Implementation of a prime factor FFT algorithm on CRAY-1
An implementation of a prime factor FFT algorithm on the CRAY-1 which adapts some of the developments to vector-processing scientific computers is described. First, the author considers the case in which many transformations are to be performed together, so that vectorization may be achieved simply by computing the transforms in parallel. Second, he addresses the more difficult problem of vectorizing a single transform. Finally, he uses timing measurements for the algorithm to estimate an appropriate value of Hockney's parameter \(n_{}\) on the CRAY-1.
- Implementation of a self-sorting in-place prime factor FFT algorithm
- A high-performance fast Fourier transform algorithm for the Cray-2
- Ultrahigh-performance FFTs for the CRAY-2 and CRAY Y-MP supercomputers
- FFT algorithms for prime transform sizes and their implementations on VAX, IBM3090VF, and IBM RS/6000
- FFT algorithms for vector computers
- Implementation of a self-sorting in-place prime factor FFT algorithm
- A segmented FFT algorithm for vector computers
- A new set of minimum-add small-n rotated DFT modules
- Parallel integration of ODEs based on convolution algorithms
- Further measurements of \((r_{\infty},n_{1/2})\) on the CRAY-1 and CRAY X-MP
- Nesting strategies for prime factor FFT algorithms
- Congruent Number Theta Coefficients to 1012
- A high-performance fast Fourier transform algorithm for the Cray-2
- A methodology for designing, modifying, and implementing Fourier transform algorithms on various architectures
- Ultrahigh-performance FFTs for the CRAY-2 and CRAY Y-MP supercomputers
This page was built for publication: Implementation of a prime factor FFT algorithm on CRAY-1
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1100875)
