Cooling the Next Generation of Computing

High performance computing (HPC) and data-intensive technology applications – like machine learning (ML), artificial intelligence (AI), generative AI, crypto mining, and high-definition video processing – can have server densities over 100kW, making the ROI for air cooling unattractive. Liquid cooling, with its higher thermal conductivity, provides significantly greater capacity to reject heat and cool the server densities that these technologies require.

Delivering Cost-Saving and Sustainability Benefits

Liquid cooling uses less energy, space and materials, while enabling higher density per rack to run next generation compute workloads such as generative AI demand.

CDU Direct to chip1-phase Immersion Cooling 2-phase Immersion Cooling
Lowest upfront cooling equipment costsvery_beneficial1-phase Immersion Cooling very_beneficial2-phase Immersion Cooling very_beneficial
Highest cooling density for high TDP chipsvery_beneficial1-phase Immersion Cooling very_beneficial2-phase Immersion Cooling very_beneficial
Best Power Utilization Efficiency (PUE) very_beneficial1-phase Immersion Coolingvery_beneficial2-phase Immersion Cooling very_beneficial
Best Water Utilization Efficiency (WUE)very_beneficial1-phase Immersion Cooling very_beneficial2-phase Immersion Cooling very_beneficial
Highest number of servers per U space very_beneficial1-phase Immersion Cooling very_beneficial2-phase Immersion Cooling very_beneficial
Most free-cooling potentialvery_beneficial1-phase Immersion Cooling very_beneficial2-phase Immersion Cooling very_beneficial
Lowest whitespace consumption most_beneficial1-phase Immersion Cooling very_beneficial2-phase Immersion Cooling very_beneficial
Quickest installation and server changeoutvery_beneficial1-phase Immersion Cooling very_beneficial2-phase Immersion Cooling very_beneficial
Most liquid-ready servers very_beneficial1-phase Immersion Coolingvery_beneficial2-phase Immersion Cooling very_beneficial
Least equipment maintenance very_beneficial1-phase Immersion Cooling very_beneficial2-phase Immersion Cooling very_beneficial
Ease of server/IT refresh very_beneficial1-phase Immersion Cooling very_beneficial2-phase Immersion Cooling very_beneficial
Source: Comparison of Server Liquid-Cooling Technologies, Syska Hennessy Group, April 2024

LiquidStack offers a range of liquid cooling solutions to match customers’ adoption approach.

Coolant Distribution Unit (CDU) and Direct-to-Chip

How it works: In a Direct-to-Chip solution liquid coolant is delivered directly to the hottest components, usually the GPU and/or CPU via a cold plate placed directly on the chip. The electric components are never in direct contact with the coolant and the liquid coolant is circulated through channels within the cold plates, absorbing heat directly from the components. The heated coolant is pumped away from the cold plates to a Coolant Distribution Unit (CDU), where the heat is dissipated to air or liquid depending on the type of CDU in place. Coolants can be either a water glycol mix or dielectric fluid.

Typical applications and use cases include artificial intelligence (AI), advanced cloud computing, video and graphics rendering, high performance computing (HPC), and any low latency, high processing applications.

LiquidStack’s Coolant Distribution Units (CDUs) can be configured for virtually any direct-to-chip solution. Powerful, compact, efficient, and easy to manage, they are designed for the latest AI chips and servers.

Single Phase Immersion Cooling

How it works: the entire server including GPUs and CPUs is submerged in a thermally conductive, dielectric liquid coolant. The liquid coolant absorbs heat from the components and is then circulated through a heat exchanger to dissipate the heat. As the liquid coolant is never allowed to boil and turn into vapor, it is called single phase immersion cooling since the liquid remains in one state. This method provides excellent cooling efficiency and density, allowing for very high-density rack configurations.

Typical applications and use cases include regional edge, retrofitting existing data center infrastructure, artificial intelligence (AI), OTT, advanced cloud services, video and graphics rendering, high performance computing (HPC), and other low latency, high processing applications
LiquidStack’s single phase immersion DataTank provides the highest cooling capacity on the market. Our advanced flow technology optimizes heat transfer and rejection, with as low as 1.03 pPUE, by leveraging warmer water temperatures, and minimizing mechanical cooling power consumption.

 Two Phase Immersion Cooling

How it works: the entire server including GPUs and CPUs is submerged in a thermally conductive, dielectric liquid coolant. Unlike single phase immersion cooling, the heat from the chips is allowed to cause the liquid coolant to boil and turn into vapor, which removes the heat from the electronics. The vapor rises, cools and condenses, allowing the liquid coolant to fall as droplets back into the tank. The continuous cycle of turning liquid into vapor and vapor into liquid is the reason why the process is called two phase immersion cooling. This approach offers exceptional cooling capacity and efficiency.

Typical applications and use cases include new data center construction, artificial intelligence (AI), OTT, advanced cloud services, video and graphics rendering, high performance computing (HPC), and other low latency, high processing applications.

LiquidStack’s two phase immersion DataTank meets the challenging needs of increased server density as well as power and energy requirements, while requiring only a fraction of the space and energy used by air-cooled data centers.

LiquidStack defies cooling conventions, empowering a new generation of edge, data center and distributed computing

icon

Liquid cooling innovator since 2012

icon

Extensive patent portfolio and growing

icon

World’s first Innovation Center for
two phase immersion liquid cooling

icon

Silent, sustainable and environmentally friendly

icon

Working with the world’s largest hyperscalers and data center operators

Stay in the know!

Sign up to get notified about the latest LiquidStack news, resources and events.