- Nvidia’s closed liquid cooling system virtually eliminates water waste
- Direct-to-chip cooling transfers heat more efficiently than air
- It enables higher performance per watts and higher rack densities
Data centers are not without their fair share of criticism – power-hungry computers raise temperatures, and giant campuses consume significant amounts of air and/or water to keep them running optimally.
Land scarcity and economic incentives have also pushed new developments closer to high-risk areas, including drought-prone regions, ultimately leading to even higher cooling requirements.
But Nvidia knows this, and it knows that traditional air cooling has pretty much reached its limits as AI hardware gets denser and denser.
Closed-circuit cooling virtually eliminates water waste
With cooling now a core part of AI infrastructure design, Nvidia’s latest liquid-cooled AI systems promise higher thresholds to reduce the burden, reducing water and energy consumption as a result.
By running coolant at higher temperatures – 45°C or 113°F, to be specific – it allowed for simpler cooling systems and lowers power consumption. Nvidia’s concept uses 75% water, 25% glycol as a coolant, and notes that it can run about 5-7°C higher than hot tubs.
Compared to traditional evaporative cooling towers, Nvidia’s latest proposal involves a closed-loop system where coolant continuously circulates through servers to remove excess heat from chips. The hot coolant then circulates through external dry coolers, leaving virtually no water evaporation.
The company boasted that cooling-related water use can be reduced by as much as 100% in suitable climates, subject to the occasional extreme day when cooling towers are completely eliminated.
“The Nvidia DSX reference design for AI factories has zero water consumption – we’ve eliminated massive amounts of power consumption and virtually all water consumption,” said director of data center cooling and infrastructure, Ali Heydari.
The system’s efficiency comes primarily from direct-to-chip liquid cooling, where liquid flows directly through cold plates attached to CPUs and GPUs. This captures and dissipates the heat from exactly where it is produced.
Not only is this more efficient than cooling entire rooms, but liquid also promises to transfer heat thousands of times more efficiently than air.
Big improvements across water usage, energy efficiency and Power Usage Effectiveness (PUE) all help on the sustainability front, but there’s another layer to the benefits.
Nvidia says it can increase rack density and performance
Nvidia recognized that chip power consumption and rack densities continue to increase, so by implementing liquid cooling, data center companies can add more GPUs per rack, use higher rack power, and ultimately pack larger AI clusters into the same building footprint.
The company explained that its Rubin systems now fit inside two racks instead of six, marking a major space saving.
At the same time, air cooling has become ineffective. “Once watts per chip crossed a certain level, liquid cooling became mandatory,” said Motivair CEO Richard Whitmore.
Independent testing, completely separate from Nvidia’s latest announcement, shows that its H100 systems delivered around 17% higher performance when water cooling compared to air cooling. During sustained AI workloads, GPU temperatures fluctuated between 41-50°C when water-cooled and 54-72°C when air-cooled.
In addition to improving instantaneous and sustained performance, greater thermal efficiency can also increase lifespan.
The new closed water cooling model with higher temperatures is set to be used in future Rubin implementations this year.
Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews and opinions in your feeds.
