SGAP: A Scatter-Gather Processing-in-Memory Architecture with Fixed-Point Reconfiguration for Energy-Efficient DNNs
ACM Transactions on Design Automation of Electronic Systems · 31.03.2027 · 32 (2) · 1-30
DOI: 10.1145/3827619 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Design Automation of Electronic Systems, online erschienen am 12.11.2026. Verfasst von Jihe Wang und 5 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Aeronautical Science Foundation of China, National Key Research and Development Program of China.
Abstract (Originalsprache)
Leveraging the robustness of deep neural networks (DNNs), fixed-point mixed-precision models have effectively reduced hardware costs in edge in-memory accelerators. However, existing studies on multipliers are poorly suited to mixed-precision models. On the one hand, most of them employ fixed bit-widths or offer only limited configurations, lacking the fine-grained reconfigurability required by mixed-precision models. On the other hand, layers with smaller retained bit-widths can tolerate larger multiplication errors to achieve lower hardware costs, as the inaccurate bits are discarded. However, existing approximate multipliers cannot achieve low-cost dynamic error control, resulting in this optimization potential being wasted. To address these issues, this study proposes a fixed-point approximate multiplier with fine-grained reconfigurability. By breaking full multiplication into small 2-bit/3-bit operations and discarding non-critical ones selectively, the proposed multiplier ensures high hardware utilization across varying bit-widths while enabling low-cost fine-grained error control. Building on this multiplier, a DDR5-oriented near-memory accelerator architecture is proposed, incorporating extended dynamic random-access memory (DRAM) commands and semi-SIMD scheduling schemes. Compared to state-of-the-art processing-in-memory (PIM) architectures, the proposed architecture achieves a reduction of 40.8% in area, 16.3% in power consumption, and 6.5% in latency, respectively.
Förderung
- National Natural Science Foundation of China
- Aeronautical Science Foundation of China
- National Key Research and Development Program of China
Zitieren
APA
Wang, J., Cao, J., Qiaoyuan, F., Wang, Z., An, J., & Wang, D. (2027). SGAP: A Scatter-Gather Processing-in-Memory Architecture with Fixed-Point Reconfiguration for Energy-Efficient DNNs. ACM Transactions on Design Automation of Electronic Systems, 32(2), 1-30. https://doi.org/10.1145/3827619
Vancouver
Wang J, Cao J, Qiaoyuan F, Wang Z, An J, Wang D. SGAP: A Scatter-Gather Processing-in-Memory Architecture with Fixed-Point Reconfiguration for Energy-Efficient DNNs. ACM Transactions on Design Automation of Electronic Systems. 2027;32(2):1-30. doi:10.1145/3827619
BibTeX
@article{Wang2027,
author = {Wang, Jihe and Cao, Jiawang and Qiaoyuan, Feilong and Wang, Zhaoqing and An, Jianfeng and Wang, Danghui},
title = {SGAP: A Scatter-Gather Processing-in-Memory Architecture with Fixed-Point Reconfiguration for Energy-Efficient DNNs},
journal = {ACM Transactions on Design Automation of Electronic Systems},
year = {2027},
volume = {32},
number = {2},
pages = {1--30},
doi = {10.1145/3827619}
}
EUVIMED