← Back
NVIDIA Blog

Hotter Than a Hot Tub: The 45°C Breakthrough to Cool AI’s Biggest Machines

7 min read
#compute#nvidia#inference#deployment
Hotter Than a Hot Tub: The 45°C Breakthrough to Cool AI’s Biggest Machines
Level:Advanced
For:AI Engineers
TL;DR

NVIDIA's newest AI servers can run their cooling liquid at up to 45 degrees Celsius, making them more energy efficient and achieving 100% liquid cooling with no fans in the system. The Rubin generation of NVIDIA AI infrastructure is the first to achieve this, and it is outlined in the NVIDIA DSX AI factory reference design. This liquid cooling methodology enables data centers to reduce cooling energy consumption, making a significant difference in overall data center energy use. The practical implication for engineers building AI systems is that they can design more efficient and sustainable data centers using liquid-cooled infrastructure.

⚡ Key Takeaways

  • The NVIDIA Rubin platform achieves 100% liquid-cooled infrastructure, with every chip and networking component cooled entirely by liquid in a closed loop with no fans.
  • Cooling alone can account for up to 40% of a data center's electricity consumption, making it a significant area for efficiency improvements.
  • Raising chiller plant temperatures by just one degree can cut cooling energy costs by about 4%, with a 50-megawatt hyperscale facility potentially saving over $4 million annually.
  • NVIDIA's 45-degree liquid-cooling architecture can enable chiller-less operation with dry coolers, reducing facility cooling water consumption from roughly 2.6 million gallons per megawatt per year to near zero.
  • The NVIDIA DSX AI factory reference design provides a guide for designing, building, and operating AI factory infrastructure with liquid-cooled infrastructure.
💡 Why It Matters

The transition to 100% liquid-cooled infrastructure has significant implications for engineers building AI systems, as it enables the design of more efficient and sustainable data centers. This can lead to substantial cost savings and reductions in water consumption, making it a crucial consideration for hyperscale data centers.

✅ Practical Steps

  1. Implement the NVIDIA DSX AI factory reference design to guide the design, build, and operation of AI factory infrastructure with liquid-cooled infrastructure.
  2. Consider transitioning to 100% liquid-cooled infrastructure to reduce cooling energy consumption and water usage in data centers.
  3. Evaluate the potential cost savings and environmental benefits of adopting liquid-cooled infrastructure in your data center operations.

Want the full story? Read the original article.

Read on NVIDIA Blog

More like this

We Built a Routing Layer to Cut Our AI Costs. It Broke the Product.

Towards Data Science#inference

Using Local Coding Agents

Ahead of AI#agents

How the English Office for Students leverages Databricks to enhance higher education standards and drive better student outcomes

Databricks Blog#compute

Build interactive PDF text extraction from Amazon S3

AWS ML Blog#amazon

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING