Title :
Parallel one- and two-dimensional FFTs on GPGPUs
Author :
Fallahpour, Mehrdad ; Lin, Chang-Hong ; Lin, Ming-Bo ; Chang, Chin-Yu
Author_Institution :
Dept. of Electron. Eng., Nat. Taiwan Univ. of Sceince & Technol., Taipei, Taiwan
Abstract :
This paper presents a method to map and implement the 1-D FFT on a GPGPU and extends the method to the 2-D FFT. Two approaches are used to maximize the performance. One is to localize data inside the caches of the GPGPU and the other is to properly assign threads and blocks to reach higher performance. The results show that our implementation is 3.62 times faster to perform 32M-point 1-D FFT and 4.89 times faster to perform 2-D FFT with 16k × 8k points, as compared to the FFTW on the 16-core MPI platform.
Keywords :
digital arithmetic; fast Fourier transforms; graphics processing units; message passing; 16-core MPI platform; 32M-point 1-D FFT; FFTW; GPGPU caches; data localization; parallel one-dimensional FFT; parallel two-dimensional FFT; Graphics processing unit; Instruction sets; Kernel; Memory management; Parallel processing; Synchronization; Writing; 1-D FFT; 2-D FFT; FFTW; GPGPU; MPI;
Conference_Titel :
Anti-Counterfeiting, Security and Identification (ASID), 2012 International Conference on
Conference_Location :
Taipei
Print_ISBN :
978-1-4673-2144-0
Electronic_ISBN :
2163-5048
DOI :
10.1109/ICASID.2012.6325347
