Design of Low Power and High-Speed MAC Unit for Digital Signal Processing Applications

Project Code :TVMAFE800

Objective

The Multiply-Accumulate (MAC) unit is a fundamental computational block in Digital Signal Processing architectures, critical for filtering, convolution, FFT, and neural network inference. Performance of the MAC unit in terms of speed and power directly determines the efficiency of the overall DSP system. This paper presents a low-power, high-speed MAC unit targeting DSP applications using a Vedic mathematics-based Urdhva-Tiryakbhyam multiplier integrated with a flag-driven Selective Partial Sum (SPS) adder that suppresses redundant carry propagation and minimizes switching activity

Abstract

The Multiply-Accumulate (MAC) unit is a fundamental computational block in Digital Signal Processing architectures, critical for filtering, convolution, FFT, and neural network inference. Performance of the MAC unit in terms of speed and power directly determines the efficiency of the overall DSP system. This paper presents a low-power, high-speed MAC unit targeting DSP applications using a Vedic mathematics-based Urdhva-Tiryakbhyam multiplier integrated with a flag-driven Selective Partial Sum (SPS) adder that suppresses redundant carry propagation and minimizes switching activity. Implemented in Verilog HDL and synthesized on a FPGA using Xilinx vivado , significantly outperforming conventional MAC architectures.

Keywords: MAC Unit, Multiply-Accumulate, Low Power, High Speed, DSP, Vedic Multiplier, FPGA, Urdhva-Tiryakbhyam

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.

Block Diagram

Specifications

Software Requirements

β€’ Xilinx Vivado

β€’ Verilog HDL / VHDL

Hardware Requirements

β€’ Xilinx FPGA (Basys-3 / Nexys A7)

β€’ Oscilloscope

β€’ Logic Analyzer

Learning Outcomes

β€’ MAC Architecture Design and Optimization

β€’ Vedic Multiplier Implementation

β€’ Low Power Adder Design Techniques

β€’ FPGA-Based DSP System Development

β€’ High-Speed Arithmetic for Signal Processing

 

Demo Video

mail-banner
call-banner
contact-banner
Request Video