Practical dynamic thermal management on Intel desktop computer

Fueled by increasing human appetite for high computing performance, semiconductor technology has now marched into the deep sub-micron era. As transistor size keeps shrinking, more and more transistors are integrated into a single chip. This has increased tremendously the power consumption and heat generation of IC chips. The rapidly growing heat dissipation greatly increases the packaging/cooling costs, and adversely affects the performance and reliability of a computing system. In addition, it also reduces the processor's life span and may even crash the entire computing system. Therefore, dynamic thermal management (DTM) is becoming a critical problem in modern computer system design. Extensive theoretical research has been conducted to study the DTM problem. However, most of them are based on theoretically idealized assumptions or simplified models. While these models and assumptions help to greatly simplify a complex problem and make it theoretically manageable, practical computer systems and applications must deal with many practical factors and details beyond these models or assumptions. The goal of our research was to develop a test platform that can be used to validate theoretical results on DTM under well-controlled conditions, to identify the limitations of existing theoretical results, and also to develop new and practical DTM techniques. This dissertation details the background and our research efforts in this endeavor. Specifically, in our research, we first developed a customized test platform based on an Intel desktop. We then tested a number of related theoretical works and examined their limitations under the practical hardware environment. With these limitations in mind, we developed a new reactive thermal management algorithm for single-core computing systems to optimize the throughput under a peak temperature constraint. We further extended our research to a multicore platform and developed an effective proactive DTM technique for throughput maximization on multicore processor based on task migration and dynamic voltage frequency scaling technique. The significance of our research lies in the fact that our research complements the current extensive theoretical research in dealing with increasingly critical thermal problems and enabling the continuous evolution of high performance computing systems.

Controls on sensible heat and latent energy fluxes from a short-hydroperiod Florida Everglades marsh

Little is known of energy balance in low latitude wetlands where there is a year-round growing season and a climate best defined by wet and dry seasons. The Florida Everglades is a highly managed and extensive subtropical wetland that exerts a substantial influence on the hydrology and climate of the south Florida region. However, the effects of seasonality and active water management on energy balance in the Everglades ecosystem are poorly understood. An eddy covariance and micrometeorological tower was established in a short-hydroperiod Everglades marsh to examine the dominant environmental controls on sensible heat (H) and latent energy (LE) fluxes, as well as the effects of seasonality on these parameters. Seasonality differentially affected H and LE fluxes in this marsh, such that H was principally dominant in the dry season and LE was strongly dominant in the wet season. The Bowen ratio was high for much of the dry season (1.5–2.4), but relatively low (H and LE fluxes across nearly all seasons and years (). However, the 2009 dry season LE data were not consistent with this relationship () because of low seasonal variation in LE following a prolonged end to the previous wet season. In addition to net radiation, H and LE fluxes were significantly related to soil volumetric water content (VWC), water depth, air temperature, and occasionally vapor pressure deficit. Given that VWC and water depth were determined in part by water management decisions, it is clear that human actions have the ability to influence the mode of energy dissipation from this ecosystem. Impending modifications to water management under the Comprehensive Everglades Restoration Plan may shift the dominant turbulent flux from this ecosystem further toward LE, and this change will likely affect local hydrology and climate.