Fitting FFT onto an Energy Efficient Massively Parallel Architecture
Résumé
We present novel implementations of the Fast Fourier Transform on the massively parallel Connex ArrayTM(CA) circuit. The Estimated performance is 19 GFlops (BenchFFT metric) of parallel computing 64 FFTs of size 1024, using 5 Watts. We compare the CA and NVIDIA's GTX 285 GPU performance. The CA is not a direct NVIDIA competitor, targeting a different application area. Considering its low power dissipation, the CA is a good solution for low cost mobile computing equipment, video processing, and multi-channel high-sampling audio processing.