News Generative Design and 3D Metal Printing Enhance CPU Cooling Performance

[Admin]

The generative AI-powered heatsink design from Diabatix, copper 3D printed by Amnovis, looks strikingly different to traditional heatsinks, but is claimed to offer 22% better cooling.

Generative Design and 3D Metal Printing Enhance CPU Cooling Performance : Read more

 

[InvalidError]

Imagine the fun you are going to have attempting to unclog an AI-generated "organic" water block with tons of tiny inaccessible cavities. Better make sure you run plain coolant with the necessary anti-corrosion, anti-bacterial, with algicide and whatever else may be necessary to prevent any clumps from forming over time.

Simple fins may not be the absolute optimal cooling option but at least inspection and maintenance are simple.

 

[bit_user]

Imagine the fun you are going to have attempting to unclog an AI-generated "organic" water block with tons of tiny inaccessible cavities.

Is this sort of maintenance typical, for water blocks?

Better make sure you run plain coolant with the necessary anti-corrosion, anti-bacterial, with algicide and whatever else may be necessary to prevent any clumps from forming over time.

Even with a more conventional design, the formation of biofilms or other buildup would hurt performance. Therefore, you'd probably always want to do that.

 

[InvalidError]

Is this sort of maintenance typical, for water blocks?

If you watch some YT vids from liquid-cooling fanatics like Jayz, people put all sorts of crazy stuff in their clear tubing loops for visual effects. Dyes, color-shifting additives, UV dyes and other similar crap has a tendency to form clumps in corners and anywhere where there isn't enough turbulent flow to prevent accumulation. If you turn off loops with such stuff in them for several days, you may have issues with sediment sticking everywhere.

Pearlescent coolant looks kind of cool, except you are almost guaranteed to have clumping issues if you turn off your PC for more than a day.

I don't do liquid cooling since I don't want to have to deal with any of that extra crap. I slap a dumb 212+/EVO on my CPU and then forget about it.

 

[RichardtST]

Stupid question.... why are we running water instead of a nice light oil, like sewing-machine oil or something? Thin and light like water, but doesn't evaporate? Wouldn't that make more sense than something as corrosive as water? And surely no one uses tap water, right? What's so wrong with radiator fluid?

Love the generative/iterative designs. Basically it figures out by itself how to maximize flow and surface contact while minimizing resistance. Keep those little molecules accelerating in all directions to break up that boundary layer!

 

[InvalidError]

Stupid question.... why are we running water instead of a nice light oil, like sewing-machine oil or something?

Two words: specific heat.
Water: 4.17 J/gram
Oil: 0.5 J/gram on average

So if you ran an oil-cooling loop, you'd need 8X as much oil flow for the same coolant temperature rise. Also, most oils have higher viscosity than water, which means the pump would need to work even harder to maintain that 8X flow.

If oil was a great coolant, combustion engines wouldn't need a whole separate radiator circuit for cooling including the added complexity of the engine block and head coolant jacket, they'd just rely on oil flow everywhere.

 

[RichardtST]

Two words: specific heat.
Water: 4.17 J/gram
Oil: 0.5 J/gram on average

So if you ran an oil-cooling loop, you'd need 8X as much oil flow for the same coolant temperature rise. Also, most oils have higher viscosity than water, which means the pump would need to work even harder to maintain that 8X flow.

If oil was a great coolant, combustion engines wouldn't need a whole separate radiator circuit for cooling including the added complexity of the engine block and head coolant jacket, they'd just rely on oil flow everywhere.

Cool. Thanks!

 

[bit_user]

My other thought was that oil is messy and flammable.

If oil was a great coolant, combustion engines wouldn't need a whole separate radiator circuit for cooling including the added complexity of the engine block and head coolant jacket, they'd just rely on oil flow everywhere.

FWIW, some turbo-chargers are oil-cooled. Not sure why. Maybe the issue with water-cooling them is they're too hot?

Simple fins may not be the absolute optimal cooling option but at least inspection and maintenance are simple.

I expect you could add a constraint to the design that limits the minimum gap.

 

[USAFRet]

FWIW, some turbo-chargers are oil-cooled. Not sure why. Maybe the issue with water-cooling them is they're too hot?

Stupid high RPM.

And is that cooled, or lubricated?

 

[bit_user]

And is that cooled, or lubricated?

Looks like it's essential for both cooling & lubrication.

