Phenom II X4 965 - Can it be Undervolted?

by Gary Key on 8/14/2009 12:00 PM EST
Comments Locked

40 Comments

Back to Article

  • Black Jacque - Thursday, August 20, 2009 - link

    The highest efficiency from a modern PSU would be at about 50% of its rated wattage. AnandTech's testing indicates less than 300W are being drawn under full gaming load and less than 200W at idle.

    Why is there a 1000W Corsair CMPSU-1000HX powering the test rig?

    If articles are going to be written about power efficiency, I'd start at the PSU.
  • wolfman3k5 - Wednesday, September 2, 2009 - link

    Normally I would bother to explain, but seriously you're ignorant and stupid. I mean, what difference does it make what wattage PSU they're using? Just so you know, that Corsair PSU is 80% efficient at full load, so at 30% load that PSU is close to 100% efficient. Get a clue, Jesus...
  • 7Enigma - Wednesday, August 19, 2009 - link

    It might be slightly out of scope for this article but you perhaps should mention GPU undervolting. While the 4890 is signficantly better at idle than the 4870 I have, a reduction in gpu clocks will far outweigh a cpu underclock. For instance using GPUTool (recommended by a member of this comments section) I was able to lower my 4870 (Sapphire Toxic version 750/1000) at idle by 45 watts and 10C (140/220 in 2D applications). This also dropped my case temp by ~10C and allowed my CPU and GPU fans to run slower (and thus quieter).

    That equates to a 37% drop in total system power....just by underclocking the video card at idle...
  • mschira - Monday, August 17, 2009 - link

    As 0 Celsius is not the real 0 but an arbitrary point, %drops in temperature are arbitrary as well.
    Imagine shifting the scale 20deg up. You percentages would go up like crazy...
    M.
  • johnsonx - Tuesday, August 18, 2009 - link

    all done talked about on page 2 of the comments
  • ravaneli - Monday, August 17, 2009 - link

    Here is my little argument - if someone knows what undervolting is, then he would probably be overclocking the CPU, in which case he would actually be overvolting.

    Not to say that if he know what undervolting is he would never buy this marketing shmockery over, say, 955 or even 940, which he can still run @ 3.4 Ghz for a fraction of the price.

    What a nonsense from a consumer standpoint that CPU is.
  • smilingcrow - Monday, August 17, 2009 - link

    Over-clocking and over-volting and two independent parameters.
    I usually over-clock but always at stock voltage or I run at stock clock speed and under-volt. I know some people that under-volt whilst simultaneously over-clocking but in that scenario you don’t usually get much of a clock speed boost.

    My E8400 (E0 3GHz) runs at 3.6GHz at stock voltage and still has some headroom that I haven’t tested yet.
  • BernardP - Monday, August 17, 2009 - link

    Although reducing power consumption and temperature are nice achievements, the in-passing reference to carbon footprint gives unwarranted credibility to the more-than-dubious man-made global warming theory. The green lobby wants us to feel guilty because we use energy. Should we accept this view of the world?
  • smilingcrow - Monday, August 17, 2009 - link

    Thanks for clearing that up for us we can all relax now and throw another log on the fire with no concern for the consequnces of our actions.
  • BernardP - Monday, August 17, 2009 - link

    Q.E.D.
  • smilingcrow - Monday, August 17, 2009 - link

    The main table of data is far too small to be read quickly and the small font size doesn’t help. Why does the main body of text only take up about 40% of the width of my screen which is only running 1680x1050 which isn’t exactly high resolution?

    It’s always good to see under-voting tests but do you need to under-size the way you display the information to match!
  • blackshard - Monday, August 17, 2009 - link

    You can use the gallery bar at the end of the article.
  • smilingcrow - Monday, August 17, 2009 - link

    Thanks but I still find it strange that the main table which holds the key data for the article is so small. Poor design.
  • 7Enigma - Wednesday, August 19, 2009 - link

    Completely agreed. Both Anandtech and DailyTech seem to have a strange formatting that only uses ~30% of my screen (24"). Literally the center 5" is being used, then I have equal-sized grey bars on either side.

