Now showing 1 - 2 of 2
  • Publication
    Efficient Concurrent Error Detection and Correction of Soft Errors in NTT-based Convolutions
    (The Institution of Engineering and Technology, 2009-06) ; ; ;
    A system for soft error detection and correction is proposed for digital Integrated Circuit (IC) implementation of convolution. The convolution is implemented in a Residue NumberSystem using Fermat Number Theoretic Transforms. The flexibility afforded by the Modified Overlap Technique in allowing transforms of differing lengths in a convolution makes it possible to easily detect and correct soft errors by means of a Single Redundant Channel and pattern matching technique. The proposed system gives area reductions in the majority of cases examined, when compared with Triple Modular Redundancy. In the case of large (e.g. 28 and 32 bit) word lengths, the proposed system provides area reductions of up to 30%.
  • Publication
    Low-Complexity Concurrent Error Detection for Convolution with Fast Fourier Transforms
    In this paper, a novel low-complexity Concurrent Error Detection (CED) technique for Fast Fourier Transform-based convolution is proposed. The technique is based on checking the equivalence of the results of time and frequency domain calculations of the first sample of the circular convolution of the two convolution input blocks and of two consecutive output blocks. The approach provides low computational complexity since it re-uses the results of the convolution computation for CED checking. Hence, the number of extra calculations needed purely for CED is significantly reduced. When compared with a conventional Sum Of Squares - Dual Modular Redundancy technique, the proposal provides similar error coverage for isolated soft errors at significantly reduced computational complexity. For an input sequence consisting of complex numbers, the proposal reduces the number of real multiplications required for CED in adaptive and fixed filters by 60% and 45%, respectively. For input sequences consisting of real numbers, the reductions are 66% and 54%, respectively.