The FFT on a GPU

By Kenneth Moreland, Edward Angel. SIGGRAPH/EUROGRAPHICS Conference On Graphics Hardware, 2003

396 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

MR image reconstruction using the GPU (2006, unknown): “For the GPU-based FFT, Moreland et al. 8 presented the ﬁrst implementation with the performance being slower than the FFTW library.”
Brook for GPUs: Stream Computing on Graphics Hardware (2004, methodology): “We also outperform Moreland and Angel’s NVIDIA specific implementation [2003] by the same margin.”
Medical image processing on the GPU - Past, present and future (2013, background): “Two of the earliest examples of FFT based filtering on a GPU were presented in 2003 (Moreland and Angel, 2003; Mitchell et al., 2003).”
Computational Physics on Graphics Processing Units (2012, result): “Despite being heavily non-local, much work has been done to improve the FFT algorithm and make it cache efficient [19,20,21,22,23], so it is possible to achieve a 20-fold speed up over the standard CPU FFTW or a 5-fold speedup when compared to a highly optimised MKL implementation.”