Abstract :

The Increasing Demand For High-performance And Energy-efficient Computing Systems Has Accelerated The Development Of Approximate Computing Techniques For Applications Where Minor Computational Inaccuracies Are Acceptable. Approximate Arithmetic Circuits Have Emerged As A Promising Solution For Reducing Power Consumption, Circuit Complexity, And Processing Latency In Error-resilient Applications Such As Image Processing, Machine Learning, Multimedia Systems, And Signal Processing. Among Various Design Approaches, Majority Logic Has Gained Significant Attention Due To Its Simplicity, Scalability, And Suitability For Emerging Nanotechnologies And High-speed Digital Architectures. This Study Presents Optimized Majority Logic Architectures For High-speed Approximate Arithmetic Processing With The Objective Of Improving Computational Efficiency While Minimizing Hardware Overhead. The Proposed Architecture Employs Optimized Majority Gate Configurations To Design Approximate Adders And Arithmetic Units Capable Of Achieving Reduced Propagation Delay, Lower Power Dissipation, And Compact Area Utilization. Advanced Logic Optimization Techniques Are Applied To Simplify Majority Gate Networks And Enhance Data Processing Speed Without Significantly Affecting Computational Accuracy. Performance Evaluation Is Conducted Using Key Metrics Such As Delay, Power Consumption, Area Utilization, Power-delay Product (PDP), And Approximation Error. Experimental Results Demonstrate That The Proposed Majority Logic Architecture Achieves Substantial Improvements In Processing Speed And Energy Efficiency Compared With Conventional Arithmetic Circuits While Maintaining Acceptable Accuracy Levels For Practical Applications. The Proposed Design Offers A Viable Solution For Next-generation Low-power And High-speed Computing Platforms, Contributing To The Advancement Of Approximate Arithmetic Processing In Modern Digital Systems.

Published:

15-11-2023

Issue:

Vol. 23 No. 11 (2023)

Page Nos:

268 - 278

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite