In this paper, we present a distributed arithmetic (DA) formulation of the computation of discrete wavelet transform (DWT) using 9/7 filters, and mapped that into bit-parallel and bit-serial architectures for high-throughput and low-hardware implementations, respectively. The bit-serial structure processes the bit-slices of input vector in serial manner for low-hardware solution, while the bit-parallel structure processes all the bit-slices in parallel for high-throughput computation. The bit-parallel structure has 100% hardware utilization efficiency. Compared with the existing multiplierless structures, the proposed structures offer significantly higher throughput rate and involve less area-delay product.
Published in:
Integrated Circuits, ISIC '09. Proceedings of the 2009 12th International Symposium on
Date of Conference: 14-16 Dec. 2009