Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering
K., Syed Rahaman
Unknown Affiliation
Computer Science & IT Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Hardware efficient multiplier design for deep learning processing unit V., Jean Shilpa; R., Anitha; S., Anusooya; P. K., Jawahar; E., Nithesh; S., Sairamsiva; K., Syed Rahaman
International Journal of Electrical and Computer Engineering (IJECE) Vol 15, No 6: December 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v15i6.pp5205-5214

Abstract

Deep learning models increasing computational requirements have increased the demand for specialized hardware architectures that can provide high performance while using less energy. Because of their high-power consumption, low throughput, and incapacity to handle real-time processing demands, general-purpose processors frequently fall short. In order to overcome these obstacles, this work introduces a hardware-efficient multiplier design for deep learning processing unit (DPU). To improve performance and energy efficiency, the suggested architecture combines low-power arithmetic circuits, parallel processing units, and optimized dataflow mechanisms. Neural network core operations, such as matrix computations and activation functions, are performed by dedicated hardware blocks. By minimizing data movement, an effective on-chip memory hierarchy lowers latency and power consumption. According to simulation results using industry-standard very large-scale integration (VLSI) tools, compared to traditional processors, there is a 25% decrease in latency, a 40% increase in computational throughput, and a 30% reduction in power consumption. Architecture’s scalability and modularity guarantee compatibility with a variety of deep learning applications, such as edge computing, autonomous systems, and internet of things devices.
Co-Authors E., Nithesh P. K., Jawahar R., Anitha S., Anusooya S., Sairamsiva V., Jean Shilpa