• https://www.counterman.com/turbo-cooling-the-real-reason-turbochargers-are-back/
• https://www.garrettmotion.com/racin...-a-turbocharger/water-cooling-for-your-turbo/

The second link implies water-cooling is very much the exception.

 

[InvalidError]

FWIW, some turbo-chargers are oil-cooled. Not sure why. Maybe the issue with water-cooling them is they're too hot?

Some? The only thing that really requires cooling in those are the bearings which also require oil flow for lubrication and cleaning exhaust that makes it past bearing shields. Not sure how you'd cool bearings with anything other than an appropriate lubricant.

 

[bit_user]

Some?

The point wasn't whether oil provides cooling, but whether it's the primary method of cooling. I based my statement on the fact that I've seen turbo-chargers described as oil-cooled, and reasonably presumed the qualification was needed due to it not always being the case. Based on the second link in my previous post, I think what they probably meant was the turbos lacked any supplementary water-cooling.

The second link makes a case for water cooling, but we don't need to have that debate. If you want to pick a fight about turbo-charger cooling, maybe find a car site to have it.

 

[BFG-9000]

Eh, could look worse, look up Hyperganics

The water jacket around the turbo bearings was a great advance in the 1980s for turbo longevity. See, in a car application, someone could shut off the car when the turbo was spinning at 100,000rpm and while ball bearings are perfectly OK with no oil pressure (unlike sleeve bearings like your engine main and conrod bearings), the friction and exhaust heat transferred from the shaft would cook the remaining oil into abrasive carbon particles. Next time the car was started, those bearings would run in the abrasive slurry until they eventually wore down enough to allow the impeller to touch the sides. That's why in the olden days people would have to change out turbos as often as every 30,000 miles.

The oil flow alone was perfectly adequate to cool the bearings in continuous operation like in a boat, plane or generator, but a car has many stop and start cycles with no oil or water flow and a glowing red impeller. The small amount of water in the water jacket (remember the water isn't flowing either with the engine off) is sufficient to keep the oil from cooking itself, and that was all that was needed.

 

[Darkbreeze]

Some? The only thing that really requires cooling in those are the bearings which also require oil flow for lubrication and cleaning exhaust that makes it past bearing shields. Not sure how you'd cool bearings with anything other than an appropriate lubricant.

Besides which, since turbos are exhaust driven, the temperatures they see would make it nearly impossible to to prevent the cooling system from being in an almost constant gaseous state, without also having the cooling and lubricating benefits of oil. In other words, a purely water cooled turbo charger would cause the coolant to boil which would effectively make it useless. But obviously, yes, bearings wouldn't last long with water as a lubricant.

 

[InvalidError]

Besides which, since turbos are exhaust driven, the temperatures they see would make it nearly impossible to to prevent the cooling system from being in an almost constant gaseous state

The bearings are behind the turbine, not much heat getting there besides what gets conducted by the shaft which is being cooled by intake air on the other side during normal operation. As bit's 2nd link and BFG pointed out though, there is the "back-soak" issue where suddenly shutting off the engine after driving hard will let the heat-soaked turbine cook the oil and seals. The coolant pocket around the turbo's bearings is meant to save the oil and seals from improper shutdown.

 

[Darkbreeze]

This is what I do for a living. Believe me, allow a turbo charged engine to get a bit too low on oil, or any kind of oil starvation to that unit which commonly happens due to poor maintenance (gummed up, restricted or collapsed oil lines), and watch how fast that turbo cooks itself and in many cases the engine as well. They can tolerate a loss of coolant for much longer than they can tolerate a loss of lubrication, and same as with an engine, the oil plays a big role in cooling as well. Water/antifreeze alone, for either of these systems, would never cut it by itself. An engine or turbo, deprived of oil, even if it COULD magically manage to not fail from lack of lubrication, would absolutely suffer damage from overheating if you took away the cooling effect that oil provides.

Sure, air plays a role too, but not nearly as much as you might think. But you are right, because heat soak from improper shut down is the second biggest factor in turbo failure after oil loss or starvation.

Turbocharger Damage: Most Common Causes And How To Prevent Them

We get the lowdown from the experts at Mahle about the most common causes of turbocharger damage and how to prevent them from occurring to you!

www.enginelabs.com

 

[BFG-9000]

This probably doesn't have much to do with a CPU water cooling block, but sure, oil is a perfectly adequate coolant for things that can tolerate a lot of heat like bearings or those transformers on telephone poles (thankfully no longer contaminated with PCBs) and is even a lot easier to deal with at high temperatures since it doesn't require pressurization to handle it.