    I think they have the website(s) designed for people with 800X600 displays! :p
  • strikeback03 - Thursday, August 20, 2009 - link

    It is about 1000 pixels wide, so there is a little bit of darker gray visible on the sides of a 1024 pixel wide scree. 1024x768 is the generally used minimum screen size for website design right now, look at some other major sites such as espn.com, cnn.com, or weather.com
  • PrinceGaz - Saturday, August 15, 2009 - link

    Interesting article, it's nice to know about those things.

    I must comment on things like talking about a reduction in temperature from 55C to 45C as a reduction of 19%. That is incorrect. If you are going to refer to changes in temperature, they should be relative to the something relevant such as the room temperature of 23.3C, instead of 0C the freezing point of water; if you'd recorded the temperatures in Fahrenheit, would you have given percentage reduction as being 14% (131F to 113F)?

    In this case (55C to 45C compared with room temperature of 23.3C), the temperature reduction was 32%.
  • Finally - Sunday, August 16, 2009 - link

    Are we having fun with maths?
    Why not simply give test result A and then B and let the nerds & geeks do all their calculations from there on out?
  • PrinceGaz - Monday, August 17, 2009 - link

    Why not actually show how much the CPU temperature was really reduced by, compared with ambient temperatures? 55C down to 45C with a room-temperature of 22C or so is a serious reduction, much greater than the reduction in system power consumption. This has important implications such as using said CPU with almost silent low-speed fans or fan-less cooling solutions.

    I think it is worth making clear just how much of an impact on temperatures undervolting can have, especially for people considering building an almost silent HTPC system.
  • strikeback03 - Thursday, August 20, 2009 - link

    Should you then investigate the impact of varying room temperature? What about summer, when room temperature can be pushing 30C?
  • johnsonx - Sunday, August 16, 2009 - link

    good point - using air cooling (or water cooling, which is air cooling by proxy), the reference point must be the ambient temperature of the test environment. comparing the temperature readings to an arbitrary 'zero' point which happens to be the freezing point of water is utterly meaningless.

    an even better illustration of this error would be if the temperature readings were in degrees kelvin... referenced to absolute zero, the percentage reduction would have been less than 2%, which everyone would of course have concluded wasn't worth the effort!
  • PrinceGaz - Monday, August 17, 2009 - link

    I did consider mentioning using the much more scientifically useful Kelvin scale with absolute zero as the minimum point temperatures are compared against as being the only possible fixed scale which would make any sense, but decided against that as it would lengthen and dilute what I had written. I think the only people who regularly use the Kelvin scale when it comes to CPUs are those whose daily shopping-list includes a large tub of LN2 :)

    The important thing we both agree on is that temperature differences have to be relative to something relevant. Perhaps more importantly, the much higher percentage reduction in CPU temperature by undervolting (relative to room-temperature) compared with the reduction in system power consumption, is exactly what would be expected. Undervolting the CPU is only really reducing the power consumption of that component alone (the rest of the system eats the watts just as before), so even a fairly small decrease in system power consumption should result in a more significant decrease in CPU temperature.
  • MrSpadge - Saturday, August 15, 2009 - link

    I wonder why they choose such a high stock voltage. Apparently it's not really neccessary as they could easily get by with 1.35 V and probably with 1.30 V on many of these well-binned chips.

    Are these first ones just cherries.. or are they trying to get good press due to "oh, our chips are soo good, they can easily hit 4 GHz at stock voltage!". And thereby take the hit of specifying 140 W TDP instead of 125 W (painful in my eyes) and take the hit of having a higher load power consumption than any current Intel CPU (also painful)? And hope that *gamers* won't care?

    What was the last Intel CPU you've seen with 1.40 V? I'm sure it was some 90 nm chip, certainly not 45 nm!

    MrS
  • MrSpadge - Saturday, August 29, 2009 - link

    Now that makes sense: [url=http://www.nordichardware.com/news,9821.html">http://www.nordichardware.com/news,9821.html]AMD reduces TDP rating of Phenom II X4 965[/url].
  • blackshard - Saturday, August 15, 2009 - link

    AMD may desire to raise 965BE yields declaring a higher stock voltage for the whole model line-up.

    BTW, you can't compare 45nm AMD SOI production with Intel 45nm production. AMD with 45nm and 1.40v has 140W TDP, while Intel has much lower operating voltage but still 130W TDP with latest Nehalem.

