Researchers have developed X-OPM, a novel system for explainable automatic digital on-chip power modeling. This framework uses a human-in-the-loop workflow and combines tree-based models for feature interaction with linear models for prediction, aiming to improve generalization across unseen workloads. Evaluated on a C906 vector processor, X-OPM achieved an R^2 score above 0.93 with minimal area overhead, outperforming existing methods like APOLLO, COBIT, and standard MLPs. AI
IMPACT Enhances robustness and efficiency in digital VLSI circuits through improved power management.
RANK_REASON The cluster contains a research paper detailing a new technical framework for on-chip power modeling. [lever_c_demoted from research: ic=1 ai=0.7]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →