Research Progress on Liquid Cooling Technologies for High-Power and Large-Area AI Chips

With advances in artificial intelligence (AI), massive computing demands have driven the development of AI chips. In particular, the recently proposed chiplet technology provides an advanced chip packaging and integration solution that offers high computing performance at a high yield rate and low cost, thus delivering solid hardware support for AI development. Chiplet-based chips are characterized by large area and high heat power, and their 3D chip stacking design leads to cooling challenges such as non-uniform heat flux distribution, long heat conduction paths for multilayer chips, and relatively thick thermal interface materials. These thermal issues are key bottlenecks limiting chip performance, making efficient chiplet thermal management a critical challenge in AI development. The progress in advanced liquid cooling technologies, including single- and two-phase liquid cooling solutions, is reviewed. Based on the cooling architecture, liquid cooling solutions can be categorized as cold-plate, near-junction-region, and immersion liquid cooling. In addition, the heat dissipation challenges and cooling strategies in 2.5D and 3D chiplets are summarized, providing a reference for the application and development of liquid cooling technologies for high-power, large-area AI chips.