• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

IBM doubles CPU cooling capabilities with simple manufacturing change

D

dmcowen674

No Lifer
By "roughing" up the CPU chip surface area, not smoothing it down.

3-27-2007 IBM doubles CPU cooling capabilities with simple manufacturing change

According to a new paper released at the IEEE Semi-Therm conference, IBM has discovered a way to dramatically improve processor cooling. Unlike some other recent cooling breakthroughs, IBM's discovery appears to be one that should be relatively inexpensive to implement, and could have a significant impact on consumer microprocessors in the near future. Without fundamentally changing the approach to CPU cooling today and without the use of more advanced setups like water coolers, IBM says that they can double CPU cooling capacity while making it easier and safer to do so.

IBM's find addresses how thermal paste is typically spread between the face of a chip and the heat spreader that sits directly over the core.

Overclockers already know how crucial it is to apply thermal paste the right way: too much, and it causes heat buildup. Too little, and it causes heat buildup.

It has to be "just right," which is why IBM looked to find the best way to get the gooey stuff where it needs to be and in the right amount, and to make it significantly more efficient in the process.

The results are quite impressive. Paste thickness could be reduced by a third, and the pressure required to properly fit a CPU cooler on top of a core was cut in half. All of this, and IBM says that cooling capabilities are effectively doubled.
 
This "discovery" is a bit amazing. Heat transfer is very well understood and has predictable charateristics. If we restrict ourself to the area between the cpu core distributer plate and the HSF heat sink plate then the only factor is the gap between the two and the specific conductivity of heat of this gap. This is a three dimensional effect with the gap as one dimension and the width and height of the contact area the other two. As the gap increases the heat conductivity decreases. As the specific conductivity of the gap material inscreases heat conductivity decreases. If the gap or some portion of it is air then this is really bad as air has poor heat conductivity.

The ideal contact design is perfectly flat surfaces with zero gap or zero material of any kind between the two plates - or better still welded together. This is not possible so it is accepted that the next best thing is to fill the irregularities with a highly conductive and flowable semi-liquid.

So what has IBM done with this lumpy surface design? First it would make absolute flatness less essential. The points are likely to give or yield a little and make virtual metal to metal contact. That is an up side. The down side is that this very intimate contact is likely very small in comparison to the whole surface area. Another up side is that the lumpy surface makes it more likely the semi-liquid fluid between can flow out of the way and allow this high point metal to metal contact. The down side of this is that between the lumps the thickness of the fluid which does not conduct heat as well (despite what the manufacturers would like us to believe) will be thicker. And this will be the largest part of the surface area.

What is the net net of all this? IBM says better. I wonder really?
 
Maybe this explains why IBM High End Server sales are now surpassing HP and Sun.
I wonder if they will be using this technique on the new P6.
 
Has anyone tried scribing small grooves into their CPU to see if that would noticeably improve cooling?
 
You must log in or register to reply here.

TRENDING THREADS

Back
Top