Title :
Fast block data processing via a new IIR digital filter structure
Author :
Nikias, Chrysostomos L.
Author_Institution :
University of Connecticut, Storrs, CT
fDate :
8/1/1984 12:00:00 AM
Abstract :
A new structure for realizing IIR digital filters is introduced based on the idea of processing sequences by blocks. It is shown that this structure exhibits high inherent parallelism that is ideally suited for VLSI implementation or multimicroprocessor systems. This enables high-speed processing with the number of multiplies and additions per output sample much less than those of the block-state or canonical filter realizations. The roundoff noise level in the output of the new filter structure is derived and compared to the noise levels of the block-state and canonical forms. Further, it is shown that the new filter structure will present no scaling problems if the canonical filter is scaled. Finally, the extension of the new filter structure to the realization of periodically time-varying digital filters is also presented.
Keywords :
Convolution; Data processing; Digital filters; Finite impulse response filter; Gold; IIR filters; Noise level; Parallel processing; Transfer functions; Very large scale integration;
Journal_Title :
Acoustics, Speech and Signal Processing, IEEE Transactions on
DOI :
10.1109/TASSP.1984.1164396