Artificial Intelligence (AI) and generative AI (GenAI) applications are taking the world by storm. Across a wide range of industries, AI is enabling breakthroughs in everything from retail to manufacturing, from financial services to healthcare, from basic research to cybersecurity. These breakthroughs were enabled by computing technology beyond our imagination just a few years ago. Yet, as this technology progresses, the power consumption for virtually every component of a server—CPUs, memory, accelerators, networking, etc.— has increased 200%, on average, over the past decade. These power-hungry systems needed for AI workloads are filling up data centers across the world and are a major contributor to the overall power increase seen in the data center space.  

In our latest research brief, Liquid Cooling: How Deep Expertise Enables Energy Efficient Computing for AI and Beyond, we assess why liquid cooling approaches are increasingly becoming a focus for both silicon and system designers because of the ability of liquid to absorb heat faster and at higher capacities than traditional air-cooling methods. Moving to liquid cooling can help meet the escalating demand to enhance data center energy efficiency for expanding AI workload environments, due to downstream effects such as the elimination of air conditioning power consumption, power to chill water and the power needed for fans to move air. This includes managing and optimizing energy consumption by using liquid cooling technologies with higher inlet temperatures (no need to chill water) all the while ensuring that system performance is not compromised and core density per data center is not affected.

In this report, you’ll learn:

• The evolving liquid cooling landscape 

• Why Lenovo Neptune is the proven solution for AI workloads: superior liquid cooling technology 

• Lenovo Neptune liquid cooling technology benefits and competitive advantages – A proven track record of solution, leadership, and tech innovation 

• The way Neptune provides a holistic cooling approach that doesn’t just cool CPUs; it includes options for direct warm water cooling of entire systems, individual components, and rack-level rear door water cooling

• How Neptune liquid cooling solutions benefit immensely from Lenovo’s partnership acumen as exemplified by the NVIDIA partnership 

Liquid cooling can maintain more compute power in traditional server form factors because it’s so efficient at absorbing heat, and the effect of surface area as a relation to performance is dramatically decreased, thus allowing for denser computing in a traditional computing footprint. Liquid-cooled servers require less space, generate less noise – lower fan power due to reduced need for high air flow – and enable an overall cooler data center environment. To find out more, download Liquid Cooling: How Deep Expertise Enables Energy Efficient Computing for AI and Beyond today!