Project Summary Overview Increased power dissipation in computing devices has led to a sharp rise in thermal hotspots on computer chips, creating a vicious cycle where higher temperature brings higher leakage power, and higher power dissipation creates increased temperature, thereby leading to more thermal hotspots. To reduce additional power dissipation caused by high temperature, the current approaches seek to apply cooling mechanisms to remove heat aggressively, as well as devising management techniques to avoid thermal emergencies by slowing down heat generation. This proposal attempts to address the heat management problem using a fundamentally different approach rather than removing the heat or slowing down heat generation, we transform this heat into reusable energy. We propose a Thermal Energy Harvesting (TEHar) framework that will allow heat energy generated by computing devices to be recovered, transformed, and harvested efficiently, to achieve better energy efficiency. Intellectual Merit This research takes a fundamentally different approach by exploring possibilities in thermal energy harvesting techniques at the architectural level. It asks and seeks solutions for the following questions: Is the degree of spatial thermal gradients observed in computing platforms at all scales sustainable for thermal energy harvesting? How do we study the impact on performance, energy and reliability when we incorporate architectural energy harvesting in our computing infrastructure? How can we methodically and systematically find the maximum amount of energy that can be harvested in modern computing environment? TEHar is based on the interesting implication of thermal energy distribution of computing platforms: the temperature differences between the hottest and the coldest components can be more than tens of degrees, creating a steep spatial thermal gradient. We discover that, by leveraging the thermoelectric effects at the architectural level, the varying spatial thermal gradients created as a result of computations can be exploited to transform heat, which is otherwise going to be dissipated, into reusable energy. Therefore, the heat generated by the circuitry of the computing devices is not wasted but is rather harvested for reuse. Overall, this proposal explores the potential for energy harvestability, particularly in the steep thermal gradients commonly observed in computing systems, while also investigating applications that can reuse this recovered energy. Broader Impacts With increased levels of global warming, we need better energy management techniques in order to reduce our carbon footprint. However, current trends to squeeze more computing power, e.g., in the form of large data centers or mobile devices, stand in direct conflict to our ability to slow down demand for more energy. The shrinking of transistor sizes further exacerbates the problem of reduced energy efficiency. The TEHar solution proposed here is anticipated to not only reduce cooling expenses and ambient temperatures, but also increase energy utilization, device lifetime, and physical space utilization. Furthermore, the TEHar technology developed here can be applied to a broad range of computing devices, large or small. This energy harvesting research requires cross-disciplinary engagement in areas such as material engineering, VLSI architecture, system architecture, and mechanical engineering and will attract a diverse set of students. Overall, the engineering and scientific contributions will also have important societal impacts, including but not limited to, the broadening of ASUs engineering curriculum, the engagement of graduate as well as undergraduate research activities, the potential of creating high-school or middle-school scientific projects, and the increased representation of target underrepresented minorities in science and engineering. We wish to solicit support from the EAGER program, to provide the resources required to lay a solid foundational work of this potentially impactful research topic.
|Effective start/end date||1/1/14 → 12/31/17|
- National Science Foundation (NSF): $200,000.00