Slashdot Mirror

← Back to Stories (view on slashdot.org)

Cooling Down Hot Processors

Posted by CmdrTaco on from the feeling-hot-hot-hot dept.

DonnaMai writes "Face it: the only scorching hot thing you want with a chip is salsa. Any other overheating is potentially counterproductive, and can be downright damaging to the microprocessor -- or other components. This article uncovers potential ways to chill the chips."

18 of 293 comments (clear)

  1. cool chips by Luxifer · · Score: 5, Interesting

    What we really need is a spare, low-power, mimimal processor without all the fancy extensions that you can switch to when you're just, say, reading a webpage or email, or such.. you could integrate this right into the motherboard and completely shut down your processor when you're not using it for real stuff. IMHO... maybe an engineer will give me a reason this is unreasonable.

    1. Re:cool chips by detritus` · · Score: 4, Interesting

      Because configuring a MB for 2 processors is going to be a lot more complicated than the switching frequency model they use now (ie. Athlon XP-M and Pentium M chips). This method is a lot less complex than attempting to use 2 processors, one for high load and one for low load. (imagine trying to determine what's considered high load? after all web browsing actually takes a fairly high CPU while rendering some pages, especially with the more complex XML and (ick) flash pages that are out there). I'm typing this on a Athlon XP-M laptop right now and it actually stays quite cool until the CPU load goes above a certain point and it jumps fromm 533Mhz to 1.74GHz, at which point if its sustained it almost gets uncomfortable for laptop use.

      --
      drunk chemists
    2. Re:cool chips by Dracolytch · · Score: 3, Interesting

      Dude, 90% of the processor power IS only used when playing a game. I have my system monitor open, and as I type this on my development computer, I'm at a steady 8 to 11 percent. 5% of that (half my CPU load) is running the flash animation on the top of this page.

      CPUs today are bored 90% of the time. Doing word processing and stuff, your CPU use is probably below 10%. The sluggishness has almost NOTHING to do with CPU speed. The big thing is load times, which is correlated to disk usage. RAM really is virtually unlimited, and the only time I've hit the limitations of my CPU are when I'm doing things like writing programs to breed multimedia files.

      If you're talking about lack of responsiveness, you sound like you don't need a faster processor... it sounds like you need a 1Ghz machine with 256 MB of decent RAM and a 10,000 RPM SATA drive. 512 MB of RAM if you surf with multiple windows and work with spreadsheets at the same time. Swear to god, that'll knock most of your lack of response time to near nothing.

      ~D

      --
      This sig has been enciphered with a one-time pad. It could say almost anything.
  2. Razored processor architecture by Raul654 · · Score: 4, Interesting

    Dr. Trevor Mudge (U. Michigan) came to give a lecture at my University last year. He had an interesting proposal which I suspect is probably going to end up being used in nearly every architecture. The energy usage of a procesor is proportion to the square of the voltage - so dropping it as much as possible is desirable. The only problem is that once you get too close, you start getting bit level errors. He proposes to use a shadow register to keep track of values as they pass through and detect bit errors automatically, and route around them. If run at the optimal voltage (1.4 volts) a razored process will see a dramatic drop in energy consumption with a virtually-nonexistant hit to processing power.

    --


    To make laws that man cannot, and will not obey, serves to bring all law into contempt.
    --E.C. Stanton
  3. Liquid Nitrogen, of course by tajmorton · · Score: 3, Interesting

    As reported on /. a while back. "Record Attempt: The 5 GHz Project"

    --
    Tell the truth and you won't have so much to remember.
  4. Overheating vs. High Operating Temps by BenBenBen · · Score: 3, Interesting
    The original poster makes the very common mistake of confusing hot chips with overheating chips - just because 90degC is hot to us meatbags, doesn't mean that it's dangerous to have ICs who run at this temp.

    There are many, many ICs that run happily for years at high operating temperatures (Blaupunkt's Digiceiver digital RF processor being one I'm familiar with).

    Saying this, I do run a 12" G4 PowerBook and can appreciate the delights of a 20degC chip...

    --
    The Slashdot Paradox: "100% Overrated"
  5. What about by LukaFox · · Score: 3, Interesting

    a liquid cooling system that is also a conversation piece http://nobispro.com/aquatank/?

  6. Ducting by kavachameleon · · Score: 4, Interesting

    When I first got my Prescott chip, it ran *way* too hot. Realized that the stock thermal pad was just acting as insulation, so I scraped it off and replaced it with Ceramique. It still ran warm, so I superglued a piece of 3" PVC pipe to my case fan. Now air blows right onto the processor area, and the CPU temps are great. I highly recommend the ducting. Cheap, easy, and oh-so-geeky.

    1. Re:Ducting by ctr2sprt · · Score: 2, Interesting
      This is the way most rackmount servers work. Because of space concerns they can't easily fit a regular heatsink/fan combo in the case, especially with 2U (3.5" tall) or 1U (1.75" tall) cases. So they put a bunch of fans on the front or rear (or both) of the chassis and use a plastic duct to route the air over the processors and vent it out of the case. It also seems to be a common tactic among the low-end home desktop systems: the power supply fan is ducted over the CPU and out the back of the case. The motivation there isn't space or cooling efficiency, it's cost (fewer fans) and noise level (again, fewer fans).

