Analyzing Threadripper Thermals: Big Base Cooling Wins
by E. Fylladitakis on March 14, 2018 8:30 AM EST- Posted in
- CPUs
- AMD
- Cases/Cooling/PSUs
- Noctua
- ThreadRipper
- 1950X
- CPU cooler
Thermal Conductance 101 with Dr. Fylladitakis
Simplified, thermal conductance is the ability of a material or arrangement to conduct heat. Thermal conductance is inversely related to the absolute thermal resistance, meaning that a lower absolute thermal resistance will improve thermal conductance. In our particular case study, that arrangement is the CPU/Cooler setup. When studying arrangements, the absolute thermal resistance of the entire arrangement is the sum of the thermal resistance that each individual part has. Anything that lowers the absolute thermal resistance of the CPU/Cooler arrangement will result to better thermal conductance, i.e. lower operating temperatures. Vice versa, if the absolute thermal resistance of the arrangement increases, the thermal conductance will be lowered.
The figure above displays a simplified CPU/Cooler arrangement. At the bottom layer we have our CPU die(s), the middle layer is the CPU’s copper lid and, finally, the top layer is the CPU cooler. With such a setup, we have three individual thermal resistances: R1) the CPU’s die (heat conduction from the CPU die to the CPU lid), R2) the CPU’s lid (heat conduction from the CPU’s lid to the cooler), and R3) the cooler’s absolute thermal resistance. These three resistances sum up to make the total absolute thermal resistance of the CPU/Cooler arrangement. Simplified and assuming one-dimensional conduction, each absolute thermal resistance depends on three things: a) the length of the material in parallel to the heat flow (i.e. its thickness), b) the thermal conductivity of the material, and c) the cross-sectional contact area.
The cooler’s absolute thermal resistance obviously depends on the cooler itself (size, materials, design, air flow, etc.). However, no matter how good a cooler is, the absolute thermal resistance of the entire arrangement can still be poor if any other thermal resistance is too high. For example, it is known amongst enthusiasts that some of Intel’s previous processor generations had poor thermal performance that was unjustified given their very low power requirements. That was because the CPU’s lid was making poor contact with the CPU’s die(s), greatly decreasing the thermal flow between the die and the lid. Hardcore enthusiasts were “delidding” their processors in order to fix this issue.
Facebook
Twitter
RSS
43 Comments
View All Comments
Ryan Smith - Wednesday, March 14, 2018 - link
To clarify, the title of page 2 is a bit of humor. E. isn't a doctor (though Ian is).LordanSS - Wednesday, March 14, 2018 - link
Thank you for the article. It was a good read with the thermodynamics explanation as well.fackamato - Wednesday, March 14, 2018 - link
What are the decibels during load for each cooler/rpm?Valantar - Wednesday, March 14, 2018 - link
A fascinating read. Now for the follow-up: an article where you test sticking two 212 Evos side by side on a Threadripper. That should cover most of the IHS, no?LanceLLandon - Wednesday, March 14, 2018 - link
My preference is Peltier air cooling. By cooling a processor slightly frozen less thermal noise is generated and less miscalculations are performed. Perhaps this is more important for studio Sound Recording and Mixing/Editing or Movie Video Editing or for Work Station performance. If I am going to all the trouble to build a multi core computer I will also so go to the trouble of cooling it far more effectively.MrSpadge - Wednesday, March 14, 2018 - link
A Peltier cooler will help you with extreme OC, if sized properly, but apart from that will only increase your energy consumption significantly. If you want lower temperatures go for chilled water, that's far more efficient. But you absolutely don't need that. Otherwise all the servers in data centers, DELL shops etc. would have to be constructed differently. And if you really want to reduce the chance of calculation errors beyond the manufacturer specification, simply drop the CPU clock by 100 MHz.BTW: are you using ECC RAM? Not that I'm recommending it for home computers, but if not you're definitely overshooting with that Peltier and should care for more probable points of failure first.
Crazyeyeskillah - Wednesday, March 14, 2018 - link
Water or GTFO.master381 - Wednesday, March 14, 2018 - link
Nice article!A question - on Page 3, is this supposed to read " absolute thermal resistance of the cooler itself needs to be very *low,*" instead of high?
Excerpt:
"The high thermal resistance caused by an undersized contact plate cannot be easily countered, which is why the absolute thermal resistance of the cooler itself needs to be very high, i.e. why AMD’s cooler recommendations are so over the top."
Ryan Smith - Thursday, March 15, 2018 - link
That was meant to read "thermal conductance". Thanks!zodiacfml - Wednesday, March 14, 2018 - link
The conclusion I can get from here is that desktop CPU with around 90W TDP can also benefit from the larger surface area, considering the differences in temps at idle of the TR chip.