Parallel vector multidimensional slant,Haar, and Walsh-Hadamard transforms

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.This work is supported in part by the National Science Foundation, Pittsburgh Supercomputing Center and by the PEW Science Education Program.