Abstract:Next-generation High-Performance Computing (HPC) systems need to provide outstanding performance with unprecedented energy efficiency while maintaining servers at safe thermal conditions. Air cooling presents important limitations when employed in HPC infrastructures. Instead, two-phase onchip cooling combines small footprint area and large heat exchange surface of micro-channels together with extremely high heat transfer performance, and allows for waste heat recovery. When relying on gravity to drive the flo… Show more
“…Previous thermosyphon prototypes such as [15], however, had a very large footprint area (1m ⇥ 1m) making them impractical in commercial servers. Nonetheless, recent work by [16] and [8] led to the design of micro-scale thermosyphons which can be placed directly on top of a CPU. Such a design, hence, necessitates careful evaluation of thermosyphon as a promising cooling device for different types of servers, which has not been performed so far in the literature.…”
Section: A Data Center Cooling Methodsmentioning
confidence: 99%
“…Authors in [8] evaluate the thermosyphon efficiency considering a uniform heat flux over the whole chip. However, this is not a realistic assumption for current applications and CPUs, as different workload mappings lead to non-uniform heat flux, which ultimately cause hot spots and spatial thermal gradients [20].…”
Section: B Motivational Examplementioning
confidence: 99%
“…One of the most recent technologies proposed for efficiently cooling servers is a micro-scale gravity-driven two-phase thermosyphon [8]. Since a thermosyphon is placed on top of the processor package, in contrast to inter-layer cooling, it does not require any changes in design and fabrication of existing processors.…”
Section: Introductionmentioning
confidence: 99%
“…Since a thermosyphon is placed on top of the processor package, in contrast to inter-layer cooling, it does not require any changes in design and fabrication of existing processors. The thermosyphon designed and manufactured in [8] achieves a PUE of 1.05. Thus, such a design, if industrialized in a way that fully exploits all its potential, can save more money than any other cooling systems.…”
Section: Introductionmentioning
confidence: 99%
“…Apart from mechanical hardware design and manufacturing challenges [8], platform-and workload-awareness play a significant role in thermosyphon efficiency for removing high heat fluxes. This, in return, can enhance performance metrics of power-hungry servers.…”
The power density and, consequently, power hungriness of server processors is growing by the day. Traditional air cooling systems fail to cope with such high heat densities, whereas single-phase liquid-cooling still requires high mass flowrate, high pumping power, and large facility size. On the contrary, in a micro-scale gravity-driven thermosyphon attached on top of a processor, the refrigerant, absorbing the heat, turns into a two-phase mixture. The vapor-liquid mixture exchanges heat with a coolant at the condenser side, turns back to liquid state, and descends thanks to gravity, eliminating the need for pumping power. However, similar to other cooling technologies, thermosyphon efficiency can considerably vary with respect to workload performance requirements and thermal profile, in addition to the platform features, such as packaging and die floorplan. In this work, we first address the workload-and platform-aware design of a two-phase thermosyphon. Then, we propose a thermal-aware workload mapping strategy considering the potential and limitations of a two-phase thermosyphon to further minimize hot spots and spatial thermal gradients. Our experiments, performed on an 8-core Intel Xeon E5 CPU reveal, on average, up to 10 C reduction in thermal hot spots, and 45% reduction in the maximum spatial thermal gradient on the die. Moreover, our design and mapping strategy are able to decrease the chiller cooling power at least by 45%.
“…Previous thermosyphon prototypes such as [15], however, had a very large footprint area (1m ⇥ 1m) making them impractical in commercial servers. Nonetheless, recent work by [16] and [8] led to the design of micro-scale thermosyphons which can be placed directly on top of a CPU. Such a design, hence, necessitates careful evaluation of thermosyphon as a promising cooling device for different types of servers, which has not been performed so far in the literature.…”
Section: A Data Center Cooling Methodsmentioning
confidence: 99%
“…Authors in [8] evaluate the thermosyphon efficiency considering a uniform heat flux over the whole chip. However, this is not a realistic assumption for current applications and CPUs, as different workload mappings lead to non-uniform heat flux, which ultimately cause hot spots and spatial thermal gradients [20].…”
Section: B Motivational Examplementioning
confidence: 99%
“…One of the most recent technologies proposed for efficiently cooling servers is a micro-scale gravity-driven two-phase thermosyphon [8]. Since a thermosyphon is placed on top of the processor package, in contrast to inter-layer cooling, it does not require any changes in design and fabrication of existing processors.…”
Section: Introductionmentioning
confidence: 99%
“…Since a thermosyphon is placed on top of the processor package, in contrast to inter-layer cooling, it does not require any changes in design and fabrication of existing processors. The thermosyphon designed and manufactured in [8] achieves a PUE of 1.05. Thus, such a design, if industrialized in a way that fully exploits all its potential, can save more money than any other cooling systems.…”
Section: Introductionmentioning
confidence: 99%
“…Apart from mechanical hardware design and manufacturing challenges [8], platform-and workload-awareness play a significant role in thermosyphon efficiency for removing high heat fluxes. This, in return, can enhance performance metrics of power-hungry servers.…”
The power density and, consequently, power hungriness of server processors is growing by the day. Traditional air cooling systems fail to cope with such high heat densities, whereas single-phase liquid-cooling still requires high mass flowrate, high pumping power, and large facility size. On the contrary, in a micro-scale gravity-driven thermosyphon attached on top of a processor, the refrigerant, absorbing the heat, turns into a two-phase mixture. The vapor-liquid mixture exchanges heat with a coolant at the condenser side, turns back to liquid state, and descends thanks to gravity, eliminating the need for pumping power. However, similar to other cooling technologies, thermosyphon efficiency can considerably vary with respect to workload performance requirements and thermal profile, in addition to the platform features, such as packaging and die floorplan. In this work, we first address the workload-and platform-aware design of a two-phase thermosyphon. Then, we propose a thermal-aware workload mapping strategy considering the potential and limitations of a two-phase thermosyphon to further minimize hot spots and spatial thermal gradients. Our experiments, performed on an 8-core Intel Xeon E5 CPU reveal, on average, up to 10 C reduction in thermal hot spots, and 45% reduction in the maximum spatial thermal gradient on the die. Moreover, our design and mapping strategy are able to decrease the chiller cooling power at least by 45%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.