Back to Article

  • aegisofrime - Monday, July 16, 2012 - link

    With the next generation of Nexus phone(s) around the corner, I'm looking forward to reading that article. Also, there are lots of smaller Chinese SoC designers coming up, would be interesting to look at them in greater detail. Particularly Mediatek (ok they are Taiwanese), which makes SoC that powers the majority of lower end Android handsets. Reply
  • lowlymarine - Tuesday, July 17, 2012 - link

    Are all the major semiconductor companies fighting to see who can make their product nomenclature the least meaningful? It was one thing when it was just AMD slapping pseudo-random "ratings" on their CPUs, but nowadays we've got Intel's i-somethingmeaningless, AMD's four different product lines and random numbers, and now the mobile space has abandoned all vestiges of common sense too:
    APQ 8050: Single-core 65nm Scorpion with Adreno 200
    APQ 8055: Single-core 45nm Scorpion with Adreno 205
    APQ 8060: Dual-core 45nm Scorpion with Adreno 220
    APQ 8030: Dual-core 28nm Krait with Adreno 305
    APQ 8060A: Dual-core 28nm Krait with Adreno 225 (is this better or worse than 8030? Who knows!)
    Now we have APQ 8064: Quad-core 28nm Krait with Adreno 320

    Don't even get me started with the ones with cellular modems. MSM 8260 is GSM APQ 8060, MSM 8660 is CDMA, what's MSM 8960 then? Why it's Krait. <i>Of course.</i>
  • frostyfiredude - Tuesday, July 17, 2012 - link

    It was working alright till Krait came along, now it's a pile of WTF. The GPU names from nVidia and AMD make sense atleast, from a pure performance/generation perspective anyway. Reply
  • Brian Klug - Tuesday, July 17, 2012 - link

    I honestly have no problem with any of QCT's product numbers, it's pretty simple when you get the hang of it.

    MSM = Mobile Station Modem
    MDM = Mobile Data Modem
    QSD = Qualcomm SnapDragon
    APQ = Application Processor Qualcomm
    MPQ = MultiProcessor Qualcomm(?)

    First digit is somewhat ambiguous, but 7 = value, 8 = mid to high end
    Second digit is for air interface, 2 = 3GPP, 6 = 3GPP + 3GPP2, 9 = 3GPP (WCDMA+LTE), 3GPP2
    Third and 4th digit is for the AP inside, higher is better (usually), eg 50 - single core, 55 single core, die shrink, 60 - dual core, 60A - dual core new architecture

    I have no problem following it, so long as you steer clear of the namespace collisions that are MSM8660A and MSM8260A (both dual core krait, new baseband).

    Anyhow that's my usual rant when I hear that the QCT parts are hard to follow...

    Now, let's not get started on Nvidia, T30, T30L, T33, wat?!

  • agag - Tuesday, July 17, 2012 - link

    I disagree on how easy the part numbers are to follow. I worked at Qualcomm for a year, and it probably took me six months to figure out the part numbers. There weren't really any internal references to clarify things either, either-- the best reference I found was the Wikipedia article on Snapdragon.

    QSD was only used for a short period of time-- everything is now MSM again.

    The 8xxx chips were, at least until last year, the only ones branded as "Snapdragon," which signified >1GHz clock speed. But of course one can clock the same part differently, and thus the 7x30 is exactly the same chip as the 8x55, except the 7x30 was clocked at 800MHz and the 8x55 is clocked higher.
  • bennyg - Thursday, July 19, 2012 - link

    You have any idea how much research has gone into the crossover between numbers, marketing, and psychology?

    Intel in particular know their buyers and numbers, you think they choose their processor numbers from a hat or by feeling? They know exactly why their products are numbered what they are... and how much to charge for each of them.

