Power Gating

With 1.45 billion transistors on die, Llano relies on extensive power gating in order to keep things in order. The APU is split into two independent power islands: the CPU and the GPU. The memory controller and North Bridge both live on the GPU's power island. Each island has its own independent voltage source.

Everything from an individual CPU core to the entire GPU or virtually the entire APU package can be power gated. AMD provided photon recombination images to show the impact power gating the GPU can have on leakage current:

Although not depicted above, Llano can also fully power gate the x86 CPU cores or both the CPU and GPU if the entire APU is in a deep sleep state. Being able to completely power gate CPU cores or the GPU is an important part of enabling the next major feature of Llano: Turbo Core.

Turbo Core

All processors whether CPUs, GPUs or APUs have to be designed to strict thermal and power limits. OEMs need to know exactly what sort of chassis they'll be able to build around these chips and as a result the chip vendors provide guidance in the form of specifications, including the chip's thermal design point (TDP).

In the old days of microprocessors things were simple. You had a single core that ran all the time and it consumed all of the available thermal budget allocated for that core. AMD and Intel eventually enabled dynamic clock frequencies which let your single core underclock itself when it wasn't being used, which helped reduce power and extend battery life. Then came the multi-core era.

CPUs couldn't just start putting out twice as much heat now that they had two cores; instead, each core had to consume less power. The chip guys achieved this by running the cores at lower frequencies and voltages than they did in the single-core days. Two cores paved the way to four cores, which meant another reduction in clock speed per core. Sure we got much better multi-threaded performance, but for single-threaded applications performance wasn't as great as it could be. Users had to make a tradeoff: good multi-threaded performance or good single-threaded performance; you couldn't have both. Until power gating came along that is.

Without power gating you can never really shut off power to an idle core. The transistors aren't switching but power is still dissipated thanks to leakage current. Remember that transistors don't simply stop conducting electricity when they're off. The smaller they get, the more leaky our beloved transistors become. Power gating lets you physically block the flow of current to the transistors that are being gated, so when they're off, they're actually off. With an idle core shut off, now you have the extra TDP headroom to run any active cores at higher frequencies.

Intel does this with a technology it calls Turbo Boost. Intel looks at current draw and thermal sensors spread out all over the chip and determines when it has the available thermal headroom to turbo up any active cores. AMD implements a similar technology in Llano (and previously in their hex-core desktop parts) called Turbo Core.

I say similar but not identical because AMD's approach differs in a very important way. While Intel looks at current draw and temperature data, AMD looks at workload. Each activity within the Llano APU is assigned a certain power weight (e.g. an integer multiply is known to require a certain amount of power). Llano is aware of the operations it's currently working on and based on the weights associated with these operations it comes up with a general estimate of its power consumption on a per core basis. I mention this is an estimate because it correlates digital activity to power consumption; it doesn't actually measure power consumption.

Based on the number of events and their individual weights, AMD estimates the power consumption of each core and determines how much TDP headroom exists in the system. If the OS is requesting the highest p-state from the CPU and there's available TDP headroom, Llano will turbo up any active cores up to a maximum frequency. Like Sandy Bridge, Llano is able to temporarily exceed the APU's maximum TDP if it determines that the recent history of power consumption has been low enough that it'll take a while for the APU to ramp up to any thermal limits.

One major limit of Llano's Turbo Core is that the GPU can't turbo up in the event of the CPU cores being idle. Only the CPU cores can turbo up if they have available headroom. I suspect future versions of Llano will probably enable GPU Turbo Core as well:

It's unclear to me at this point what shortcomings or advantages exist for AMD's Turbo Core method vs. Intel's Turbo Boost. At the bare minimum the two are finally comparable although they use different approaches to attain a similar end result. AMD doesn't yet have a method of actually displaying Turbo Core frequencies, unfortunately, so we're operating a bit blind at this point. Over time I hope to have a better idea of how AMD's solution stacks up.

The GPU Introducing Mobile Llano
Comments Locked

177 Comments

View All Comments

  • Brian23 - Tuesday, June 14, 2011 - link

    Jarred/Anand,

    Based on the benchmarks you've posted, It's not very clear to me how this CPU performs in "real world" CPU usage. Perhaps you have it covered with one of your synthetic benchmarks, but by looking at the names, it's not clear which ones stress the integer vs floating point portions of the processor.