    Power requirements are comparable, operating voltages aren't.
  • MrSpadge - Sunday, August 16, 2009 - link

    Well.. they could sell the better chips at 1.35 V (still enough margin) and the worse ones at 1.40 V. Later on when enough chips can get by with <1.35 V they could officially lower the TDP rating to 125 W. This has been done with the 9950 before and e.g. the old X2 3800+ came in 1.35 V and 1.30 V varieties. They could do this and save some power, if they wanted to. I assume AMD's not stupid, so they know their chips need less voltage. Voltage is bad: it shortens chip lifetime significantly and makes you look worse in power consumption measurements. hat'Ts why I'm asking: why are they doing it nevertheless?

    Sure, there are differences in the process. But these CPUs all have to get along with the same physics ;) Intel reaches a comparable TDP because ~130 W is what shaped to be the maximum which desktop systems can handle without too much hassle (more cool = increased system cost). They're achieving it at a lower voltage because in the i7 design more transistors are switching during the clock cycles (=more work gets done if these transistors are put to good use). This and the TDP dictate the maximum voltage they can apply to their chip.

    That Intel can reach the same clock speeds at lower voltages is a result of clever chip design and details of the manufacturing process. So, yes, you have to be careful in comparing voltages. But saying that such comparisons were meaningless would be utterly wrong.

    MrS
  • blackshard - Sunday, August 16, 2009 - link

    Yes, but then they have to sell 1.40v parts with lower price than 1.35v. Since they can't overprice their processors (965BE is currently a bit overpriced if compared to 2.66 Ghz Nehalem, and will sure be overpriced with i5 coming next month), they have to sell two 3.4 Ghz flavours with different prices. Also they may need more testing, and it has a cost. It has more sense to sell all equal processors now, then introduce a 125W refinement when possible (if possible).

    Intel can reach lower voltages because they have to (and can) use lower voltages with high-k dielectrics and metal gates. Probably imho their leakage currents will be much larger with higher voltages. Instead AMD has SOI which helps reducing leakage, but can't reduce voltages. That's the reason I say voltages can't be really compared. Also TDP's can't be really compared, since AMD states that their TDP is the maximum power drain, while Intel states that it is maximum typical power drain.
  • MrSpadge - Monday, August 17, 2009 - link

    No, they should just offer both versions of the chip (and switch when the time is right) for the same price, without special markings (as has been done for the lower TDP version of the 9950, the X2 3800+ and probably many other ones). And they need to test and speed-bin the chips anyway, so I don't think that would be too much of a hassle (=cost).

    I know TDPs can't be directly compared. However, they're guidelines.. and when you take a look at test you'll likely find that "130W" i7 CPUs need less juice than most "125W" AMDs. So I don't think this adds anything to the discussion: AMD going from 125W to 140W is painful for the user, cost cooling and noise wise.

    And regarding the 2nd part: sorry, but I think you got it totally wrong. SOI helps reduce substrate leakage and leakage between elements in the plane (usually taken care of by a "FOX" field oxide layer), but does'n affect much else. A High-K gate dielectric reduces gate leakage currents by several orders of magnitude and in turn enables one to build faster transistors (which achieve a higher switching speed at similar voltages). The metal contact doesn't add much, just a little series resistence reduction. It's being introduced together with the high-k because the traditional highly doped poly-Si doesn't mix as well with the high-k (some HfO) as it does with SiO2.

    To first approximation power consumption and lifetime still scale the same way with voltage, regardless of SOI or high-k + metal. Voltage is bad in either case. What AMD is really doing here is overvolting their chips to give them more frequency headroom, normally only exploited by overclockers. That's why I suppose they do it for good press, nevermind the drawbacks.

    MrS
  • blackshard - Monday, August 17, 2009 - link

    Dunno if it has sense for AMD to ship two kinds of the same processors, changing just for a minor detail to save 7W of power :/
    Also consider that lousy motherboards may cause some small or large voltage drop during massive cpu usage, so maybe AMD is just taking care of this.

