Energy-Efficient Computing Architectures for Edge Multimodal AI

A Cross-Layer Approach to Adaptive Inference and Efficient System Design
Erscheinungsjahr 2026
ISBN: 978-981-9267-99-6
Verlag: Springer

Buch, Englisch, 213 Seiten, Format (B × H): 155 mm x 235 mm

This monograph addresses the critical efficiency gap between the theoretical accuracy of multimodal deep neural networks and their deployment cost on resource-constrained edge platforms. It identifies a common root cause—multi-layered "System Rigidity"—that leads to the crisis of "Dark Intelligence," where edge devices cannot sustain their theoretical AI capabilities due to strict thermal and power limits.

To dismantle this rigidity, the book pioneers the paradigm of Energy-Proportional Intelligence (EPI), ensuring that a system's energy consumption scales strictly in proportion to the intrinsic cognitive complexity of the input data. The book presents a comprehensive, full-stack approach: it begins with a novel benchmark suite (MMBench) that reveals physical workload characteristics and bottlenecks. It then introduces model-layer adaptive inference techniques (MMExit, MMBypass) that dynamically reduce computation, scheduling-layer runtime optimizations (CPM, A²) that manage power and heterogeneous accelerators under strict constraints, and architecture-layer modality gating designs (SMG, AMG) that proactively cut sensing and preprocessing costs.

Readers will gain a cohesive cross-layer methodology and practical techniques to make multimodal systems accurate, fast, and energy-efficient on edge devices. Prerequisites include a graduate-level familiarity with computer architecture, operating systems, and machine learning.

Zielgruppe

Research

Autoren/Hrsg.

Hou, Xiaofeng

Liu, Jiacheng

Li, Chao

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
• Mathematik | Informatik EDV | Informatik Betriebssysteme
• Mathematik | Informatik EDV | Informatik Technische Informatik

Inhaltsverzeichnis

- Chapter 1 Introduction.- Chapter 2 Related Works.- Chapter 3 A Full-Stack Benchmark for Multimodal Computing Characterization.- Chapter 4 Adaptive Multimodal Inference Through Early Exiting.- Chapter 5 Agile Execution Throttling under Runtime Constraints.- Chapter 6 Decoupled Architecture through Modality Gating.- Chapter 7 Conclusion and Future Directions.

Über Autor(innen)

Xiaofeng Hou is currently an Associate Professor in the School of Computer Science at Shanghai Jiao Tong University. She received her Ph.D. degree from Shanghai Jiao Tong University in 2020. Her research mainly focuses on high-performance and energy-efficient architectures and systems for intelligent computing centers. She is an IEEE Senior member.

Jiacheng Liu is currently an Associate Professor in the Global Institute of Future Technology at Shanghai Jiao Tong University. He received his Ph.D. degree in 2022 from Shanghai Jiao Tong University. His research interests include efficient data processing, machine learning algorithms, and intelligent computing systems.

Chao Li is a Full Professor in the School of Computer Science at Shanghai Jiao Tong University. He received his Ph.D. degree from the University of Florida in 2014. His research mainly focuses on computer architecture, datacenter-scale computing, and emerging computing systems. He is a senior member of IEEE and ACM.