Low-complexity Concurrent Error Detection for convolution with Fast Fourier Transforms

Abstract

Abstract-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 purely for CED is significantly reduced. When compared with a conventional Sum Of Squares -Dual Modular Redundancy technique, the proposal provides similar single error coverage at significantly reduced computational complexity. For complex input sequences, the proposal provides reductions in the number of real multiplications of 60% and 33% for adaptive and fixed filters, respectively. For real input sequences, the reductions are 70% and 59%, respectively.