Adaptive Energy—Accuracy Trade-Offs in Configurable MAC Architectures for AI Acceleration
Electronics · 09.03.2026 · 15 (5) · 1129
DOI: 10.3390/electronics15051129 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 09.03.2026. Verfasst von Turki Alnuayri und 1 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Taibah University, Madinah, Kingdom of Saudi Arabia.
Abstract (Originalsprache)
Energy efficiency has become a primary bottleneck in hardware platforms supporting machine learning workloads, particularly as modern inference and training tasks demand sustained high-throughput computation. This challenge is further amplified in energy-harvesting and intermittently powered systems, where the available energy budget varies over time. This work introduces a run-time configurable multiply–accumulate (MAC) architecture that dynamically adjusts arithmetic precision to match instantaneous energy availability. The proposed design relies on an internally adaptive multiplier based on bit-level logic compression, enabling controlled modulation of power consumption while preserving numerical robustness. Crucially, the MAC maintains a fixed external operand interface, allowing for seamless precision adaptation without operand reformulation or datapath disruption. The architecture is implemented in System Verilog and evaluated using both ASIC synthesis in a 90 nm CMOS technology and FPGA deployment. Experimental results demonstrate approximately a fourfold improvement in power–delay product (PDP) relative to full-precision operation, with only limited degradation in inference accuracy.
Förderung
- Taibah University, Madinah, Kingdom of Saudi Arabia
Zitieren
APA
Alnuayri, T., & Haddadi, I. (2026). Adaptive Energy—Accuracy Trade-Offs in Configurable MAC Architectures for AI Acceleration. Electronics, 15(5), 1129. https://doi.org/10.3390/electronics15051129
Vancouver
Alnuayri T, Haddadi I. Adaptive Energy—Accuracy Trade-Offs in Configurable MAC Architectures for AI Acceleration. Electronics. 2026;15(5):1129. doi:10.3390/electronics15051129
BibTeX
@article{Alnuayri2026,
author = {Alnuayri, Turki and Haddadi, Ibrahim},
title = {Adaptive Energy—Accuracy Trade-Offs in Configurable MAC Architectures for AI Acceleration},
journal = {Electronics},
year = {2026},
volume = {15},
number = {5},
pages = {1129},
doi = {10.3390/electronics15051129}
}
EUVIMED