What Took So Long?

AMD announced the acquisition of ATI in 2006. By 2007 AMD had a plan for CPU/GPU integration and it looked like this. The red blocks in the diagram below were GPUs, the green blocks were CPUs. Stage 1 was supposed to be dumb integration of the two (putting a CPU and GPU on the same die). The original plan called for AMD to release the first Fusion APU to come out sometime in 2008—2009. Of course that didn't happen.

Brazos, AMD's very first Fusion platform, came out in Q4 of last year. At best AMD was two years behind schedule, at worst three. So what happened?

AMD and ATI both knew that designing CPUs and GPUs were incredibly different. CPUs, at least for AMD back then, were built on a five year architecture cadence. Designers used tons of custom logic and hand layout in order to optimize for clock speed. In a general purpose microprocessor instruction latency is everything, so optimizing to lower latency wherever possible was top priority.

GPUs on the other hand come from a very different world. Drastically new architectures ship every two years, with major introductions made yearly. Very little custom logic is employed in GPU design by comparison; the architectures are highly synthesizable. Clock speed is important but it's not the end all be all. GPUs get their performance from being massively parallel, and you can always hide latency with a wide enough machine (and a parallel workload to take advantage of it).

The manufacturing strategy is also very different. Remember that at the time of the ATI acquisition, only ATI was a fabless semiconductor—AMD still owned its own fabs. ATI was used to building chips at TSMC, while AMD was fabbing everything in Dresden at what would eventually become GlobalFoundries. While the folks at GlobalFoundries have done their best to make their libraries portable for existing TSMC customers, it's not as simple as showing up with a chip design and having it work on the first go.

As much sense as AMD made when it talked about the acquisition, the two companies that came together in 2006 couldn't have been more different. The past five years have really been spent trying to make the two work together both as organizations as well as architectures.

The result really holds a lot of potential and hope for the new, unified AMD. The CPU folks learn from the GPU folks and vice versa. Let's start with APU refresh cycles. AMD CPU architectures were updated once every four or five years (K7 1999, K8 2003, K10 2007) while ATI GPUs received substantial updates yearly. The GPU folks won this battle as all AMD APUs are now built on a yearly cadence.

Chip design is also now more GPU inspired. With a yearly design cadence there's a greater focus on building easily synthesizable chips. Time to design and manufacture goes down, but so do maximum clock speeds. Given how important clock speed can be to the x86 side of the business, AMD is going to be taking more of a hybrid approach where some elements of APU designs are built the old GPU way while others use custom logic and more CPU-like layout flows.

The past few years have been very difficult for AMD but we're at the beginning of what may be a brand new company. Without the burden of expensive fabs and with the combined knowledge of two great chip companies, the new AMD has a chance but it also has a very long road ahead. Brazos was the first hint of success along that road and today we have the second. Her name is Llano.

The Llano A-Series APU
Comments Locked

177 Comments

View All Comments

  • ionave - Thursday, June 16, 2011 - link

    I'm honestly sick of the fact I can't play TF2 on high settings on my laptop AND I cannot find an affordable computer to do so while I'm not paying attention during class. Several people I know feel the same way.
  • krumme - Tuesday, June 14, 2011 - link

    The GPU performance hits dues to the shares bus is very low. Getting NV 540 /ati 5650 performance is far better than most expected.
    Battery life is simply amazing. Far better than expected.

    The OEM is standing at a very long line for this.
  • GeorgeH - Tuesday, June 14, 2011 - link

    That battery life is incredibly impressive. That AMD will finally have a competitive mobile offering is huge news; their engineers definitely deserve a pat on the back. Let's just hope that OEMs don't mess things up by cutting costs and shipping Llano laptops with tiny batteries.

    Unfortunately AMD will almost certainly struggle to get the message across that their CPU performance deficit is pretty much irrelevant for the vast majority of mobile usage models. It'll be especially difficult to get across to the huge number of consumers that think a 2GB 6570 is better than a 768MB GTX 460, but I wish AMD's marketing department the best of luck.
  • Dribble - Tuesday, June 14, 2011 - link

    They'll struggle because cpu performance deficit does matter, cpu performance matters more then gpu performance for most of us. While llano might be *enough* today everyone buys a notebook and expects it too last several years.

    If llano currently only has the performance of a notebook several years old (core 2 intel) then you can bet in 3 years it'll be dog slow.

