Parallel vector multidimensional slant, Haar, and Walsh-Hadamard transforms
- 45 Downloads
A new factorization for the slant matrix is developed. The structure of the proposed slant algorithm based on the new factorization is suitable for vector and parallel processing of one- and two-dimensional slant transforms. A unified approach to compute the Walsh-Hadamard, Haar, and slant transforms is presented. Multitasking with four processors is implemented to improve the speed performance of two-dimensional transforms. Simulation results on CRAY X-MP/48 using single-processor and multiprocessors are also included.
Key WordsParallel vector processing slant transform Haar transform and Walsh-Hadamard transform
Unable to display preview. Download preview PDF.
- 1.William K. Pratt, “Slant Transform Image Coding,”IEEE Trans. Comm., vol. Com-22, 1974.Google Scholar
- 3.M. El-Sharkawy, W. Tsang, and M. Aburdene, “Parallel Hadamard Transform with Transputers,”Int. J. Mini Microcomputers, vol. 12, 1990, pp. 20–24.Google Scholar
- 4.Harry C. Andrews,Computer Techniques in Image Processing, New York: Academic Press, 1970.Google Scholar
- 5.Bernard J. Fino, “A Unified Treatment of Discrete Fast Unitary Transforms,”SIAM J. Comput., vol. 6, 1977.Google Scholar
- 6.M. El-Sharkawy, W. Tsang, and M. Aburdene, “Vector Processing of Orthogonal Transforms for Digital Signal Processing Application,”Proc. 1989 Summer Computer Simulation Conf., 1989, pp. 203–210.Google Scholar
- 7.Paul N. Swarztrauber, “FFT Algorithms for Vector Computers,”Parallel Computing, 1984, pp. 45–63.Google Scholar
- 8.David G. Korn, “Computing the Fast Fourier Transform on a Vector Computer,”Math. Comp. vol. 33, 1979, pp. 977–992.Google Scholar
- 9.Ramesh C. Agarwal and James W. Cooley, “Vectorized Mixed Radix Discrete Fourier Transform Algorithms,”Proc. IEEE, vol. 75, 1987.Google Scholar
- 10.W.P. Petersen, “Vector FORTRAN for Numerical Problems on CRAY-1,”Comm. ACM, vol. 26, 1983.Google Scholar