Power Agnostic Technique for Efficient Temperature Estimation of Multicore Embedded System

Devendra Rai, Hoeseok Yang, Iuliana Bacivarov, and Lothar Thiele.
In CASES, pages 61-70, 2012.
Temperature plays an increasingly important role in the overall performance of a computing system and in its reliability. Increased availability of multi- and many-core systems provides an opportunity to manage the overall temperature pro le of the system by cleverly designing the application-to core mapping and the associated scheduling policies. There are clear penalties associated with an uncontrolled temperature pro le: a core reaching a critical temperature usually activates built in shut down or voltage and/or frequency scaling mechanisms to cool it down, thereby leading to unplanned performance loss of the system. Similarly, deep thermal cycles with high frequency lead to severe deterioration in the overall reliability of the system. Design space exploration tools are often used to optimize binding and scheduling choices based on a given set of constraints and objectives. These exploration tools rely on fast and accurate temperature estimation techniques. We argue that the currently available techniques are not an ideal t to design space exploration tools, and suggest a system level technique which is based on application fingerprinting. It does not need any information about the processor floorplan, the physical and thermal structure, or about power consumption. Instead, its temperature estimation is based on a set of application-specific calibration runs and associated temperature measurements using available built-in sensors. Using extensive experimental studies, we show that our technique can estimate temperature on all cores of a system to within 5 °C, and is three orders of magnitude faster than state of the art numerical simulators like Hotspot.