AMD's 90nm Processors to Dissipate 105W?

BlackHawkBlackHawk Bible music connoisseurThere's no place like 127.0.0.1 Icrontian
edited December 2003 in Science & Tech
While Intel Corporation ran into very serious heat dissipation issues with its NetBurst architecture CPUs and 90nm strained silicon technology, looks like its arch rival AMD will also have some hot chips in future.

Sources close to AMD’s partners said the company is going to employ some new power requirements for mainboards designed to support future AMD64 processors, such as Athlon 64 4000+ and the Athlon 64 FX-55, both most probably to be made using 90nm technology. Changes are necessary for mainboards set to come in the second half of 2004.

According to currently available details, maximum current (IDD) of future 64-bit processors from AMD will be 80A, while maximum thermal power will be 105W. These are mandatory requirements for mainboards in the second half of the year. The requirements are only for Socket 939 mainboards, as 754-pin and 940-pin products have very limited future, as AMD roadmap for 2004 revealed.

Apparently, AMD’s 90nm chips will have Vcore at 1.20V – 1.35V, in contrast to current core voltage of 1.40 – 1.55V for 64-bit chips. The first 90nm chips are expected to hit 2.60GHz, but AMD currently does not specify the top speed bin for its new CPUs.

Intel's Prescott 3.60GHz processors are expected to dissipate up to 103W of heat early next year.
Source: X-bit labs.com

Comments

  • Geeky1Geeky1 University of the Pacific (Stockton, CA, USA)
    edited December 2003
    So? The 3.06GHz P4-HT dissipates 105w of heat (Intel's 85w claim is based on "maximum real-world output", not the ABSOLUTE maximum output).

    A SLK-900A with the right fan can handle in excess of 150w of heat; I see no problem with this. Actually, it is a good thing in some ways.

    Why? As CPUs get hotter, you need either more surface area or higher airflow to keep them at the same temperature. Sooner or later, big OEMs such as Dell won't be able to use standard HSFs because the fans would be too noisy, or the heatsink too big. So, they'll switch to one (or both) of two things: watercooling or heatpipes. Dell is actually using the latter already, but they (as usual) screwed up the design, so they don't work properly.

    But, eventually this will force heatpipes and watercooling into the mainstream market, which is a good thing.
  • LeonardoLeonardo Wake up and smell the glaciers Eagle River, Alaska Icrontian
    edited December 2003
    But, eventually this will force heatpipes and watercooling into the mainstream market, which is a good thing.

    Heatpipes? Yes, possible so. Watercooling mainstream? I seriously doubt it. That's just just over the top for mass production.
  • BlackHawkBlackHawk Bible music connoisseur There's no place like 127.0.0.1 Icrontian
    edited December 2003
    IMHO if a simpler and easier technology is developed for watercooling, it could go mass production. Only problem for the retailers would be the warranty.
  • LeonardoLeonardo Wake up and smell the glaciers Eagle River, Alaska Icrontian
    edited December 2003
    That simpler technology would have to be something self contained, that would simply bolt on like a duct or fan. It would also have to be something that the ordinary mom & pop computer store technician or Best Buy service dude could pull out quickly without fear of damage. It just seems to me, that if it were a necessity for mainstream liquid cooling, we'd already see some form of it in laptops. Why, laptops are already very, very hot stage. The new ones are even difficult to use as a true laptop - on the lap.
  • Geeky1Geeky1 University of the Pacific (Stockton, CA, USA)
    edited December 2003
    There are a number of reasons why a laptop has not been seen with water cooling:
    Size- you cannot fit a water pump in a laptop. I've taken the damn things apart, and there is no room in there for a pump, so the laptops would have to be bigger
    Portability- water is heavy (8lbs/gallon)
    Power- a water pump would kill battery life

    A water cooling system that a normal person could work on would be dead easy to do; the reason on one has done it yet is that there is no demand for it. You can even use off the shelf parts; Leo, are you familiar with QDs (Quick Disconnect valves)?
  • BlackHawkBlackHawk Bible music connoisseur There's no place like 127.0.0.1 Icrontian
    edited December 2003
    Leonardo had this to say
    That simpler technology would have to be something self contained, that would simply bolt on like a duct or fan. It would also have to be something that the ordinary mom & pop computer store technician or Best Buy service dude could pull out quickly without fear of damage. It just seems to me, that if it were a necessity for mainstream liquid cooling, we'd already see some form of it in laptops.
    For something like that to happen they really need to rethink the cpu socket and how a hsf connects to it. There's gotta be an easier way than that. Fix that and I think things can get easier. Also a standered in case design might help so everything in each case is the same place. I dunno.
  • primesuspectprimesuspect Beepin n' Boopin Detroit, MI Icrontian
    edited December 2003
    I think standard air cooling has a lot of life left in it. In our current case designs (ATX) they were just never designed with heat in mind. The BTX form factor will address some of this, and we will see fewer "dead zones" inside the case. I mean, look at abit's use of OTES on their "ferrari" grade mobos. We'll be seeing more of that. By properly using ambient intakes, I'm sure we can squeeze a lot more life out of air.
  • Geeky1Geeky1 University of the Pacific (Stockton, CA, USA)
    edited December 2003
    ABIT's motherboard OTES system is most likely almost totally worthless. I haven't done any testing to validate that, but those dinky fans flow so little air that they aren't qualified to cool a single voltage regulator, let alone a stack of them.
  • TheLostSwedeTheLostSwede Trondheim, Norway Icrontian
    edited December 2003
    Geeky,
    Everything that you haven't tested or don't have in your possession isn't all worthless.
  • Geeky1Geeky1 University of the Pacific (Stockton, CA, USA)
    edited December 2003
    True, but I was looking at the A64 Max board the other day. Unless someone ripped off the heatsinks (which is entirely possible, considering that this was at Fry's...), there are no heatsinks on the voltage regulators.

    That 40mm fan pushes <10cfm.

    Most likely, it does very little (if anything) in the way of aiding cooling, and may in fact, harm it. How? That damn big duct is right next to the heatsink. If it interferes with airflow sufficiently, it will be more of a hindrance than a help.

    So Mackanz, you're right... just because I haven't tested it doesn't make it worthless. However, I can arrive at some logical conclusions based on what I know about something. And, IMO, I know enough about air cooling that I can make a fairly good determination of what works and what doesn't. This doesn't look to me like it works all that well. It may very well work better than I think it does, but I tend to doubt it.

    I'll have to wait until I get ahold of one of the boards (if I do) to test that, though.
  • ThraxThrax 🐌 Austin, TX Icrontian
    edited December 2003
    More than the traditional concept of the OTES simply cooling something, the OTES system, the concept, and then proof-of-concept is compelling.

    It shows that manufacturers are finally beginning to take the infant steps into cooling warm-running chips and circuits that haven't received that form of attention before.

    Each step along the lines of the OTES system is a baby-step in the direction the industry needs to go.. System-wide cooling, not just localized component cooling.

    It's a symbolic step, even if it isn't a very good one when it comes to actual application.
  • Geeky1Geeky1 University of the Pacific (Stockton, CA, USA)
    edited December 2003
    True, Thrax. I wasn't thinking about it in those terms, but you're right.
Sign In or Register to comment.