Entropy-based Thermal Sensor Placement and Temperature Reconstruction based on Adaptive Compressive Sensing Theory

TL;DR

This paper introduces an entropy-based sensor placement combined with adaptive compressive sensing to improve full-chip temperature reconstruction accuracy and hardware efficiency in multi-core systems.

Contribution

It proposes a novel entropy-based sensor placement strategy with adaptive measurement matrix adjustment for enhanced thermal sensing accuracy.

Findings

Reduces temperature reconstruction error by 18% to 95%.

Improves hardware efficiency by 5% to 514%.

Enhances dynamic temperature management in multi-core systems.

Abstract

This paper addresses the challenges of thermal sensor allocation and full-chip temperature reconstruction in multi-core systems by leveraging an entropy-based sensor placement strategy and an adaptive compressive sensing approach. By selecting sensor locations that capture diverse thermal behaviors and dynamically adjusting the measurement matrix, our method significantly enhances the accuracy of the full-chip temperature reconstruction. Experimental results demonstrate that our approach reduces full-chip temperature reconstruction error by 18% to 95%. In addition to the full-chip temperature reconstruction efficiency enhancement, our proposed method improves hardware efficiency by 5% to 514% over the related works. These findings highlight the potential of our method for more effective dynamic temperature management in future high-performance multi-core systems.