Share Email Print
cover

Proceedings Paper

New encoding/decoding methods for designing fault-tolerant matrix operations
Author(s): Dali L. Tao; Y. S. Han; Carlos R.P. Hartmann
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The algorithm-based fault tolerance (ABFT) provides low-cost error protection for VLSI processor arrays used in real-time digital signal processing. Several ABFT techniques (weighted check-sum) have be proposed to design fault-tolerant LU decomposition, QR decomposition, and matrix inversion. In these schemes, encoding/decoding uses either multiplication or division so that overhead is high. In this paper, we propose new encoding/decoding methods for designing fault-tolerant matrix operations. Since the new encoding/decoding methods use only additions and subtractions, the overhead of a fault-tolerant processor array can be drastically reduced.

Paper Details

Date Published: 30 November 1992
PDF: 12 pages
Proc. SPIE 1770, Advanced Signal Processing Algorithms, Architectures, and Implementations III, (30 November 1992); doi: 10.1117/12.130918
Show Author Affiliations
Dali L. Tao, SUNY/Stony Brook (United States)
Y. S. Han, Syracuse Univ. (United States)
Carlos R.P. Hartmann, Syracuse Univ. (United States)


Published in SPIE Proceedings Vol. 1770:
Advanced Signal Processing Algorithms, Architectures, and Implementations III
Franklin T. Luk, Editor(s)

© SPIE. Terms of Use
Back to Top