Design of a Two-Phase Gravity-Driven Micro-Scale Thermosyphon Cooling System for High-Performance Computing Data Centers

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 flow to the heat sink, the system is called a closed-loop two-phase thermosyphon. Previous research work either focused on the development of large-scale proof-of-concept thermosyphon demonstrators, or on the development of numerical models able to simulate their operation. In this work, we present a new ultra-compact microscale thermosyphon design for high heat flux components. We manufactured a working 8 cm height prototype tailored for Virtex 7 FPGAs with a heat spreader area of 45 mm × 45 mm, and we validate its performance via measurements. The results are compared to our simulator and accurately match the thermal performance of the thermosyphon, with error of less than 3.5% . Our prototype is able to work over the full range of power of the Virtex7, dissipating up to 60 W of power while keeping chip temperature below 60 • C. The prototype will next be deployed in a 10 kW rack as part of an HPC prototype, with an expected Power Usage Effectiveness (PUE) below 1.05.

Enhancing Two-Phase Cooling Efficiency through Thermal-Aware Workload Mapping for Power-Hungry Servers

“…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.…”

“…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].…”

“…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.…”

“…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.…”

“…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.…”