    About the second part, I'm sure you're right. I was misinformed.
  • MrSpadge - Saturday, August 22, 2009 - link

    Hi. Well, I think we can leave it at that. I calculate savings of 10 W when going from 1.40 V to 1.35 V.. but this does not really change the picture. I still don't like it, but it's not catastrophic. And I have to admit that further binning would cost something and would get them at best *questionable* advantages ;)
  • strikeback03 - Monday, August 17, 2009 - link

    Those definitions of TDP always seem a little odd, since the comparisons between actual draw of the processors against their TDP that I have seen all show the Intel processors at well below their TDP, while AMD processors are much closer. For example, the numbers in this ( http://www.anandtech.com/casecoolingpsus/showdoc.a...">http://www.anandtech.com/casecoolingpsus/showdoc.a... ) test are a few years old now, but the Intel processors generally come in well under their rated TDP, with the QX6850 the closest at about 80% of its TDP. Meanwhile the AMD processors all seem to be at or above their TDPs (though the naming of the Athlon X2s makes it hard to determine which version they were testing).
  • blackshard - Monday, August 17, 2009 - link

    Take a look here for example:

    http://www.anandtech.com/cpuchipsets/showdoc.aspx?...">http://www.anandtech.com/cpuchipsets/showdoc.aspx?...

    2.66 Ghz i7 has higher power consumption than 955BE. Not talking about performance per watt, 955BE is rated at 125W and i7 is rated at 130W.

    Also consider that in the Phenom I period no AMD motherboards had any kind of energy saving feature like DES/EPU. This lead to overgrown power requirements for phenoms (parts ate too much current + no optimization in voltage regulation on the mobos). Now the situation is far better because there exist EPU/DES/Dr.Mos features for AMD, and AMD 45nm are much more competitive with intel 45nm parts.
  • strikeback03 - Thursday, August 20, 2009 - link

    Those are total system power measurements, not CPU-only measurements. I wasn't talking performance per watt either, I was comparing measured power drawn by the CPU only to the rated TDP of that CPU, and pointing out that Intel has traditionally been much more conservative in the TDP assigned to processors than AMD has.
  • blackshard - Thursday, August 20, 2009 - link

    Sure they are measurements of the total system power, but actually they have comparable idle power requirements, and other components are comparable too, so with some margin of error (including PSU and VRM efficiency) you may obtain some sort of raw cpu power usage.

    About "traditional" TDP, Intel states that their TDP is calculated on a typical load, while AMD states that their TDP is calculated on maximum load, impossible to achieve in a normal condition.

    If you jump the core2 era, Intel wasn't so conservative and, just to push some meaningless numbers, looks like it will not be so conservative even in the near future:

    http://www.hwupgrade.it/articoli/cpu/2264/consumo_...">http://www.hwupgrade.it/articoli/cpu/2264/consumo_...

    AFAIK all core i7 processors have the same TDP of 130W, while 965BE has 140W TDP. i7 have the power consumption advantage of DDR3-1333 Mhz instead of DDR2-1066 Mhz of the AMD setup, and idle power consumption is comparable (4W of difference)
  • strikeback03 - Friday, August 21, 2009 - link

    Intel wasn't conservative with Core2? you mean like the 136W TDP QX9770 that draws 86W at full load?
  • destrobig - Saturday, August 15, 2009 - link

    Those tables look they got hit with an ugly stick. Two separate ugly sticks by the looks of it.
  • MadMan007 - Saturday, August 15, 2009 - link

    Bery nice but are there any plans do do this for any other CPUs? Ime over the last two years every CPU can be undervolted a decent amount at stock and save a noticable amount of power, this isn't unique to this CPU obviously. It might be interesting to see how much other CPUs can have their power draw decreased by optimizing voltage.
  • gigahertz20 - Saturday, August 15, 2009 - link

    Gary Key: "Damn, I wonder what that thing on my desk is then" when referring to if AMD has final RV870 silicon.


    Any other tid bits of info Gary? Benchmarks on Sept. 10th maybe....or later?

  • Roland00 - Sunday, August 16, 2009 - link

    And you won't get any new info till September 10th due to Non Disclosure agreements.
  • deputc26 - Friday, August 14, 2009 - link

    for what it's worth my 940 can do 1.22v minimum at stock 3.0ghz. 3.4ghz requires 1.3875v
  • ciparis - Friday, August 14, 2009 - link

    [quote]the last minute change from a 125W TDP rating to a 140W TDP rating had us scratching our heads and those of the motherboard suppliers[/quote]

    That sounds rather friendly :)

Log in

Don't have an account? Sign up now