Introducing AMD's Mobile Kaveri APUs

A couple weeks back, AMD flew us out to San Francisco for a briefing on their upcoming Mobile Kaveri APUs. Along with the briefing, we were given some time to run benchmarks on a prototype Kaveri laptop, though I'll note up front that the laptop isn't intended for retail and is merely a demonstration of performance potential. A funny thing happened about a week after the briefing, which some of you likely saw: AMD's web team accidentally posted all of the specs for the upcoming mobile Kaveri APUs ahead of schedule (for about half a day). We removed our coverage of the Mobile Kaveri APUs when AMD corrected the error, but we might as well jump right into things with the overview of the new mobile APUs.

Kaveri is AMD’s latest generation high-performance APU, and appeared first released on the desktop back in January of this year. We were a bit surprised – perhaps even perplexed – about the desktop first launch, considering AMD's "we're not going after the highest performance CPU market" stance. Then again, AMD-equipped laptops haven't been as strong as Intel-equipped laptops – not that the APUs aren't fast enough, but getting OEM partners to make a compelling AMD laptop seems rather difficult. As the saying goes, "You can lead a horse to water but you can't make him drink." AMD has provided a compelling APU and platform solution for a couple years, but the perception is that AMD platforms are budget platforms, so basically almost every corner gets cut. I'll have more to say on that later, but it's still a major concern in my book. Regardless, since the desktop Kaveri launch we have been eagerly awaiting the release of the mobile incarnation.

The launch has been scheduled for H1 2014 for some time now, and with AMD able to offer significant GPU performance with their APUs coupled with the space benefits of an integrated GPU versus a discrete GPU, it should be an easy sell. Mobile of course is not without its challenges. Power use is paramount, and while AMD has always been able to meet the desired TDPs, there is often the matter of performance tradeoffs required to hit those TDPs. Mobile is also a highly contested market right now; Intel of course has their Bay Trail and Haswell parts, but we're now seeing tablets and ARM-based Chromebooks pushing into AMD territory.

Despite the somewhat questionable decision to launch first on desktop – particularly odd given both Llano and Trinity launched more or less simultaneously on laptops and desktops – it's now time to pull the wrappings off Kaveri for the second time and see what AMD has created. We're now almost exactly a year after the launch of mobile Richland, which was really just a minor tweak of Trinity that launched about two years back. This is the first major architectural upgrade for AMD laptop APUs in two years, and expectations and hopes are high.

Kaveri brings a number of improvements, including the higher performance Steamroller based CPU cores and modern GCN based GPUs. We've previously covered this material, so rather than rehash things on the mobile side I'll simply refer back to the desktop Kaveri launch information. (You can also view the full presentation deck in the above gallery if you're interested.) AMD's Kaveri will be going up against Intel’s existing Haswell products, and this is AMD’s best chance to claw back market share from the Haswell family. Of course AMD has other APUs as well – specifically, Beema/Mullins will target the ultra-low power and tablet markets – but those compete in an even lower price bracket and go up against Intel's Bay Trail offerings. For now, let's start with an overview of the new Mobile Kaveri APUs.

AMD Mobile Kaveri SKUs
Comments Locked


View All Comments

  • Flunk - Wednesday, June 4, 2014 - link

    Under clocking the CPU and overclocking the GPU. that would be helpful. I've actually done this in a laptop that shares coolers between a discrete GPU and CPU but I imagine it would be useful in an APU laptop too.

    E.G. Note that the CPU is not underclocked in this test but I do normally underclock it to reduce the volume of the fan.
  • Meaker10 - Friday, June 6, 2014 - link

    The GS60 with M290x, with an a10-5750 it's a questionably balanced system, with an ad 5550m at 3.6-3.7ghz it offers a great deal of value.
  • Meaker10 - Friday, June 6, 2014 - link

    Damn auto correct, gx60 not gs60.
  • vladx - Wednesday, June 4, 2014 - link

    There's a mistake on the 3rd page, it should be i5-4200U not 5200U afaik.
  • texasti89 - Wednesday, June 4, 2014 - link

    I looked straight for the single-threaded performance and I see the 15w 4500u gets >50% higher score than the 35W 7600P. Yes, graphics is good at that high TDP, but without a competitive CPU performance I think it's hard to justify these SKUs for the target market. AMD really needs to stop this disastrous adoption of bulldozer-based CPUs for good.
  • TrackSmart - Wednesday, June 4, 2014 - link

    Three thoughts:
    1) I'm not defending AMD's single core performance, but the single-threaded cinebench test shows a 33% lead for the Intel Core-i5, which is not "greater than 50%". That said, I agree that AMD needs to close the gap on single-threaded CPU performance (and CPU performance-per-watt). This is as close as they've been in a long time, but the gap is still large. Their grand strategy has supposedly been to leverage the interaction of CPU+GPU to provide better performance, but when you are the minority player in the chip market, that's a tough hill to climb. How can you get software makers to write code for your APUS when they are only a fraction of the market *and* mostly found in the lowest-end consumer laptops?

    2) Sure, multi-threaded CPU performance looks competitive here since AMD has thrown in more "cores" (purposeful use of quotation marks) for the same price as Intel, but that strategy can only go so far. At any time, Intel can choose to lower the price on its chips to match AMDs performance-per-dollar because Intel's chips use less silicon to produce the same CPU performance.

    3) Anand is right that AMD needs to get these chips into nice laptops -- with lower-than-Intel prices -- and emphasize the gaming performance advantage. And those laptops had better have good battery life under normal usage. The presumed niche would be for an AMD laptop with reasonable gaming chops at several hundred dollars less than an Intel laptop with a discrete GPU.

    That said, 35 watts is too high for the ultrabook form factor. Will AMDs graphics advantage remain this large when you move down to a 15 Watt APU? If the answer is no, then Anand's ideal doesn't really work. All you would get is a $50 cheaper AMD laptop with slower CPU performance and similar GPU performance!

    [Note: I'm really rooting for AMD, but I'm going to remain cautious in my enthusiasm for these new chips until I see them in actual laptops. As they say, the proof is in the pudding.]
  • Natfly - Wednesday, June 4, 2014 - link

    > I'm not defending AMD's single core performance, but the single-threaded cinebench test shows a 33% lead for the Intel Core-i5, which is not "greater than 50%".

    1.33 / .87 = 1.53. 53% faster.
  • TrackSmart - Thursday, June 5, 2014 - link

    Yes, but the core i5 I specifically refer to is only a 33% difference. I'm guessing you were looking at the i7. So we are both wrong and both right. And in agreement about the need for better single threaded performance.
  • piroroadkill - Wednesday, June 4, 2014 - link

    Nice chip. But that said, without battery life results, this review does fall flat, I understand that they couldn't be done, though.

    Other than that, you've touched on the main issue with AMD based laptops: nobody wants to make a good one.

    Give me something like my old Sony Vaio Z12 with that FX-7600P in it, at a decent price, and you have a compelling product. I don't want ridiculous resolutions. I want one that will work well for games and desktop use at a nice size. The Z12 @ 13.1" 1600×900 offers that absolutely perfectly in my opinion.
  • Homeles - Wednesday, June 4, 2014 - link

    "From what I could gather, AMD used "V" transistors in Trinity/Richland but has switched to "T" transistors for Kaveri, which explains the drop in maximum clock speed."

    Perhaps, but the most important reason was the regression from PD-SOI to bulk.

    Interesting claim there about the transistor "shapes." I've not heard of T and V shaped transistors... it appears to be the shape of the gate.

Log in

Don't have an account? Sign up now