In an orthogonal frequency division multiplexing (OFDM)-based digital transmitter, the inverse fast Fourier transform (Ifft) processing unit consumes the most hardware area and power, especially because of the twiddle...
详细信息
In an orthogonal frequency division multiplexing (OFDM)-based digital transmitter, the inverse fast Fourier transform (Ifft) processing unit consumes the most hardware area and power, especially because of the twiddle multipliers in the cooley-tukey-baseddecimation-infrequency (DIF) Ifftarchitecture. This work concentrates on the trivial multiplications in the input stage of the Ifft unit and replaces them by the proposed 'pass-logic'. These replacements can be possible because the inputs are bitwise with binary-phase shift keying (PSK) or qudrature-PSK digital modulation. The input stage of DIF-fft for 8 to 128 points (N) were implemented with multipliers and 'pass-logics'. The performance improvements (PIs) of the proposed fft/Ifft implementation have been analysed. For a 64-point fft in FPGA, the number of slices was reduced by 9% and the total power by 6.5%. The same implementation on an ASIC, consumed 28% less power and 27% lesser gates. In 128-point implementation, these PIs are more than those of the 64-point, thus PI is in upward trend as N increases. A chip for fft processing as per IEEE 802.11a specifications (64-point, 16-bit data) is designed with pass-logics, which uses 24 947 gates and consumes 6.45 mW at 1.8 V, 20 MHz in 0.18 mu m 1P6M CMOS process.
暂无评论