A measurement-based calibration approach for highly scalable timing and energy modeling of EdgeAI multi-core systems

Key Points

• The calibration approach demonstrates improved timing modeling efficiency in multi-core systems, enhancing overall performance.
• Increased scalability in energy modeling was achieved, yielding significant improvements in system optimization.
• Analysis utilized a measurement-based method to assess the efficiency of EdgeAI technologies across multiple cores.
• The findings highlight the potential for better performance in multi-core systems, suggesting further investigation is needed.