N4SID: subspace algorithms for the identification of combined deterministic-stochastic systems
Automatica (Journal of IFAC) - Special issue on statistical signal processing and control
An introduction to computational learning theory
An introduction to computational learning theory
Digital Control of Dynamic Systems
Digital Control of Dynamic Systems
Bayesian Averaging of Classifiers and the Overfitting Problem
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Temperature-aware microarchitecture
Proceedings of the 30th annual international symposium on Computer architecture
Dynamic Thermal Management for High-Performance Microprocessors
HPCA '01 Proceedings of the 7th International Symposium on High-Performance Computer Architecture
Compact thermal modeling for temperature-aware design
Proceedings of the 41st annual Design Automation Conference
A systematic method for functional unit power estimation in microprocessors
Proceedings of the 43rd annual Design Automation Conference
Efficient power modeling and software thermal sensing for runtime temperature monitoring
ACM Transactions on Design Automation of Electronic Systems (TODAES)
Architecture-level thermal behavioral characterization for multi-core microprocessors
Proceedings of the 2008 Asia and South Pacific Design Automation Conference
Hi-index | 0.00 |
This paper proposes a new architecture-level thermal modeling method to address the emerging thermal related analysis and optimization problem for high-performance multi-core microprocessor design. The new approach builds the thermal behavioral models from the measured or simulated thermal and power information at the architecture level for multi-core processors. Compared with existing behavioral thermal modeling algorithms, the proposed method can build the behavioral models from given arbitrary transient power and temperature waveforms used as the training data. Such an approach can make the modeling process much easier and less restrictive than before, and more amenable for practical measured data. The new method is based on a subspace identification method to build the thermal models, which first generates a Hankel matrix of Markov parameters, from which state matrices are obtained through minimum square optimization. To overcome the overfitting problems of the subspace method, the new method employs an over-fitting mitigation technique to improve model accuracy and predictive ability. Experimental results on a real quad-core microprocessor show that ThermSID is more accurate than the existing ThermPOF method. Furthermore, the proposed overfitting mitigation technique is shown to significantly improve modeling accuracy and predictability.