    Qualcomm's numbers may be random... not all of them do though. The technical term for what AMD started with the compete-with-P4-GHz ratings thing: quasi-quantitative.
  • CoreDuo - Tuesday, July 17, 2012 - link

    > The quad core, the 4410, is shipping internationally in the Galaxy S III, and is by all accounts a scorcher

    4412 not 4410, yes?
  • JasonInofuentes - Tuesday, July 17, 2012 - link

    Yep. Fixed. Thanks. Reply
  • jjj - Tuesday, July 17, 2012 - link

    About the competition the main thing is still the CPU and if they have quad Krait they might just have to compete with dual cores A15 and in late 2013 be the first to go 20nm.
    There is also the timing,this way they get deals for phones shown at CES and MWC that won't get EOLed before the end of 2013.
    About integration ,they should integrate (on die or in package) as much as they can and not only compute units ,smaller PCB and lower volume are something everybody is looking for.
    I am curious about very specialized cores (like in GreenDroid ) but i doubt we'll see that kind of thing soon.
    On the fabs issue, there was the rumour that they might invest in UMC and maybe they actually do it but i doubt they'll use Samsung.Most likely they'll go for both UMC and GloFo.
    I am more curious to see if Qualcomm (and others) will manage to have 20nm in late 2013 and if anyone that goes 20nm early also goes FinFET in (maybe) 2014- we know that UMC intends to have a FinFET version of it's 20nm process and it seems that TSMC might do the same ,
  • JasonInofuentes - Tuesday, July 17, 2012 - link

    Specializing the die and package to too fine a degree is a bit risky. It takes time and resources to alter the fab for an utterly bespoke chip, and so you need a customer willing to pay more and commit to however many chips your going to make. We've seen it done, most notably with Apple sourcing Samsung SoC's for the iPhone, but also with the repackaged CPU of the original MBA. But those were package redesigns, integrating additional phone components on die, or even on package could prove more difficult.
    The list of items is pretty slim as it is:
    -power management
    -baseband power amps
    -new radio components
    -new interface components

    I'm sure I'm missing some but all of those are risky to integrate. Memory and NAND lock the OEM into whatever quantity of each they ordered. So, if customers want more of your 16GB product, but you have tons of your 8GB product, then your stuck holding the bag. Power management seems a real possibility, as do sensors, but they're also value add components that often get left off of lower end devices, so you might only integrate them on your higher end chips. Power amps for international devices might be something they could consider, but in the US, with every network using a different set of frequencies, it wouldn't be feasible. New radio and interface components is a very real possibility; if a wireless display standard wins out that could be integrated, if an application for USB3 or TB on phones is found, that could be added.
    We'll see what gets added next, but probably not for a while.
  • twotwotwo - Tuesday, July 17, 2012 - link

    I'm surprised by benchmarks that favor the international (Exynos-based) Samsung SGS3's over the US (S4-based) ones. Some numbers pulled from Anandtech tests (international first, then US):

    SunSpider: 1424 vs. 1751 (Exynos wins)
    BrowserMark: 161710 vs. 114812 (Exynos wins)
    Vellamo: 2072 vs. 2290 (S4 wins--note this is Qualcomm's benchmark)
    GLBenchmark offscreen 720p: 103 fps vs. 54 (Exynos wins)

    The Exynos has a better GPU (Mali-something), and will win on any highly multithreaded benchmarks, but I'm confused at how it gets that better SunSpider score, since I thought SunSpider was CPU-only and single-threaded. Does the A9 design inherently beat Krait at SunSpider, and if so does that mean anything for day-to-day performance? Is SunSpider more multithreaded than it seems? Does the Exynos' turbo-boost-type dynamic clocking favor it in benchmarks (with battery life suffering)? Are the two flavors of SGS3 not actually fair comparison platforms (different software or clocks or something?)? You guys know if anyone does. :)

    For the record, here's an Engadget page about this and AnandTech sources for numbers:
  • JasonInofuentes - Tuesday, July 17, 2012 - link

    You'll get more of this in our State of the SoC discussion but I'll drop a preview here.

    Let's look at the Windows PC model real quick. You can go to the store, pick out your mobo, your CPU, your GPU and your memory and storage. Grab a wireless card and some HIDs, and a nice monitor and now you've got a lot of stuff that does nothing. So, you go grab your OS of choice and load it up, but let's say you don't load any device specific drivers. It'll work, it'll boot. But the display driver won't go over 1024x768 and is really sluggish. The WiFi doesn't work, at all. And your USB3 ports are running at USB2. Your CPU is working fine, except maybe it doesn't use the media acceleration components. So, you go find drivers.