    IMO, a test I'd REALLY like to see is how this APU compares in a compile benchmark against a C2D 8400 and a i3 380M. Those are both common CPUs that can be used to compare against other benchmarks.

    Could you compile something like Chrome or Firefox on this system and a couple others and update the review?

    Thanks! I appreciate the work you guys do!
  • ET - Tuesday, June 14, 2011 - link

    PCMark tests common applications. You can read more details here: http://www.pcmark.com/wp-content/uploads/2011/05/P...

    While I would find a compilation benchmark interesting, are you suggesting that this will be more "real world"? How many people would do that compared to browsing, video, gaming? Probably not a lot.
  • Brian23 - Tuesday, June 14, 2011 - link

    Thanks for the link. I was looking for something that described what the synthetic benchmarks mean.

    As for "real world," it really depends from one user to the next. What I was really trying to say is that no-one buys a PC just to run benchmarks. Obviously the benchmark companies try to make their benchmarks simulate real world scenarios, but there's no way they can truly simulate a given person's exact workload because it's going to be different from someone else's workload.

    If we're going down the synthetic benchmark path, what I'd like to see is a set of benchmarks that specifically stresses one aspect of a system. (i.e. integer unit or FPU.) That way you can compare processor differences directly without worrying about how other aspects of the system affect what you're looking at. In the case of this review, I was looking at the Computation benchmark listed. After reading the whitepaper, I found out that benchmark is stressing both the CPU and the GPU, so it's not really telling me just about the CPU which is the part I'm interested in.

    Switching gears to actual real world tests, seeing a compile will tell me what I'm interested in: CPU performance. Like you said, most people aren't going to be doing this, but it's interesting because it will truly test just the CPU.
  • JarredWalton - Tuesday, June 14, 2011 - link

    Hi Brian,

    I haven't looked into compiling code in a while, but can you give me a quick link to a recommended (free) Windows compiler for Chrome? I can then run that on all the laptops and add it to my benchmark list. I would venture to say that an SSD will prove more important than the CPU on compiling, though.
  • Brian23 - Tuesday, June 14, 2011 - link

    Jarred,

    This link is a user's quick how-to for compiling chrome:
    http://cotsog.wordpress.com/2009/11/08/how-to-comp...

    This is the official chrome build instructions:
    http://dev.chromium.org/developers/how-tos/build-i...

    Both use Visual Studio Express which is free.

    I really appreciate this extra work. :-)
  • krumme - Tuesday, June 14, 2011 - link

    The first links at the top is sponsored
    3 times exactly the same i7 + 460 ! ROFL
    Then 1 i7 with a 540
    Damn - looks funny, but at least it not 1024 *768 like the preview, but the most relevant resolution for the market - thank you for that
  • Shadowmaster625 - Tuesday, June 14, 2011 - link

    Man what is it with this dumb yuppie nonsense. No I dont want to save $200 because I dont actually work for my money. Hell, if you're even reading this site then it is highly likely that the two places you want more performance from your notebook is games and internet battery life. All this preening about intel's crippled cpu being 50% faster dont mean jack because ... well its a crippled cpu. It cant play games yet it has a stupid igp. Why get all yuppity about such an obvious design failure, so much so that you'd be willing to sneeze at a $200 savings like it means nothing. It actually means something to people who work for a living. Most people just dont need the extra 50% cpu speed from a notebook. But having a game that runs actually does mean something tangible.
  • madseven7 - Tuesday, June 14, 2011 - link

    I'm not sure why people think this is such a crappy cpu. Am I missing something? Wasn't the Llano APU that was tested the lowest of the A8 series with DDR 1333? Doesn't it give up 500MHz-800MHz to the SB notebooks that were tested? Wouldn't the A8 3530mx perform much better? I for one would love to see a review of the A8 3530mx personally.
  • ET - Tuesday, June 14, 2011 - link

    Good comment. This is the highest end 35W CPU, but not the highest end Llano. So it gets commended for battery life but not performance. It will be interesting to see the A8-3530MX results for performance and battery life. It would still lose to Sandy Bridge quite soundly on many tests, I'm sure, but it's still a significant difference in clock speed over the A8-3500M..
  • Jasker - Tuesday, June 14, 2011 - link

    One thing that is really interesting that isn't brought up here is the amount of power used during gaming. Not only do you get much better gaming than Intel, but you also get much less power. Double whammy.

Log in

Don't have an account? Sign up now