CPUs are not designed to handle such high temperatures so a more effective coolant is better. If you're going to settle for an inferior coolant, then you may as well use high speed fans and air cooling as there's less to go wrong. Air may be a terrible coolant too but it's easy to get a lot of it if you don't mind noise.

Air cooled engines generate less power than water-cooled because the higher heat in the cylinder head causes more preignition, requiring less boost, timing and compression ratio to combat. However there are other considerations--the US military long preferred air-cooled because the engine could be shot up a lot more (with even entire cylinders blown off) and still make it home or at least to over friendly territory (they carried a LOT of oil). It's why the rugged giant flying pickup-truck P47 had ~50% more kills than the sleek Ferrari-esque P51 despite both being produced in similar numbers. Once the water cooling system was holed anywhere on the V-12, it was done.

 

[bit_user]

If you're going to settle for an inferior coolant, then you may as well use high speed fans and air cooling as there's less to go wrong. Air may be a terrible coolant too but it's easy to get a lot of it if you don't mind noise.

At some point, air cooling should suffer from aerodynamic effects, whereby it takes a nonlinear amount of energy to force more air through. In Paul Alcorn's recent review of Epyc Genoa, he mentioned the dual-CPU server's fans can consume up to 300 W, all by themselves.

https://www.tomshardware.com/reviews/amd-4th-gen-epyc-genoa-9654-9554-and-9374f-review-96-cores-zen-4-and-5nm-disrupt-the-data-center/3

So, I'd say air cooling is good, if you can afford enough surface area that you don't need to force it through at high-velocity.

 

[bit_user]

In other words, a purely water cooled turbo charger would cause the coolant to boil which would effectively make it useless.

I let it slip, but this statement kept gnawing at me. Phase-change cooling is actually the most efficient. Therefore, I don't see why boiling the water would be a problem, so long as the cooling system was designed to cope & had enough radiator capacity to re-condense it.

 

[InvalidError]

I let it slip, but this statement kept gnawing at me. Phase-change cooling is actually the most efficient. Therefore, I don't see why boiling the water would be a problem, so long as the cooling system was designed to cope & had enough radiator capacity to re-condense it.

In the case of turbo bearings and soak-back after a "hot-shutdown", the radiator won't be able to condense anything that is getting boiled off in the turbo since the coolant pump isn't running anymore. Shouldn't need much coolant to protect the bearings from heat soak though and what may get displaced by boiling will just wait in the overflow tank to get sucked back in as everything cools back down.

 

[Darkbreeze]

But, automotive cooling systems aren't designed with phase change in mind. Temperatures that cause water to boil in an automotive cooling system would result in a variety of problems including collapsed or blown hoses, failure of cooling to circulate since water pumps do a particularly lousy job of moving gases from one place to another, not to mention the probability that without direct water contact the thermostat would be unlikely to open, sensors would be unlikely to read thermal values correctly and gaskets and seals designed to retain water will likely be damaged and/or leak as well as potentially blowing out the expansion tank.

Aside from it's anti-corrosive properties the main purpose of antifreeze when used in a 50/50 mixture is to raise the boiling point, because boiling water is bad in a this type of system, and lower the freezing point. Additionally, the point of designing the systems for a certain amount of pressure is to suppress the coolant from boiling as pressure also increases the boiling point. Everything about these systems is purposely designed to make sure it never boils.

 

[InvalidError]

But, automotive cooling systems aren't designed with phase change in mind.

They actually are, to a limited extent: that is why the coolant return pipe is at the top so any gas bubbles that may be present have to make their way down through the radiator and get condensed before reaching anything else. As long as you still have enough coolant in the radiator to condense vapor before it reaches the bottom, everything is fine. If your cooling system explodes for no apparent reason, then you had a stuck, defective, incorrect or missing pressure relief valve.

 

[Darkbreeze]

Ok. We'll agree to disagree on this one.

 

[bit_user]

In the case of turbo bearings and soak-back after a "hot-shutdown", the radiator won't be able to condense anything that is getting boiled off in the turbo since the coolant pump isn't running anymore.

Then you didn't read the first link I posted, which claims at least some cars with these turbos have oil pumps which continue running after shutdown.

 

[InvalidError]

Then you didn't read the first link I posted, which claims at least some cars with these turbos have oil pumps which continue running after shutdown.

No, didn't look at the first one, only read the second to find out what they did with the coolant. Running the oil pump after engine shut off makes sense if you have an electric oil pump instead of a conventional crank-driven one.