Sign in with
Sign up | Sign in

Conclusion

CORE Or Boost? AMD's And Intel's Turbo Features Dissected
By

Intel arms its Core i5 and Core i7 CPUs with Turbo Boost. AMD's hexa-core Phenom II X6 chips sport Turbo CORE. Both technologies dynamically increase performance based on perceived workloads and available thermal headroom. Which one does the better job?

We can only recommend that AMD and Intel continue implementing and developing their Turbo-oriented features. Both do their job in increasing performance. Since the two approaches are different, though, we found that their outcomes in real life are different, as well.

Let’s start with Intel. The six-core, 3.2 GHz Core i7-980X speeds up a single core by 266 MHz if a single-threaded application wants maximum performance, and it can accelerate all six cores by 133 MHz if thermal headroom allows. This is the main difference compared to AMD’s solution, because Intel's Gulftown design can accelerate single-threaded apps, as well as high-end applications. From a multi-core processing standpoint, Turbo Boost makes more sense than Turbo CORE, since all types of workload benefit when compared to nominal clock speed.

AMD’s Turbo CORE only knows one acceleration mode. It increases clock speed for three cores by up to 400 MHz in the case of the Phenom II X6 1090T 3.2 GHz six-core. This means that all applications that utilize no more than three cores experience immediate acceleration. In this case, we found that AMD's performance improvement is higher, as a 400 MHz upgrade is much more noticeable than Intel’s 133/266 MHz speed bump. The downside is nonexistent acceleration if four to six cores are being taxed.

Neither solution is a clear winner. Intel is better for extremely performance-hungry, multi-threaded environments, while AMD's approach provides more benefits for less-threaded environments. The best Turbo technology would be a more granular one, and a perfect Turbo mode would accelerate a single core by even more than AMD’s 400 MHz, two cores by around 400 MHz, three and four cores by less, and all cores by as much as the remaining thermal envelope allows.

Display all 56 comments.
This thread is closed for comments
Top Comments
  • 17 Hide
    tony singh , July 28, 2010 6:29 AM
    Not as powerful but at least amd is doing some thing to stand up to the monster named i7...
  • 12 Hide
    eddieroolz , July 28, 2010 7:11 AM
    While AMD's implementation is more crude, I think they did okay in this test. I hope they will continue improving their Turbo CORE so it can become more competitive against Intel. After all, Intel had nearly 2 years of head start to perfect their Turbo feature.
  • 10 Hide
    antlee , July 28, 2010 6:52 AM
    It would be nice to include i3 530/i5 750/i7 860 so that we can see if a more aggresive speed bump worth its cost.
Other Comments
  • 17 Hide
    tony singh , July 28, 2010 6:29 AM
    Not as powerful but at least amd is doing some thing to stand up to the monster named i7...
  • 10 Hide
    antlee , July 28, 2010 6:52 AM
    It would be nice to include i3 530/i5 750/i7 860 so that we can see if a more aggresive speed bump worth its cost.
  • 3 Hide
    Emperus , July 28, 2010 6:57 AM
    With manual overclocks being as easy as changing numbers due to unlocked multipliers on both those CPU's, i guess the turbo effect is not that much of a consideration.. Moreover, most of us (IMO) prefer running at single stable clock readings rather than allowing frequent dynamic changes..
  • 12 Hide
    eddieroolz , July 28, 2010 7:11 AM
    While AMD's implementation is more crude, I think they did okay in this test. I hope they will continue improving their Turbo CORE so it can become more competitive against Intel. After all, Intel had nearly 2 years of head start to perfect their Turbo feature.
  • -1 Hide
    rohitbaran , July 28, 2010 7:56 AM
    AMD's Turbo CORE is not that good, but I will give it that it came up with a trick that works, at least for single threaded applications.
  • 0 Hide
    Hamsterabed , July 28, 2010 8:22 AM
    I couldn't tell was Hyper threading on or off for these tests? Also I agree seeing the other i5 and i7 implementations that have more aggressive turbo boost parameters would be good to see in that we could see if the efficiency holds up and what % increase per clock is, like if it is a linear gain or a diminishing returns game.
  • 0 Hide
    SpadeM , July 28, 2010 8:40 AM
    When was this article actually written? I'm asking because the Drivers and Software section for the AMD motherboard isn't present and the BIOS on the Asus and Intel boards are old.
    I'm not saying that with new bios-es and drivers the outcome would be different(or would it be?) but what I am saying is that if this was written a couple of months ago, why wasn't it published then?
  • 2 Hide
    Anonymous , July 28, 2010 9:15 AM
    Quote:
    The 800-series even bumps clock speed up by five clock speed bins for a single core. One speed bin equals 133 MHz at stock speed, so we’re effectively talking about a 133 to 533 MHz dynamic increase.

