Portal de Periódicos da CAPES

High-Performance Architectures For Adaptive Filtering Based On The Gram-Schmidt Algorithm

1984; SPIE; Volume: 0495; Linguagem: Inglês

10.1117/12.944006

1996-756X

Kyle A. Gallivan, Charles E. Leiserson,

Photonic and Optical Devices

The difficulties in designing systolic processors can be reduced by applying the architectural transformations of code motion, retiming, slowdown, coalescing, parallel/serial compromises and partitioning to a more easily designed combinational or semisystolic form of the processor. In this paper, the use of these transformations and the attendant tradeoffs in the design of architectures for adaptive filtering based on the Gram-Schmidt algorithm are considered. A modification to the classical Gram-Schmidt algorithm which eliminates the use of division under certain assumptions is suggested. Also, size and speed statistics are given for a projected .5 micron VHSIC implementation of the processor.