원문정보
초록
영어
The proliferation of multimodal systems demands efficient management of heterogeneous computing resources. However, most GPU-centric frameworks still rely on static scheduling, resulting in unbalanced utilization and energy waste. This paper presents HERMES (Heterogeneous Efficient Resource Management and Execution Scheduling), an adaptive scheduling framework designed for efficient scheduling in heterogeneous multimodal AI systems. HERMES introduces HScore, a unified metric that quantifies heterogeneous efficiency by integrating performance (FPS) and power consumption. Experimental results on a ViT-based multimodal benchmark show that HERMES achieves up to 12.7% faster execution and 15.8% higher energy efficiency than static hybrid baselines, while maintaining balanced CPU–GPU utilization. These findings confirm that adaptive feedback scheduling significantly enhances both scalability and sustainability in multimodal AI systems.
목차
I. INTRODUCTION
II. METHODOLOGY
A. Overall Framework
B. Definition of Efficiency Metric (H-Score)
C. Algorithm Design
D. Summary
III. EXPERIMENTAL RESULTS AND DISCUSSION
A. Experimental Environment
B. Evaluation Metrics
C. Results and Analysis
D. Discussion
IV. CONCLUSION AND FUTURE WORK
REFERENCES