A $10,000 cooler designed with AI keeps the Core i9-14900KF cool at 7.5 GHz

WhatsApp Group Join Now
Telegram Group Join Now
Instagram Group Join Now

Pushing the boundaries: Enthusiasts are always looking for an edge in the world of overclocking and extreme cooling. In this wild test, the team tried to determine if advanced GenAI and 3D printing could help them squeeze more performance out of today's processors. To answer this, they designed a liquid nitrogen (LN2) container in a completely new way – and came up with some interesting results.

The project brought together experts from across the ecosystem – Skatterbencher known for its overclocking capability. Diabatix, specializing in generative AI for thermal solutions; 3D systems for additive manufacturing; And finally ElmorLabs for overclocking gear.

The team took ElmorLabs' existing Volcano LN2 container as a reference point, then put Diabatix's ColdStream Next AI to work to develop an improved design. 3D Systems then brought this digital blueprint to life, 3D printing a prototype using oxygen-free copper powder. Shockingly though, the latest process commanded a hefty price tag of $10,000 – a far cry from the original Volcano's $260 price tag.

The AI/3D printed design showed promise in early testing, focusing on three key metrics: time to cool down from room temperature to -194°C, from -194°C to 20°C under a 1250W load. heating time, and the lowest temperature achieved using 500mL of liquid nitrogen.

It blew the volcano at a cooler speed, cooling from 28°C to -194°C in one minute, compared to the volcano's 3-minute speed. Heatup performance was also improved, with the AI ​​container heating up 30% faster. Performance also favored the AI ​​design – using 500mL of LN2, it reached -133°C, while the Volcano stopped short at -100°C.

However, since these tests do not represent real-world performance, the team decided to run three more using an Intel Core i9-14900KF Raptor Lake processor. First, they fired up Cinebench 2024 to find the most stable maximum CPU frequency.

“We found that both LN2 containers could handle the Core i9-14900KF with P-cores at 7.4 GHz without issue. It seemed that the AI-powered design might hold 7.5 GHz for a little longer. But it may just be a variation to run,” he noted.

In the second test, they checked the CPU temperature delta between the heat spreader and the cooling container base to gauge the actual heat transfer capabilities. There was also an all-out stress test, which pushed 600W through the chip for several minutes.

While the AI ​​container advanced a smidge, the gains were relatively muted compared to theoretical test results. The temperature deltas between the CPU heat spreader and the container base were tight on the 3D printed model, but not by a ground-shattering margin. Even the performance increase in the Cenbench was quite modest, as seen above.

After crunching the numbers, the team determined that while technically impressive, the currently AI/3D printed design doesn't pencil out from a cost/benefit perspective for modest overclocking scenarios. Not with that $10,000 price tag.

However, they are not done yet. While “nothing concrete” is in hand, the team says they can see efficiency and cost optimization. For example, the LN2 container design does not have to be circular. They are also exploring new designs for high-powered CPUs such as Ryzen Threadripper or Intel's Xeon 6.

Overall, the feasibility study may have exposed some limitations, but it also proved that creative AI applications are better than just six-fingered models.

WhatsApp Group Join Now
Telegram Group Join Now
Instagram Group Join Now

Leave a Comment