Image: TSMC

Future processors could boast built-in water cooling thanks to ambitious research by the world’s leading semiconductor foundry, TSMC. During a recent symposium, the Taiwanese company demonstrated three water cooling methods that would integrate water channels directly into a chip’s design. Out of the three methods, TSMC had the most luck with one leveraging direct water cooling, in which the water has its own circulating channels etched into the silicon. That method allowed for up to 2.6 kW of heat dissipation and a temperature delta of 63 degrees Celsius. Of course, it’ll probably be a while before any of this technology reaches the mainstream.

Image: TSMC

The company further tested three types of water cooling designs: one with only direct water cooling (DWC), where water has its own circulating channels etched directly into the chip’s silicon as part of the manufacturing process; another design with water channels being etched into their own silicon layer on top of the chip proper, with a Thermal Interface Material (TIM) layer of OX (Silicon Oxide Fusion) that carried heat from the chip to the watercooling layer; and lastly a design which swapped the OX layer for a simpler, cheaper liquid metal solution.

Sources: HardwareLuxx, Tom’s Hardware

Don’t Miss Out on More FPS Review Content!

Our weekly newsletter includes a recap of our reviews and a run down of the most popular tech news that we published.

Join the Conversation


  1. I know this has been on the table for a while, and I remember a particular ‘Sunny Delight’ mod using the top of the bottle for direct-die cooling.

    I’m interested in seeing what they come up with, as well as the infrastructure beyond the die itself needed to support it. It seems a bit like building the waterblock into the silicon itself, but with such small water channels concerns such as water (or coolant) purity as well as pressure regulation and air bubble prevention start to grow in my mind!

  2. I can see it going into some specific high density applications but not a consumer market. Like Lazy said – too many variables in a consumer liquid system. This would have to be highly specialized and controlled to be reliable – even something as lame as trapped gas and microboiling in the liquid could screw up coolant channels that small.

    Physical construction I think would be the easy part.

Leave a comment