• What
    is this?
    You've landed on the AMD Portal on AnandTech. This section is sponsored by AMD. It features a collection of all of our independent AMD content, as well as Tweets & News from AMD directly. AMD will also be running a couple of huge giveaways here so check back for those.
    PRESENTED BY

The Llano A-Series APU

Although Llano is targeted solely at the mainstream, it is home to a number of firsts for AMD. This is AMD's first chip built on a 32nm SOI process at GlobalFoundries, it is AMD's first microprocessor to feature more than a billion transistors, and as you'll soon see it's the first platform with integrated graphics that's actually worth a damn.

AMD is building two distinct versions of Llano, although only one will be available at launch. There's the quad-core, or big Llano, with four 32nm CPU cores and a 400 core GPU. This chip weighs in at 1.45 billion transistors, nearly 50% more than Sandy Bridge. Around half of the chip is dedicated to the GPU however, so those are tightly packed transistors resulting in a die size that's only 5% larger than Sandy Bridge.

CPU Specification Comparison
CPU Manufacturing Process Cores Transistor Count Die Size
AMD Llano 4C 32nm 4 1.45B 228mm2
AMD Llano 2C 32nm 2 758M ?
AMD Thuban 6C 45nm 6 904M 346mm2
AMD Deneb 4C 45nm 4 758M 258mm2
Intel Gulftown 6C 32nm 6 1.17B 240mm2
Intel Nehalem/Bloomfield 4C 45nm 4 731M 263mm2
Intel Sandy Bridge 4C 32nm 4 995M 216mm2
Intel Lynnfield 4C 45nm 4 774M 296mm2
Intel Clarkdale 2C 32nm 2 384M 81mm2
Intel Sandy Bridge 2C (GT1) 32nm 2 504M 131mm2
Intel Sandy Bridge 2C (GT2) 32nm 2 624M 149mm2

Given the transistor count, big Llano has a deceptively small amount of cache for the CPU cores. There is no large catch-all L3 and definitely no shared SRAM between the CPU and GPU, just a 1MB private L2 cache per core. That's more L2 cache than either the 45nm quad-core Athlon II or Phenom II parts.


Intel's Sandy Bridge die is only ~20% GPU

The little Llano is a 758 million transistor dual-core version with only 240 GPU cores. Cache sizes are unchanged; little Llano is just a smaller version for lower price points. Initially both quad- and dual-core parts will be serviced by the same 1.45B transistor die. Defective chips will have unused cores fused off and will be sold as dual-core parts. This isn't anything unusual, AMD, Intel and NVIDIA all use die harvesting as part of their overall silicon strategy. The key here is that in the coming months AMD will eventually introduce a dedicated little Llano die to avoid wasting fully functional big Llano parts on the dual-core market. This distinction is important as it indicates that AMD isn't relying on die harvesting in the long run but rather has a targeted strategy for separate market segments.

Architecturally AMD has made some minor updates to each Llano core. AMD is promising more than a 6% increase in instructions executed per clock (IPC) for the Llano cores vs. their 45nm Athlon II/Phenom II predecessors. The increase in IPC is due to the larger L2 cache, larger reorder and load/store buffers, new divide hardware, and improved hardware prefetchers.

On average I measured around a 3% performance improvement at the same clock speed as AMD's 45nm parts. Peak performance improved up to 14% however most of the gains were down in the 3—5% range. This is arguably the biggest problem that faces Llano. AMD's Phenom architecture debuted in 2007 and was updated in 2009. Llanos cores have been sitting around for the past 3-4 years with only a mild update while Intel has been through two tocks in the same timeframe. A ~6% increase in IPC isn't anywhere near close enough to bridge the gap left by Nehalem and Sandy Bridge.

Note that this comparison is without AMD's Turbo Core enabled, but more on that later.

What Took So Long? The GPU
POST A COMMENT

177 Comments

View All Comments

  • phantom505 - Tuesday, June 14, 2011 - link

    I went with a K325 in a Toshiba with a Radeon IGP. Nobody I have lent it out to has every complained about it being slow or incapable of doing what they wanted/needed to. I get about 5 hours of battery life consistently. I don't do too much that is CPU intensive but I hear people moan and groan about the E-350 and Atom both when they try to open 50MB+ ppt files. I have no such problems.

