Modern microprocessors utilise embedded thermal sensors to continuously monitor the chip's temperature during runtime. However, the overheating locations change temporally and spatially depending on the various workloads running on the chip. Furthermore, on-chip thermal sensor readings are highly affected by noise due to fabrication fluctuations and randomness, which makes the task of thermal monitoring particularly challenging. In this study, the authors first establish overheating detection models to address the thermal sensor allocation problem under two different conditions when the on-chip thermal sensor observations are corrupted by noise. On this basis, a heuristic method based on genetic algorithm is proposed to find a near-optimal thermal sensor allocation solution, which can make overheating detection probability significantly improved with a greatly reduced execution time. They also propose a hybrid algorithm to identify the optimal thermal sensor placement for each individual chip block or component. Moreover, they develop an oil-based cooling system and utilise infrared thermal imaging techniques to capture the thermal traces of a real dual-core microprocessor when running various workloads. The experiments demonstrate that the authors' proposed thermal sensor allocation methods obviously outperform several common allocation approaches in terms of overheating detection, which can provide an accurate and reliable thermal monitoring.

No abstract

No abstract