    Really its only a winner for a pretty small margin of people. If you don't really care about gaming you go intel because cpu's are faster, if you really care about gaming you go intel + discrete. That leaves those who really care about gaming but are on an extremely tight budget.
  • ET - Tuesday, June 14, 2011 - link

    I think that you underestimate the effect of price. If you really care about gaming you go desktop, anyway. If you want a reasonable size laptop with good battery life and capable of some gaming, Llano will fit the bill, and if it sells considerably lower than the competition, then I'm sure a lot of people will buy it. It won't be anyones main gaming rig, but it will surely serve many as a secondary one.

    I agree that Llano is disappointing at the CPU level, but it really should be enough for most people. How well it sells will depend on pricing. There are big E-350 laptops being sold, which boggles the mind, and there wouldn't be if all people really cared or had any clue about performance.
  • ppeterka - Tuesday, June 14, 2011 - link

    I strongly disagree with you. My first notebook was exceptionally crappy in terms of raw CPU power. Desktop P4 Celeron 2.6GHz was used to power it. Yet I could use it for more than 4 years, after which I changed the CPU to a 2.8GHz P4, only to discover that the "user experience" was left unchanged except of the rare cases when I used the computer to work on it. Compile times were not left unchanged...

    But even with the Celeron in, the casual usage was just fine. Why? Because of the quite nice VIA IGP in it. I could actually play GTA San Andreas on the poor thing - even though there were times it was not very much fun, but it did work. Swapping the CPU didn't make it much better, only considering work duties.

    Today "everything" is about multimedia. By "everything" I mean 80% of what the people are doing. Youtube, Facebook, who-knows-what, all. None of my friends ever regretted heeding to my advice to choose a notebook with a reasonable graphics solution even when there would be an altenative type with a stronger CPU. (of course not to the extremities). Granted, they were not primarily interested in scientific calculations, or heavy duty software development.
  • Dribble - Tuesday, June 14, 2011 - link

    Multimedia doesn't need llano's gpu - SB graphics accelerates video just fine. Hence why you are recommending something that has better 3D graphics performance they'll never use, over something with a faster cpu which they will use all the time?
  • GeorgeH - Tuesday, June 14, 2011 - link

    You claim that CPU performance matters. That's true, but can you answer the following -

    1) Consider two laptops side by side. One has a ~2.5GHz C2D, one has a quad-core Sandy Bridge. Name a single task more than 5% of mobile users run that would allow you to definitively tell which laptop is running the C2D and which has the SB. (Task Manager doesn't count, I'm talking actually using an application.)

    2) Name a single task or application that theoretically might let you do the above once it's widespread in the next 3-5 years.

    3) What percentage of laptops are sold for <$1000 with roughly Llano or below levels of graphics?

    4) What percentage of laptop buyers care about battery life?

    My answers are -
    1) No clue
    2) No clue
    3) Most of them
    4) Most of them

    That's why I say that Llano's battery life is huge and its CPU performance really doesn't matter. Even Intel agrees, which is one reason why you're seeing them move towards lower-power CPUs. Ivy Bridge will have "configurable" TDP, and Haswell will move from 35-35W to 10-20W:
    http://www.anandtech.com/show/4378/ivy-bridge-a-ti...
  • RussianSensation - Tuesday, June 14, 2011 - link

    3) The fact is you can get a laptop with better GPU performance and faster CPU performance for $700-750 on the Intel side:

    i5 480 + HD5730 for $700:
    http://www.newegg.com/Product/Product.aspx?Item=N8...

    i5 480 + GT 540M (which beat 6620 in almost every gaming benchmark in this review) for $700:
    http://www.newegg.com/Product/Product.aspx?Item=N8...

    i5 480 + HD6550M for $700:
    http://www.newegg.com/Product/Product.aspx?Item=N8...

    i5 2410 + GT 540M for $750:
    http://www.newegg.com/Product/Product.aspx?Item=N8...

    Every single one of these provides faster CPU & GPU performance (http://www.notebookcheck.net/Mobile-Graphics-Cards...

    So Llano A-8 would need to be less than $700.
  • GeorgeH - Tuesday, June 14, 2011 - link

    Can you find faster GPUs for <$1000? Sure, but that wasn't the question. Go to Dell or HP's website and look at the number of laptops priced under $1000, then look at the percentage of those that come with significantly better than Llano-level graphics.

    There's much more to determining the value of a laptop than raw CPU and GPU performance; you could easily pay more than $700 for a Llano laptop and still be getting a very good deal.

    I'm not saying whether or not Llano should target this or that price point, though - I'm just trying to give a little perspective.

Log in

Don't have an account? Sign up now