Overclocking and 22nm

In the old days, whenever Intel transitioned to a new manufacturing process it was accompanied by increased overclocking headroom thanks to the reduction in power consumption and increase in switching speed afforded by the new transistors. To be honest, it's surprising the ride has even lasted this long.

Intel's 22nm process (P1270) is the most ambitious yet. The non-planar "3D" transistors promise to bring a tremendous increase in power efficiency by increasing the surface area of the transistor's inversion layer. It's the vehicle that will bring Intel into new form factors in mobile, but we're around a year away from Haswell's introduction. Rather than 22nm being a delivery platform for Ivy Bridge, it feels like Ivy Bridge is being used to deliver 22nm.

The process is still young and likely biased a bit towards the lower leakage characteristics of lower voltage/lower wattage CPUs, such as those that would be used in Ultrabooks. These two factors combined with some architectural decisions focused on increasing power efficiency result in what many of you may have heard by now: Ivy Bridge won't typically overclock as high as Sandy Bridge on air.

The frequency delta isn't huge. You'll still be able to hit 4.4—4.6GHz without resorting to exotic cooling, but success in the 4.8—5.0GHz range will be limited to water alone for most. Ivy Bridge is also far more sensitive to voltage than Sandy Bridge. Heat dissipation can increase significantly as a function of voltage, so you'll want to stay below 1.3V in your overclocking attempts.

Dr. Ian Cutress, our own Senior Motherboard Editor, put Ivy Bridge through a pretty exhaustive investigation if you want more details on exactly how the chip behaves when overclocking and how best to overclock it.

For the past few years I've been focused on power efficient overclocking. I'm looking for the best gains I can get without significant increases in core voltage. With my 3770K I was able to reliably hit 4.5GHz with only a 140mV increase in core voltage:

The end result is a 15—28% overclock, accompanied by a 32% increase in power consumption. The relationship between overclock speed and power consumption actually hasn't changed since Ivy Bridge, at least based on this datapoint.

Ivy Bridge Overclocking
Intel Core i7 3770K Stock 4.6GHz Overclock % Increase
Load Power Consumption 146.4W 204W 39.3%
x264—2nd Pass 41.8 fps 49.5 fps 18.4%

As always, your mileage may vary depending on the particular characteristics of your chip. Ivy Bridge can be overclocked, but at least initially it's not going to be as good of an overclocker as Sandy Bridge. Over time I expect this to improve somewhat as Intel's 22nm process matures, but by how much remains a question to me. It's unclear just how much of these limits are by design vs. a simple matter of process maturity.

Die Size and Transistor Count The 7 Series Chipset & USB 3.0
Comments Locked

173 Comments

View All Comments

  • JarredWalton - Tuesday, April 24, 2012 - link

    I don't think it's a mystery. It's straight fact: "One problem Intel does currently struggle with is game developers specifically targeting Intel graphics and treating the GPU as a lower class citizen."

    It IS a problem, and it's one INTEL has to deal with. They need more advocates with game developers, they need to make better drivers, and they need to make faster hardware. We know exactly why this has happened: Intel IGP failed to run for so long that a lot of developers gave up and just blacklisted Intel. Now, Intel is actually capable of running most games, and so long as they aren't explicitly blacklisted things should be okay.

    In truth, the only title I can think of from recent history where Intel could theoretically work but was blacklisted by the game developer is Fallout 3. Even today, if you want to run FO3 on Intel IGP (HD 2000/3000/4000), you need to download a hacked DLL that will identify your Intel GPU as an NVIDIA GT 9800 or something.

    And really, there's no need to blacklist by game developers, because you can't predict the future. FO3 is the perfect example: it runs okay on HD 3000 and plenty fast on HD 4000, but the shortsighted developers locked out Intel for all time. It's better to pop up a warning like some games do: "Warning: we don't recognize your driver and the game may not run properly." Blacklisting is almost more of a political statement IMO.
  • craziplaya21 - Monday, April 23, 2012 - link

    I might be blind or something but did you guys not do a comparison between an original bluray IQ vs an encoded 1080p IQ by quicksync??
  • toyotabedzrock - Monday, April 23, 2012 - link

    Why is Intel disabling this on the K parts? And why disable vPro?
  • jwcalla - Monday, April 23, 2012 - link

    First, a diversion: "I was able to transcode a complete 130 minute 1080p video to an iPad friendly format..." Just kill me. Somebody please. Why do consumers put up with this crap? Even my ancient Galaxy S has better media playback support.

