Nisar, Malik Zohaib and Ibrahim, Muhammad Sohail and Gorgin, Saeid and Usman, Muhammad and Lee, Jeong-A. (2024) DSLR-CNN: Efficient CNN Acceleration Using Digit-Serial Left-to-Right Arithmetic. IEEE ACCESS, 12. pp. 174608-174622. ISSN 2169-3536
Full text not available from this repository. (Request a copy)Abstract
Digit-serial arithmetic has emerged as a viable approach for designing hardware accelerators, reducing interconnections, area utilization, and power consumption. However, conventional methods suffer from performance and latency issues. To address these challenges, we propose an accelerator design using left-to-right (LR) arithmetic, which performs computations in a most-significant digit first (MSDF) manner, enabling digit-level pipelining. This leads to substantial performance improvements and reduced latency. The processing engine is designed for convolutional neural networks (CNNs), which includes low-latency LR multipliers and adders for digit-level parallelism. The proposed DSLR-CNN is implemented in Verilog and synthesized with Synopsys design compiler using GSCL 45nm technology, the DSLR-CNN accelerator was evaluated on AlexNet, VGG-16, and ResNet-18 networks. Results show significant improvements across key performance evaluation metrics, including response time, peak performance, power consumption, operational intensity, area efficiency, and energy efficiency. The peak performance measured in GOPS of the proposed design is 4.37x to 569.11x higher than contemporary designs, and it achieved 3.58x to 44.75x higher peak energy efficiency (TOPS/W), outperforming conventional bit-serial designs.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | Arithmetic; Energy efficiency; Convolutional neural networks; Delays; Throughput; Power demand; Low latency communication; Filters; Convolution; Computational efficiency; Convolutional neural network accelerator; left-to-right arithmetic; digit-serial; most-significant digit first |
| Subjects: | 000 Computer science, information & general works > 004 Computer science |
| Divisions: | Informatics and Data Science > Department Computational Life Science > Chair of Image Analysis and Computer Vision (Prof. Dr.-Ing. Dorit Merhof) |
| Depositing User: | Dr. Gernot Deinzer |
| Date Deposited: | 03 Dec 2025 07:54 |
| Last Modified: | 03 Dec 2025 07:54 |
| URI: | https://pred.uni-regensburg.de/id/eprint/64331 |
Actions (login required)
 |
View Item |
