Qualcomm has had an incredible year. It wasn’t too long ago that I was complaining about Qualcomm’s release cadence, the lull between Scorpion and Krait allowed competitors like NVIDIA, Samsung and TI to get a foothold in the market. Since the arrival of Krait, the move to 28nm and the launch of monolithic AP/LTE solutions, no competitor has been able to come close to touching Qualcomm. These days the choice of integrating mobile silicon really boils down to what Snapdragon variant an OEM wants to go with. TI is out of the business, NVIDIA hasn’t seen much traction with Tegra 4 and even Samsung will ship Qualcomm silicon in many of its important markets. 
Qualcomm’s Snapdragon 600 was the SoC of choice at the beginning of the year, with Snapdragon 800 taking over that title more recently. Earlier this week, Qualcomm announced the successor to the 800: the Snapdragon 805. 
We’re expecting to see devices based on the Snapdragon 805 to be shipping in the first half of 2014, so Snapdragon 800 will still enjoy some time at the top of the charts.
The 805 starts by integrating four Krait 450 cores. Krait 450 appears to be an evolutionary upgrade over Krait 400, with no changes to machine width, cache sizes or pipeline depth. Qualcomm claims to have improved power and thermal efficiency, as well as increased maximum frequency from 2.3GHz to 2.5GHz. I suspect the design is quite similar to Krait 400, perhaps with some bug fixes and other minor tweaks. Qualcomm is likely leveraging yield and 28nm HPM process tech improvements to get the extra 200MHz over Krait 400. Krait 450 also adds 36-bit LPAE (Large Physical Address Extensions) to enable memory support above 4GB. This is a similar path to what we saw desktop PCs take years ago, although I'd expect the transition to 64-bit ARMv8 to happen for Qualcomm next year.
The GPU sees the bigger upgrade this round. The Snapdragon 805 features Qualcomm’s Adreno 420, designed 100% in house at Qualcomm. Adreno 420 brings about a D3D11-class feature set to Qualcomm’s mobile graphics, adding support for hull, domain and geometry shaders. Adreno 420 also includes dedicated tessellation hardware. Full profile OpenCL 1.2 is now supported. Texture performance improves by over 2x per pipe, and also gains ASTC support.
Adreno 420 is more efficient at moving data around internally. The GPU has a new dedicated connection to the memory controller, whereas in previous designs the GPU shared a bus with the video decoder and ISP. 
Qualcomm insists on occluding things like shader unit counts, so all we have to report today are a 40% increase in shader bound benchmarks (implying a 40% increase in shader hardware and/or more efficient hardware). 
Snapdragon 805 also features hardware accelerated decode of H.265 content. Hardware encode is still limited to H.264, but this is an awesome first for Qualcomm.
The Snapdragon 805 brings a much improved ISP. Qualcomm claims more than a 50% increase in ISP throughput (1GPixel/s class) compared to 640MP/s for Snapdragon 800. The 805 leverages its Hexagon DSP to deliver this level of performance. Qualcomm lists no change in DSP architecture between the 805 and 800.
Lastly, we see Qualcomm move to a 128-bit wide LPDDR3 memory interface for Snapdragon 805.  With support for LPDDR3-1600, the Snapdragon 805 features up to 25.6GB/s of peak memory bandwidth. It’s interesting to see Qualcomm go this wide just as Apple moved back down to a 64-bit wide interface. Qualcomm and Intel will be the only two shipping such a wide memory interface in the ultra mobile space come next year (although I do expect Apple to return to a wider memory bus at some point).
All of this makes for one beefy SoC, and a continuation of Qualcomm’s leadership in this space. I doubt we’ll see any slowing of Qualcomm’s roadmap after the 805 though. TSMC expects to be shipping 20nm wafers by the end of next year, and I wouldn’t be surprised to find a 20nm successor to the 805 in late ’14/early ’15. Remember that on the last process node shift we got Krait, I wonder what we’ll get this time.
Comments Locked


View All Comments

  • ArthurG - Friday, November 22, 2013 - link

    if you don't see how well Nvidia improved their SoCs, generation after generation, then you are blind ! T4 is a major speed bump with great performance, topping many CPU and GPU benchmarks.
    T5 Logan with mobile Kepler on HPM process will be another giant bump, thus its not so hard to believe that it will easily lead the pack in the performance field...
  • guidryp - Friday, November 22, 2013 - link

    Of course they improved.

    But you are really blind if you didn't notice the competitors improve as well, usually leaving the hyped NVidia chips out of the picture.
  • ArthurG - Friday, November 22, 2013 - link

    I'm not blind at all.
    T2: a flop, not even needed to talked about it.
    T3: was outperformed on day1. It really lagged behind but got some robust design wins.
    T4: even with the late launch, is on part with the fastest competitive SoC, Qualcomm S800. Note that its even more impressive that T4 uses lower HPL process, giving 20~30% advantage on S800
    T5: A15r4 at 2.3GHz on same HPM process than S805. And desktop class Kepler GPU (not the crippled mobile version of Adreno 420).
    Conclusion, its very clear that each generation Nvidia improves much faster than the competition. It's not hype, these are facts.
  • guidryp - Friday, November 22, 2013 - link

    Tegra 4 on par?

  • ArthurG - Friday, November 22, 2013 - link

    how easy... me too I can also handpick a bench:
  • guidryp - Friday, November 22, 2013 - link

    Yours is an isolated subsystem. Mine is full GPU game emulation.
  • Suneater - Friday, November 22, 2013 - link

    And now try to find results from 3dMark mobile benchmark and see how much Tegra 4 better than Snapdragon 800. There are a lot of benchmarks. It's stupid to decide based on the results from only one of them!
  • guidryp - Friday, November 22, 2013 - link

    Just make sure you are looking at the offscreen tests, and not the onscreen test with a low res Tegra 4 device.
  • ArthurG - Friday, November 22, 2013 - link

    Bullsh*t !!! Offscreen and onscreen are both important, that's why Anand shows both.
    Offscreen provides normalized scores, very useful to compare GPUs running on same resolution.
    But Onscreen provides scores at the device resolution, the one people must look at to see how the device will perform in real world.
    Thanks to Onscreen scores, we can clearly see that SoCs are not yet powerful enough to drive these insane resolutions at descent frame rate. Much better to have a lower resolution but smooth gameplay than a choppy retina one. Thats why I enjoy so much my Tegra Note 7, its screaming fast with all the games, even the heaviest ones. And it will still be fast next year with the new demanding games...
  • infra_red_dude - Friday, November 22, 2013 - link

    You'd settle for 1280x800 instead of 1920x1080 just because the GPU cannot handle it? I'm not sure majority of the crowd would agree with you. But then everyone is entitled to have their own opinion :)

Log in

Don't have an account? Sign up now