This paper will show an alternative method to compute the two-dimensional Discrete Fourier Transform. While current GPU Fourier transform libraries need a large buffer for storing ...
Daniel Kauker, Harald Sanftmann, Steffen Frey, Tho...
– Efficient implementations of the Discrete Fourier Transform (DFT) for GPUs provide good performance with large data sizes, but are not competitive with CPU code for small data ...
We present an implementation of general FFTs for graphics processing units (GPUs). Unlike most existing GPU FFT implementations, we handle both complex and real data of any size t...
This paper proposes a new memory system called shuffle memory. The shuffle memory is a generalization of transposition memory that has been widely used in 2-D Discrete Cosine Tran...
—Analytical models have been used to estimate optimal values for parameters such as tile sizes in the context of loop nests. However, important algorithms such as fast Fourier tr...
Basilio B. Fraguela, Yevgen Voronenko, Markus P&uu...