    That's pretty much the same thing that happens in the SoC space. When an OEM orders chips from Qualcomm, or any of the chip makers, they get Android builds that have been optimized to leverage all the silicon components on that SoC. It's the showcase build, and it's what is found in Qualcomm's Mobile Development Platform. Those builds are for the OEM to look at, and to select parts of and implement in their own software. But, they don't have to, and often they don't want to because they've already put in tons of work building their own version of Android and it would take more time and resources to integrate the new code when it probably works well enough.

    In this case, Samsung's Android has always included it's own version of the Android browser that uses SOME GPU acceleration, and a few other silicon specific optimizations. When they use S4, they aren't likely to tear down and rebuild their software to leverage S4's strengths, knowing most likely that to the average user the difference will be invisible. And so, Sunspider on optimized software vs. unoptimized, we know who will win.

    Now, that said, the best results from Qualcomm's Android build still don't beat Exynos in Sunspider (1532 vs. 1424). There are other optimizations that can be done that do things like recognize opportunities for parallelism in a program and implement them, that's a possibility. It's also possible that some of the Sunspider tests do lend themselves to multiple cores (the crypto ones come to mind). Regardless, you have to look at the broader case to make your choices, not SoC alone.
    We love Krait's performance and power characteristics, but we hate it that they're alone. Competition is good. Even where physics poses limitations on how fast one can innovate, competition ensures that everyone's on their toes. I think it's a shame that the carriers were more interested in featuring their network speeds than offering the customer a chance to own a top notch quad-core phone. Hopefully that won't continue when Cortex-A15 designs start to make their way onto the market.
  • tipoo - Tuesday, July 17, 2012 - link

    Just wanted to say I've been wanting an up to date SoC article, looking forward to that.

    Also to the OP my impression was that Samsung does a lot of their own optimization for the browser/SoC combo which leads to higher scores than you would expect.
  • twotwotwo - Wednesday, July 18, 2012 - link

    Thanks--very helpful. And agree about competition--the folk wisdom seems to be nobody has but Qualcomm a next-gen CPU + LTE baseband with low enough wattage, which is frustrating when there are other great CPU/GPU designs out there. Interested to read the update. Reply
  • dagamer34 - Tuesday, July 24, 2012 - link

    We also know from Microsoft's 1200 SunSpider Score from it's Windows Phone 8 Dev Summit that there's still a bit more performance to be extracted from these SoCs. Heck, the iPhone 4S is competitive with most Android phones and it has a Cortex A9 CPU clocked at ~800Mhz. So it really is all about optimizations. Reply
  • ltcommanderdata - Tuesday, July 17, 2012 - link

    "Adreno 3xx is so far only being announced to run at 9_3, leaving it in the Geforce 200 space, and at feature parity with NVIDIA’s Kal-El Geforce GPU."

    With the Geforce 200 series being DX Level 10_0 parts, the Adreno 3xx would actually be comparable to the ATI X700/X800. I believe DX Level 9_3 is defined against SM2.0b, so feature-wise the Adreno 3xx should be below DX9.0c/SM3.0 GPUs like the ATI X1000 and nVidia 6000/7000 series.

    "If Samsung Semiconductor found itself with spare capacity, an eager customer (Qualcomm), and a handset manufacturer (Samsung Mobile) interested in using a 28nm product with limited availability, it could be reasoned that they’d partner with Qualcomm to deliver SoCs for the US Galaxy S IIIs"

    Recent Samsung fab coverage has been about their 32nm process. Are there any details on their 28nm process? With the 32nm process still ramping, was the 28nm process developed in parallel or is it's ramp a few months behind? How does Samsung's 28nm process compare to TSMC and UMCs?
  • rd_nest - Tuesday, July 17, 2012 - link

    Some marketing info here:
  • ltcommanderdata - Tuesday, July 17, 2012 - link

    Thanks for the links. I wonder how Samsung's 28nm process compares to their 32nm process since all their comparisons are relative to the 45nm process? Half nodes have historically been focused on cost-optimization so the 28nm process's major benefit is probably just making smaller dies rather than major power consumption improvements relative to the 32nm process. Reply
  • esteinbr - Tuesday, July 17, 2012 - link

