[polvs]

Hi Tom, I think I remember you from the C3 Crypto Conference where we had a booth. I know what you mean, the initial cost of acquiring this technology compared to regular air cooling technologies is more expensive in the very short term, but when you consider the operational costs of electricity, the ROI can be under a year.

It becomes much more interesting when you also factor in that you can pack >4x computing power into the same physical space saving a lot of real estate and don't need the huge CAPEX in expensive prepared server rooms nor plan ahead the “hot-spots”.

[ksec]

Why hasn't this taken up pace though? I am pretty sure I read about immersive cooling at least 4 -5 years ago. And 3M had some new "liquid" shown 1 - 2 years ago. Given the scale of which now Google, Amazon, Microsoft and Apple operate, surely they should be the first one to adopt?

Edit:

Looks like I asked the question a while ago. From Anandtech and Servethehome:

10 years ago, liquid had a thermal limit. Now it is around 5x that old limit. Problem is cost ($$$/gallon of the liquid) and installation. Has to be marketed on TCO. Also, issues with submerged fiber connections

2U air cooling can reliably handle 8x 200w+ TDP CPUs, 600w of NVMe, plus RAM and add-in cards. 4U designs can handle 6kW of cooling on air. Liquid may be more efficient, and more data centers are being built for it, but air is easy to deploy.