Follow Slashdot blog updates by subscribing to our blog RSS feed

 



Forgot your password?
typodupeerror
×
Hardware Technology

On-Chip Liquid Cooling Permits Smaller Devices With No Heatsinks Or Fans 45

An anonymous reader writes: DARPA-funded research into on-chip liquid cooling has resulted in a field-programmable gate array (FPGA) liquid-cooled device that can operate at 24 degrees Celsius, versus 60 degrees Celsius for an equivalent air-cooled device. The cooling fluid resides only nanometers from the heat it must address, and operates so efficiently as to offer potential to stack CPUs and GPUs using copper columns, as well as dispensing with heat-sinks and fan systems. With those components removed, the system can facilitate far more compact designs than are currently feasible.
This discussion has been archived. No new comments can be posted.

On-Chip Liquid Cooling Permits Smaller Devices With No Heatsinks Or Fans

Comments Filter:
  • by Anonymous Coward

    I can hear Jony Ive yell: "thinnnnnner...!!

    • I can hear Jony Ive yell: "thinnnnnner...!!

      I thought that was the old hag's line in the Stephen King movie.

  • by TWX ( 665546 ) on Monday October 05, 2015 @02:26PM (#50663919)
    ...there still is a form of exterior cooling, it's just now the interface between the case's liquid cooling system interfaces with the IC packaging rather than with an exterior heatsink module that's in contact with the packaging.

    This is not a cooling system integrated into the chip directly without an exterior component.

    I see good and bad. Good, packaging becomes smaller so the processor can fit into smaller cases, and now there's no need for all of the mounting bosses for the traditional heatsink. Bad, the interface between the cooling system and the chip will undoubtedly be more fragile than between a cooling system and a large (relatively speaking) metal heatsink, and if there's a problem in the cooling passages on the chip there is no inexpensive method to replace the cooling portion if it's clogged-up.

    We'll have to see how well this operates in the wild. If a lot of cooling system pressure loss and leaking occurs where the tubing interfaces with the chip then this won't be so good. If it manages to not leak and not plug-up then this could be a nice evolutionary step.
    • Dunno... most laptops nowadays have closed-loop cooling, and very few (I daresay statistically next-to-none) come across clogging and/or cooling-fluid corruption issues.

      • by Anonymous Coward

        There are a total of ZERO laptops that use closed loop liquid coolers. You're using the wrong term for copper heatpipes. Asus makes a gaming laptop with an external radiator that is an overpriced cooling stand, that connects using compression fittings, which in turn will introduce air bubbles into the system which causes premature pump failure. What this article is discussing seems to be integrating a waterblock into the IHS, which would have been a much nicer summary than the one we got.

    • Running outside the chip water cooling previously, I never ran into a problem with clogging, but I can see that with this. The answer is to have filtering of the working fluid before the chip in a replaceable part. You also need a working fluid that discourages biological growth, but that shouldn't be too hard either. I am wondering how they cool the liquid without radiators or fans though.

      • by jandjmh ( 66714 )

        This liquid cooling scheme is just a way to move the heat somewhere, but there still needs to be a heatsink, and fan, and with this liquid method also a fluid pump.

        The advance here is that the working fluid is so close the the chip that the thermal resistance of the package is bypasses, theoretically allow either lower chip temperatures or more power without overheating.

        • by TWX ( 665546 )
          Makes me wonder if they can take enough heat away to use the chip and convection to power the circulation process passively.
      • "You also need a working fluid that discourages biological growth, but that shouldn't be too hard either."

        Exactly, my fridge did it for 20 years.

        • Somehow I don't think the working fluid in a liquid cooling setup will be kept at quite the temperatures in a refrigerator. Rather, the temperature of the working fluid will be in the biological "danger zone"

          https://www.google.com/search?... [google.com]

          which encourages the growth of microorganisms which can clog a liquid cooling setup. I believe this is why many use antifreeze or special fluids designed for the purpose, but I could be wrong about that.

  • by pla ( 258480 ) on Monday October 05, 2015 @02:34PM (#50663969) Journal
    Liquid cooling, no matter how efficient, still requires you to dump the waste heat somewhere. You don't magically get to just seal up the vents in the case because "liquid!".

    That said, yes, this counts as a very cool (no pun intended) step forward, and will vastly improve the number of transistors we can pack into an arbitrary sized box - But make no mistake, that "savings" comes at the cost of needing an external radiator.

    TANSTAAFL.
    • True indeed... but then, you can pipe it off to a heatsink sitting off to the side (meaning you can make the overall device thinner), and the closer proximity betwixt fluid and heat source means that you don't need as large of a heatsink (mostly because you're not waiting for a relatively large amount of heat to work its way out past the packaging.)

    • You can magically seal up the vents and pump the liquid through the case of the device, turning the entire casing and all of it's surface area in to the heatsink.

    • You could seal up the vents to the circuitry and pipe the vaporized liquid to a condenser in an area that doesn't have circuitry. Then you could replace the air in the circuitry area with argon or dry nitrogen. If you need an external radiator, you might as well enjoy the advantages that come with that sort of design and make the radiator external to more than just the processor.
  • DARPA-funded research into on-chip liquid cooling has resulted in a field-programmable gate array (FPGA) liquid-cooled device that can operate at 24 degrees Celsius, versus 60 degrees Celsius for an equivalent air-cooled device.

    So do most FPGAs need an external heater to get them up to 60C before they'll operate, or don't they all work at 24C?

    Or do they mean that this one WILL only REACH 24C WHILE running?

    • As a rule of thumb, the colder electronic components are, the cleaner their signals are, the faster they can run, etc. All the fastest overclocking gets done via subzero temperatures [kitguru.net] (though this is dangerous as condensation of water from the atmosphere can cause catastrophic short-circuits).

      • Field effect transistors - the dominant devices in modern digital logic - run faster at low temperatures. Conductor resistance usually drops as temperature drops; that also helps. Bipolar transistors lose current gain at low temperatures, and generally run fastest around room temperature.
  • It seems to still require an external pump, and liquid cooling didn't seem to take off yet except among hardcore overclocking enthusiasts. It's complicated, messy, and can fail in ways that are much worse than air cooling.

    And what happens if those tiny channels erode or get clogged?

    Or perhaps this is supposed to be paired with an OEM system intended to be maintenance free to solve such problems?

    The article unfortunately is short on useful information.

  • Where does the heat go? Is it magically carried away by the liquid into some sort of wormhole?
    • by suutar ( 1860506 )

      no heatsink attached to the chip. There's one elsewhere, even if it's just tubing wall.

      Personally, and for no good reason, I kind of want to build a rig that uses a radiator from a '57 chevy :)

  • Do you want Terminators? Because this is how you get Terminators. [wordpress.com]

Every nonzero finite dimensional inner product space has an orthonormal basis. It makes sense, when you don't think about it.

Working...