      I think this is increasingly the way we are going to have to go as we try to squeeze a little more life out of air-cooling. But I really think we are going to have to move to water cooling soon. I'm a little surprised it isn't already happening with servers: due to the space constraints, they would be the biggest beneficiaries. And due to the efficiency benefits, you could cool several servers - maybe even an entire rack - with one radiator (assuming of course that the radiator is designed for that). Smaller installations, with only a few racks, might even be able to eliminate expensive dedicated AC units.

      Even in the home market, you could cool a radiator pretty well with a small number of large, low-RPM fans. It should result in a cooler system. My understanding is that at present water cooling is not much quieter than air cooling, if it's quieter at all, but I think that's more a limitation of currently implementations (which target the insane overclocker crowd, who don't care as much about noise).

  7. More efficient software by G4from128k · · Score: 2, Interesting

    Call me a curmudgeon, but it seems like most of the heat is created by wasted cpu cycles. Eye candy is nice, but at 200 million computers in the U.S. alone, each Watt saved represents about $31 million in annual energy costs (assuming 40 hrs/wk, @ $0.074/kWHr. Reducing power consumption by 10 W would pay for a lot of good beer to fuel software development for more efficient software.

    --
    Two wrongs don't make a right, but three lefts do.
  8. Excuse my Ignorance.... by devphaeton · · Score: 2, Interesting

    ...but would increasing the size of the actual chip help any? Like a vented, flow-through design. The actual chip is about the size of a fingernail, i know, but if we increased it to the size of the whole plastic skirt around it (that which has all the pins) wouldn't that help heat dissipation?

    I haven't taken any measurements, but i'm willing to bet that the skirting around that wouldn't be much bigger- we've got more length on all sides, so we don't have to go as deep.

    However, i don't design microprocessors, and don't know anything about electronics, so i'm betting there's something i'm missing out- i.e. the impedance or capacitance effects of increasing the microscopic traces. I would assume someone has thought of this once before, but with all the rush to make stuff smaller and smaller, can it be overlooked?

    It's not like we don't have any spare room in a PC case, y'know...

    --


    do() || do_not(); // try();
  9. Re:Better than water cooling by Blue-Footed+Boobie · · Score: 5, Interesting
    I built one of those a while back...

    Here it is in the "mostly finished" stage:

    Picture 1

    Picture 2

    --
    DAMN YOU OCTODOG! DAMN YOU TO HELL!
  10. Use athcool. by Nosf3ratu · · Score: 1, Interesting

    apt-get install athcool

    --
    The old Lie: Dulce et decorum est Pro patria mori
  11. Obligatory link by Spy+der+Mann · · Score: 2, Interesting

    How to fry an egg on an XP

  12. Re:Laptops by LurkerXXX · · Score: 5, Interesting

    Someone needs to figure out an efficient way of makeing use of the huge surface area on the lid of a laptop for cooling. When in operation, it's facing away from you, so you wouldn't feel all the heat from it. The problem is tranferring the heat to a part that has to hinge away from the area that's making the heat. Plus there might be problems if it transfers too much heat to the LCD screen rather than to the air on the surface away from the user. It just seems a shame not to be able to take advantage of all that surface area.

  13. Re:Water cooling is inevitable by A.+Rimmer · · Score: 2, Interesting

    Water cooling is the WORST for of cooling if have encountered.

    When a water filled radiator is used on a cpu instead of a fan the heat that leaves does not get dealt with. Small components overheating aren't any better than the cpu. Sure, you can put in a powerfull (loud) set of case fans to deal with the extra heat, but what's the water system there for then?

    I worked in a small "geeks for hire" computer support team. ALL THREE of the water cooled systems I worked inside of had HEAT problems. And one was leaking!

    The problem with computers heating up is caused by tower cases. If you lay the components out on a sheet of plywood and use regular fans you get superb cooling. Submerged in mineral oil works great too. Don't be an idiot though, you need depth, a few millimeters over the cpu won't cut it (this guy is going to use a pump and copper radiator for what would have cost $2 in mineral oil!).

  14. Re:You Insensitive Clod by jovlinger · · Score: 2, Interesting

    well,

    the linux kernel (and presumbaly the windows kernels as well) issue the hlt instruction when idle, which allows parts of the chip to power down, significantly reducing power and heat.

    (some/all?) desktop P4s can also scale down clock cycles under software control, but that is significantly coarser grain than the hlt instruction. When it works, the hlt instruction should be sufficient to keep the cpu cool when not doing anything.

    Of course, these recourses don't always work. My P4's fan is currently running very loud: I'm unsure whether the fan is on its last legs, or the CPU is erroneously not doing the hlt thing. Some suggestions are that SMP architectures hate hlt, and that hyperthreaded p4s are treated like SMPs. I'm still actively researching this. Anyone want to chime in?

  15. Re:Cool it down by gnuman99 · · Score: 2, Interesting
    AMD Athlon XP 2200 - Best AMD to date. Runs very hot (55-60c)...A few times I've approached 80c

    Something is broken with either your installation, motherboard, fan or air circulation in the case. My Athlong *never* goes above 50. Most of the time, it runs under 40. Stock heatsink/fan.

    Your setup is messed up.