    The DirectX level really doesn't have any correlation to performance of a part. It's actually tells you the functional capabilities. Generally, higher DirectX levels do correspond to new cards which are naturally faster but it doesn't have to be that way. A Bottom of the line budget directx 10 card isn't necessarily going to be faster than a top of the line directx 9.3 card from the previous generation. Reply
  • ltcommanderdata - Tuesday, July 17, 2012 - link

    I never made any association to performance at all. I'm merely saying that a feature level 9_3 GPU like the Adreno 3xx is not at feature parity with the GeForce 200 series rather it's feature set is in line with SM2.0b GPUs like the X700/X800. Reply
  • MadMan007 - Tuesday, July 17, 2012 - link

    Adreno 320 with a dual-core MSM S4 please. Reply
  • JasonInofuentes - Tuesday, July 17, 2012 - link

    That's the S4 Pro, or MSM8960A. It'll be around before year end, I expect. Reply
  • SydneyBlue120d - Tuesday, July 17, 2012 - link

    "The IP used for the A/V components in S4 Prime will be 3rd party, however it’s always possible that Qualcomm will put their capable DSP and silicon engineers to work on their own proprietary A/V blocks."

    Are you completely sure it is 3rd party IP? Do You remember that Qualcomm acquired HQV last Year?
  • JasonInofuentes - Tuesday, July 17, 2012 - link

    It's 3rd party, today. It won't be in the future. But today's A/V components are definitely 3rd party. Reply
  • Tanclearas - Tuesday, July 17, 2012 - link

    "Another wise gamble would be to integrate wireless display technology"

    Actually, S4 is supposed to feature that already.

    "Every Snapdragon S4 device will support WiFi Display, but the first ones to ship will not have it enabled out of the box. Android already supports the WiFi Direct software stack, but the WiFi Display still needs to be tested and finalized."
  • JasonInofuentes - Tuesday, July 17, 2012 - link

    Noted. WIll update. Thanks. Reply
  • hormel - Tuesday, July 17, 2012 - link

    I know it isn't intended for high end smart phones, but I wish they had an LTE modem in it. I would have made the most awesome cell phone in the world. Reply
  • dagamer34 - Tuesday, July 24, 2012 - link

    For the moment, these are meant for tablets. I suspect they traded baseband space for more cores. Reply
  • jwcalla - Tuesday, July 17, 2012 - link

    Hopefully this DirectX silliness stays away from the mobile space and hopefully it won't be used to draw comparisons between SoCs. Game developers are going to stick with OpenGL (I pray) since they want to target iOS and Android too.

    The choice is between an open-standard library and one that is proprietary and locked to a single platform. Seems pretty clear-cut to me.
  • phoenix_rizzen - Tuesday, July 17, 2012 - link

    It's needed for GPUs that will be used in Windows RT tablets. Although, I believe it's more about what features are available, than actually using DirectX to access the GPU. But I could be wrong about that.

    I would also like to see more information about the actual OpenGL version/features supported, instead of some random DirectX stuff.
  • Lucian Armasu - Wednesday, July 18, 2012 - link

    I hope so, too. I don't understand why the author even mentions it. even if they have "DirectX 11 support", that doesn't need it necessarily supports all the features of DirectX11 like the PC cards do, does it?

    What's far more relevant is OpenGL ES 3.0 support, which all new mobile GPU architectures will have, including Adreno 320, Mali T604, Tegra 4 and so on.
  • dagamer34 - Tuesday, July 24, 2012 - link

    DirectX cards v10 and up require capabilities to be present in order to be certified. This isn't like DirectX 9 where developers needed to check cap bits to see what was supported in a piece of hardware. Reply
  • Lucian Armasu - Wednesday, July 18, 2012 - link

    Mali T604 will also haen ve Directx11 support, and it's coming out this year, rather than the next like PowerVR 6200. Reply

Log in

Don't have an account? Sign up now