INTELLIGENT HARDWARE MANAGEMENT FOR HIGH-PERFORMANCE FPGA-BASED APPROXIMATE MULTIPLICATION IN BIOINFORMATICS COMPUTING

Abstract

The rapid growth of genomic, molecular, and bioinformatics data has increased the demand for intelligent hardware management solutions capable of supporting computationally intensive biological applications with high performance and energy efficiency. This study presents an FPGA-based Additive Multiplication Module (AMM) designed to improve computational performance through optimized approximate arithmetic and efficient hardware resource management. The proposed architecture integrates Dadda reduction, modified 3:2 and 4:2 compressor structures, selective bit truncation, approximate partial-product accumulation, multiplexer-based compressors, and mirror multiplier optimization to reduce hardware complexity, execution latency, logic utilization, and power consumption while maintaining acceptable computational accuracy. The design was implemented using Verilog HDL and synthesized on an Artix-7 FPGA to evaluate its computational and resource management capabilities. Experimental results demonstrate significant improvements in operating frequency, area efficiency, throughput, and energy consumption compared with conventional multiplier architectures. The proposed framework enables efficient acceleration of multiplication-intensive operations commonly encountered in genomic sequence analysis, molecular signal processing, bioinformatics algorithms, and AI-driven biological data analytics. By combining intelligent hardware management with scalable FPGA implementation, the proposed approach offers a reliable and energy-efficient computing platform for advanced bioinformatics applications, embedded biomedical systems, and next-generation computational intelligence environments requiring high-speed data processing and optimized resource utilization.