Publication

Abstract : In this paper, an efficient parallel multiplier and accumulator (MAC) unit based on Vedic mathematics is presented. Vedic mathematics utilizes the Urdhva-tiryagbhyam sutra for the multiplier design. The proposed MAC architecture enhances the speed of operation while reducing the gate area and power dissipation. We also achieve improved delay with the help of Vedic encoder followed by the removal of accumulator stage by parallelizing the intermediate results feeding the input. Such pipelining of the midway results, prior to the final adder, has the effect of combining the accumulator stage with the partial product stage of the multiplier. Further, the overall computation speed of MAC unit is elevated by the efficient use of higher order compressors in the merged partial product compression and accumulator (PPCA) architecture. The area, timing and power reports show that, the critical path delay of the proposed design is significantly reduced and it outperforms the existing designs. We report an absolute improvement of 20-30% and 7-18% respectively for the 4-bit and 8-bit Vedic MAC units, in terms of its total circuit power, critical path delay and cell area. The architecture was synthesized using standard 90nm CMOS library and implemented on Altera's Cyclone II seriesFPGA.