CUDA環境における高性能3次元FFT  [in Japanese] High Performance 3-D FFT in CUDA Environment  [in Japanese]

Access this Article

Search this Article

Abstract

NVIDIAの最新GPUがサポートするCUDA環境では共有メモリを用いたスレッド間のデータ共有と,自由度が高いメモリアクセスが可能である.我々はこのCUDA環境に適した高性能3次元FFTアルゴリズムを提案する.GeForce 8シリーズのGPUを用いた3次元FFTにおいて,CUFFTライブラリ1.1と比較して3.1∼3.3倍,最大79.5GFLOPSの演算性能を達成した.CUDA environment, which is supported in latest NVIDIA GPUs, allows data sharing between threads using shared memory, and also provides more flexible memory accesses. We propose a high performance 3-D FFT algorithm for the CUDA environment. Using GeForce 8 series GPUs, we achieved a high performance up to 79.5GFLOPS at 3-D FFT, which is from 3.1 to 3.3 times the performance compared with the performance of CUFFT library 1.1.

CUDA environment, which is supported in latest NVIDIA GPUs, allows data sharing between threads using shared memory, and also provides more flexible memory accesses. We propose a high performance 3-D FFT algorithm for the CUDA environment. Using GeForce 8 series GPUs, we achieved a high performance up to 79.5GFLOPS at 3-D FFT, which is from 3.1 to 3.3 times the performance compared with the performance of CUFFT library 1.1.

Journal

  • 情報処理学会論文誌コンピューティングシステム(ACS)

    情報処理学会論文誌コンピューティングシステム(ACS) 1(2), 231-239, 2008-08-21

    情報処理学会

Cited by:  1

Keywords

Codes

  • NII Article ID (NAID)
    110007990187
  • NII NACSIS-CAT ID (NCID)
    AA11833852
  • Text Lang
    JPN
  • Article Type
    Journal Article
  • ISSN
    1882-7829
  • NDL Article ID
    024351758
  • NDL Call No.
    YH247-812
  • Data Source
    CJPref  NDL  NII-ELS  IPSJ 
Page Top