Universal Wavelet Kernel Implementation Using Reconfigurable Hardware

Designing a universal embedded hardware architecture for discrete wavelet transform (DWT) is a challenging problem due to the diversity among wavelet kernel filters. In this work, we present three different hardware architectures for implementing multiple wavelet kernels. The first scheme utilizes fixed, parallel hardware for all the required wavelet kernels whereas the second scheme employs a processing element (PE) based datapath that can be configured for multiple wavelet filters during run-time. The third scheme makes use of partial runtime configuration of FPGA units for dynamically programming any desired wavelet filter. We present FPGA synthesis results for simultaneous implementation of six different wavelets for the proposed methods. Performance analysis and comparison of area, timing and power results are presented for the Virtex-II Pro FPGA implementation.