher, "Efficient Systolic Implementation of DFT Using a Low-Complexity Convolution-Like Formulation," in IEEE Transactions on Circuits and Systems II: Express Briefs, vol.53, no.8, pp.702-706, 2006. DOI: 10.1109/TCSII.2006.875379
  2. Hyesook Lim and E. E. Swartzlander, "Multidimensional systolic arrays for multidimensional DFTs," 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings, vol.6, pp.3276-3279, 1996. DOI: 10.1109/ICASSP.1996.550576
  3. J. G. Nash, "Computationally efficient systolic architecture for computing the discrete Fourier transform," in IEEE Transactions on Signal Processing, vol.53, no.12, pp.4640-4651, 2005. DOI: 10.1109/TSP.2005.859216
  4. J. G. Nash, "A High Performance Scalable FFT," 2007 IEEE Wireless Communications and Networking Conference, pp.2367-2372, 2007. DOI: 10.1109/WCNC.2007.442
  5. J. G. Nash, "A New Class of High Performance FFTs," 2007 IEEE International Conference on Acoustics, Speech and Signal Processing-ICASSP '07, vol.2, pp.22-24, 2007. DOI: 10.1109/ICASSP.2007.366162
  6. J. Greg Nash, "High-throughput programmable systolic array FFT architecture and FPGA implementations," 2014 International Conference on Computing, Networking and Communications (ICNC), pp.878-884, 2014. DOI: 10.1109/ICCNC.2014.6785453