    Dousn't 5 times 133Mhz equals 666Mhz ?
  • 2 Hide
    Anonymous , July 28, 2010 9:30 AM
    Wow, the benchmark graphs in this article are absolutely nonsensical! What are they calibrated against? Sometimes the Turbo value is at 100%, sometimes the non-turbo value, and it's different for AMD and Intel in the same graph.
  • 0 Hide
    BruceOTB , July 28, 2010 11:04 AM
    Probably amd's development is hindered by intel's patents.
  • 2 Hide
    frozentundra123456 , July 28, 2010 12:48 PM
    Am I reading the graphs correctly?? AMD's 400 mhz overclock is more than 10 percent on half the cores, but performance only increased a few percent at max and in most cases only a percent or two??? Doesnt seem to scale very well with the speed increase. I think intel is the same but their overclock is less so it is hard to say.
    Also, I know it has already been published, but I would like to see the absolute performance of the two chips vs one another. The percent increase does not address at all which chip is actually faster. I know that was not the point of the article, but that is still the most inportant factor, after all.

    And how about some gaming results??
  • 0 Hide
    halls , July 28, 2010 1:03 PM
    Cool article. In the future, when there are cheaper processors available that use these features from both manufacturers, I would like to see a similar article related to games!
  • -1 Hide
    kikireeki , July 28, 2010 1:16 PM
    AMD's 300$ processor on par with Intel's 1000$ !! I think this is more than enough to declare AMD as a clear winner here.
  • 0 Hide
    scook9 , July 28, 2010 1:36 PM
    If on par means taking about 30% longer to complete the same tasks....lol

    And it sounds like the authors "ideal turbo" is exactly what the socket 1156 parts all use....an i7 870 should have been included in these tests
  • 4 Hide
    gxpbecker , July 28, 2010 1:39 PM
    Good to see AMD trading blows with Intel. The main reason i have stuck with AMD is the price/performance. Even with the boosts intel is clearly superior and in most cases really doesnt need the boost.. though it never hurts. Will be interesting to see if Bulldozer come to fruition in early 2011 how much things will change.
  • 0 Hide
    lradunovic77 , July 28, 2010 1:41 PM
    Turbo feature -> retarded. Do old style overclocking!
  • 0 Hide
    saint19 , July 28, 2010 1:48 PM
    Nice article and doesn't exist a winner here just depends of what do u want to do with the CPU. Intel is much better is somethings and AMD have better results in others.

    The price of both Intel and AMD CPUs aren't important here since is a performance chart with stock and turbo features not a price/performance comparative.
  • 2 Hide
    ta152h , July 28, 2010 1:52 PM
    These two write the most boring articles, and come up with a conclusion anyone would have guessed.

    The Lynnfield processors already have a more aggressive turbo boost, by the way.

    The last statement is really poor. The specifics of the processor should determine how much boost they give it, not a blanket statement of discrete amounts. While I agree the boosting could have been improved on these processors, it's got to be a case by case basis depending on the processors' characteristics, and the companies design goals with that specific unit.
  • -1 Hide
    hundredislandsboy , July 28, 2010 2:14 PM
    I liked the article because for me it further justifies why my last CPU purchases made this year were for AMD's 955BE and hexacore 1055T. This article shows that AMD not only can compete with their own version of turbo boost but more importantly, AMD offers better value - $180 for an AMD hexacore versus nearly a grand. $1,000!!, for Intel's hexacore.
Display more comments