Server-Level Demonstration of Package-Integrated, Two-Phase Jet Impingement Cooling on AI Chipsets

Abstract The rapid growth of digitalization and data-driven technologies is driving large-scale deployment of data centers worldwide. As societies become increasingly data-hungry, the energy consumption of data centers continues to rise at an unprecedented rate, with a significant fraction of this energy being expended on thermal management and cooling infrastructure. Improving cooling efficiency has therefore become a critical challenge for the thermal management community, directly impacting both the sustainability and scala-bility of future computing systems. In this manuscript, we demonstrate an energy-efficient cooling solution based on chip-integrated two-phase cooling, which leverages liquid to vapor phase-change heat transfer to achieve high heat-flux dissipation at reduced pumping power and thermal resistance. This paper investigates an aggressive cooling architecture utilizing direct-on-die two-phase jet impingement on an NVIDIA Tesla V100 GPU. By eliminating the TIM and impinging the working fluid?R1233zd(E), a low-GWP (< 1) refrigerant?directly onto the silicon backside, the primary thermal bottleneck is removed. Experimental results demonstrate a remarkably low thermal resistance of 0.056 °C/W and a theoretical pumping power of only 0.172 W. The system exhibits superior ther- mal stability and rapid transient response compared to conventional air-cooled solutions. Furthermore, the reliability of the direct-exposure manifold was validated through 200 hours of continuous, stable operation. This study positions direct jet impingement as a highly efficient, compact, and sustainable solution for next-generation high-performance computing (HPC) environments.