    I for one an quite happy to see that AMD is still leading this segment since most users will be quite happy with AMD. I'm finding it more and more that Intel may own the top end, but nobody I know cares in the slightest.
    Reply
  • mino - Tuesday, June 14, 2011 - link

    E-350 is generally faster than K325 + IGP. Then than that, I fully agree. Reply
  • ash9 - Tuesday, June 14, 2011 - link

    In this price range, I think not, besides Open(X) applications will reveal the potential - its up to the application developers now Reply
  • GaMEChld - Tuesday, June 14, 2011 - link

    My netbook is a pain to use precisely because of its graphics. It cannot properly play youtube or movie files fluently. Aside from its multi-media problems, I don't try to do ridiculous things on a netbook, so the other components are not much of a factor for me. But if I can't even watch videos properly, then it's trash.

    Luckily, I got that netbook for free, so I'm not that sad about it. I'll probably sell it on eBay and get a Brazos netbook at some point.
    Reply
  • hvakrg - Tuesday, June 14, 2011 - link

    Yes, they're becoming primary machines, but what exactly do you need the CPU part for in a primary machine today? Let's face it most people use their computer to browse the web, listen to music and watch videos, all of which are either relying on the GPU today or is clearly moving in that direction.

    Intel will have an advantage in the hardcore CPU market probably forever due to them being years ahead of the competition in manufacturing processes, but what advantage does that give them when it comes to selling computers to the end user? Things like battery life and GPU performance is what will be weighted in the future.
    Reply
  • Broheim - Wednesday, June 15, 2011 - link

    personally I need it to compile thousands of lines of code sometimes several times a day, if I were to settle for a E-350 I'd die of old age long before I get my masters in computer science.... some of us actually gives our 2600k @ 4.5ghz a run for it's money.

    th G in GPU doesn't stand for General... the GPU can only do a few highly specialized tasks, it's never going to replace and will always rely on the CPU. Unless you're a gamer you benifit much more from a fast CPU than a fast GPU, and even as a gamer you still need a good CPU.

    don't believe me? take a E-350 and do all the things you listed, then strap a HD6990 onto it and try and see if you can tell the difference...
    trust me, you can't.
    Reply
  • ET - Wednesday, June 15, 2011 - link

    Compiling code is a minority application, although I did that at a pinch on a 1.2GHz Pentium M, so the E-350 would do as well. Certainly won't use it for my main development machine, I agree.

    Still, as hvakrg said, most users do web browsing, listen to music, watch video. The E-350 would work well enough for that.
    Reply
  • sinigami - Wednesday, June 15, 2011 - link

    >most users do web
    >browsing, listen to music,
    >watch video. The E-350
    >would work well enough
    >for that.

    The Atom also works well enough for that, for less money.

    You might be pleasantly surprised to find that current Atom netbooks can play 720p MKVs. For netbook level video, that's "well enough".

    As you said, for anything tougher than that, i wouldn't use it for my "main machine" either.
    Reply
  • ionave - Thursday, June 16, 2011 - link

    Why would you spend $2000 for an intel powered laptop when you can build a desktop to do computations for a quarter of the price at 20x the speed, and get a laptop for $400 to run code on the desktop remotely and use it for lighter tasks? I'm surprised that you are a masters student in computer science, because your lack of logic doesn't reflect it. Correct me if I'm wrong, but why would you compute on the go when you can let the code on a desktop or cluster while the laptop is safely powered down in your backpack?

    Also, I can run Super Mario Galaxy using dolphin (CPU intensive) emulator at full frame rate on my AMD Phenom II X2 BE, and the cores in the A8 are improved versions of Phenom II X4. You really need to get your facts straight, since the CPU is actually VERY good. Go look at the benchmarks and do your research
    Reply
  • Broheim - Thursday, June 16, 2011 - link

    he clearly said primary machine, so before you go around insulting me I'd suggest you learn how to read.
    the 2600K is a desktop CPU you douchebucket, I never said my main machine was a laptop, quite to the contrary.

    what you can and can't do is of no interrest to me, but first off, I never mentioned the A8 I said E-350, again with the failure to read.
    nevertheless...
    K10 is not even a match for Nehalem, and so far behind Sandy bridge it's ridiculous.
    I've seen the benchmarks, I've done my research and concluded that the A8 CPU is far from "VERY" good, have you done yours?
    Reply

Log in

Don't have an account? Sign up now