Fitting FFT onto an Energy Efficient Massively Parallel Architecture

Abstract : 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.
Type de document :
Communication dans un congrès
Hisham El-Shishiny and Erven Rohou. IFMT'10 - Second International Forum on Next Generation Multicore/Manycore Technologies, Jun 2010, Saint Malo, France. ACM, 2010
Liste complète des métadonnées

https://hal.inria.fr/inria-00492915
Contributeur : Ist Rennes <>
Soumis le : jeudi 17 juin 2010 - 14:12:15
Dernière modification le : jeudi 14 juin 2018 - 11:00:02

Identifiants

  • HAL Id : inria-00492915, version 1

Collections

Citation

István Lorentz, Mihaela Malita, Razvan Andonie. Fitting FFT onto an Energy Efficient Massively Parallel Architecture. Hisham El-Shishiny and Erven Rohou. IFMT'10 - Second International Forum on Next Generation Multicore/Manycore Technologies, Jun 2010, Saint Malo, France. ACM, 2010. 〈inria-00492915〉

Partager

Métriques

Consultations de la notice

17