    It's the same story with my HP TouchPad: MP4 container or GTFO. Who can stand to re-encode their media libraries or has the patience to deal with DLNA slingers when the hardware is perfectly capable of curb-stomping any container / codec you could even conceive? Just get an Android tablet if this is the crap they force on you. Or, in the TouchPad case, wipe it and install ICS.

    As for the article... did I totally misunderstand the page about power consumption? I got the impression that idle power is relatively unchanged. I must be misreading that. Or maybe the lower-end chips will show a stark improvement. Otherwise I totally miss the point of IVB.

    I'm beginning to lose confidence in Intel, at least in terms of innovation. These tick-tock improvements are basically minor pushes in the same boring direction. From an enthusiasts' perspective, the stuff going into ARM SoCs is so much more interesting. Intel makes great high-end CPUs but it seems that these are becoming less important when looking at the consumer market as a whole.
  • Anand Lal Shimpi - Monday, April 23, 2012 - link

    Idle power didn't really go down because at idle nearly everything is power gated to begin with. Any improvements in leakage current don't help if the transistors aren't leaking to begin with :)

    Your ARM sentiments are spot on for a huge portion of the market however. Let's see what Haswell brings...

    Take care,
    Anand
  • thomas-hrb - Monday, April 23, 2012 - link

    I disagree with the testing methodology for the World of Warcraft test. Firstly no gamer of any game buys hardware so they can go to the most isolated areas in a game. Also the percentage of who can pay for one of these CPU's who would be playing at 1650x1050, would be pretty small.

    I've been playing WoW for a number of years and I don't care about 60fps+ because my monitor won't display it anyway. I care about minimum fps and average fps. nVidia's new adaptive vsync is a great innovation, but I am sure there are other tests that while not as controlled and repeatable is a much indicative of real world performance (the actual reason behind purchasing decisions).

    One possible testing methodology you could look into is to take a character into one of the topend 25man raids. There are 10 classes in WoW and my experience is that a 25man raid will show up every single possible spell/ability and effect that the game has to offer in fairly repeatable patterns.

    I agree that it is not the most scientific approach but I put more stock in a friend saying "go buy this cpu/gpu you can do all the raids and video capture and you get no lag" than you telling me that this cpu will give me 100+ fps in the middle of nowhere. There is a fine line between efficient and effective. I am just hoping that you can dial down the efficiency and come up with a testing methodology that actually produces a metric I can use in my purchasing decisions. After all that is one of the core reasons most people read reviews at all.
  • redisnidma - Monday, April 23, 2012 - link

    Expect Anand's Trinity review to be heavily biased with lots of AMD bashing.
    This site is so predictable...
  • Nfarce - Monday, April 23, 2012 - link

    Oh boy. Another delusional red label fangirl. Maybe when AMD gets their s**t together Anandtech will have something positive to review in comparison to the Intel offerings at the moment. Bulldozer bulldozed right off a cliff. And don't get me wrong: I WANT AMD to whip out some butt-kicking CPUs to keep the competition strong. But right now, Intel is not getting complacent and keep stepping their game up when the competition isn't even on the same playing court. But that's just for now. If AMD continues to falter, Intel may not be as motivated to stay ahead and spend so much R&D in the future. After all, why put the latest F1 car on the track when the competition can only bring a NASCAR car to every track?
  • Reikon - Monday, April 23, 2012 - link

    Temperature is in the overclocking article.

    http://www.anandtech.com/show/5763/undervolting-an...
  • rickthestik - Monday, April 23, 2012 - link

    An upgrade for me makes sense as my current cpu is an Intel Core 2 Quad and the new i7-3770K will be a pretty significant upgrade...2.34Ghz to 3.5Ghz and the heaps of additonal tech to go with it.
    I could see a fair number of Sandy Bridge owners holding off for Haswell, though for me this jump is pretty big and I'm looking forward to seeing what the i7-3770K can do with the Z77 motherboards and a shiny new PCI 3.0 GPU.

Log in

Don't have an account? Sign up now