High-speed 8/16/32-point DCT Architecture Using Fixed-rotation Adaptive CORDIC

In this paper, the high-speed Discrete Cosine Transform (DCT) architecture is presented using the Adaptive CORDIC (ACor) algorithm built with a fixed-rotation angle. The proposed method is implemented in six different versions corresponding to the number of DCT point, i.e., 8-point (8p), 16-point (16p), and 32-point (32p), and the number of ACor stages, i.e., 2-Stage (2S) and 3-Stage (3S). The implementations are built and verified on an Altera Stratix IV FPGA. The 2S designs of 8p-DCT, 16p-DCT, and 32p-DCT achieve the maximum operating frequencies of 179.86 MHz, 162.60 MHz, and 136.97 MHz, respectively. Moreover, the 2S-32p-DCT module is implemented in ASIC with the 65nm-SOTB CMOS technology. The synthesis shows that the core costs 47.2K gates and consumes about 0.68 mW while operating at 100 MHz clock rate. The 2S implementations of 8p-DCT, 16p-DCT, and 32p-DCT achieve four, five, and six adder-delay, mean-square-error of 1.403e-4, 2.029e-2, and 7.663e-2, and coding gain of 8.8108 dB, 9.0984 dB, and 9.2170 dB, respectively. In comparison with recent works, the proposed method achieves the best timing performances, good accuracy results, and adequate resources cost. � 2018 IEEE.