A8’s GPU: Imagination Technologies’ PowerVR GX6450

Last but not least on our tour of the A8 SoC is Apple’s GPU of choice, Imagination’s PowerVR GX6450.

When Apple first announced the A8 SoC as part of their iPhone keynote, they told us to expect a nearly 50% increase in graphics performance. Based on that information and on the fact that that Apple was moving to a denser 20nm process, we initially believed that Apple would be upgrading from A7’s 4-core PowerVR design to a 6-core design, especially in light of the higher resolution displays present on the iPhone 6 and iPhone 6 Plus.

Instead our analysis with Chipworks found that only four GPU cores were present on A8, which ruled out the idea of a 6-core design but did narrow down the options considerably. Based on that information and more importantly Apple’s Metal Programming Guide, we have been able to narrow down our options to a single GPU, the PowerVR GX6450.

The GX6450 is the immediate successor to the G6430 first used in the A7 and is based on Imagination’s PowerVR Series6XT architecture. Imagination first announced PowerVR Series6XT to the public at CES 2014, and now just a short eight months later we are seeing the first Series6XT hardware reach retail.

We have already covered the PowerVR Series6/Series6XT architecture in some detail earlier this year so we won’t go through all of it again, but we would encourage anyone who is interested to take a look at our architectural analysis for additional information. Otherwise we will be spending the bulk of our time looking at how GX6450 differs from G6430 and why Apple would choose this specific GPU.

From a technical perspective Series6XT is a direct evolution over the previous Series6, and GX6450 is a direct evolution over G6430 as well. Given a 4-core configuration there are only a limited number of scenarios where GX6450 outright has more hardware than G6430 (e.g. additional ALUs), and instead Series6XT is focused on adding features and improving performance over Series6 through various tweaks and optimizations to the architecture. Series6 at this point is actually over two years old – it was first introduced to the public at CES 2012 – so a lot has happened in the mobile GPU landscape over the past couple of years.

The closest thing to a marquee feature on Series6XT is support for Adaptive Scalable Texture Compression (ASTC), a next-generation texture compression technology that is slowly making its way into GPUs from a number of manufacturers. Designed by the consortium responsible for OpenGL ES, Khronos, ASTC is designed to offer better texture compression (with finer grained quality options) than existing texture compression formats while also being a universal format supported by all GPUs. In Apple’s case they have always been using PowerVR GPUs – and hence all products support PVRTC and more recently PVRTC2 – however ASTC being exposed allows them to take advantage of the quality improvements while also making game development and porting from other platforms easier.

Less visible to users but certainly important to Apple, Series6XT also includes new power management capabilities to reduce power consumption under idle and light workloads. Through finer grained power gating technology that Imagination dubs “PowerGearing G6XT”, GX6450 can now have its shading clusters (USCs) powered down individually, allowing only as many of them as are necessary to be fired up. As Apple continues to min-max their designs, being able to idle at a lower power state can be used to improve battery life and/or increase how often and how long the A8’s GPU uses higher power states, improving overall efficiency.

Apple iPhone GPU Performance Estimate: Over The Years

And, perhaps most importantly overall, Series6XT comprises a series of under-the-hood optimizations to improve overall performance. When it comes to the internals of PowerVR architectures we only have limited details from Imagination on how they operate, so in some areas we know quite a bit about what Imagination has been up to and in other areas their architectures are still something akin to a black box. At any rate Imagination’s goal for Series6XT was to improve performance by up to 50% – this seems to be where Apple’s 50% performance improvement claim comes from – though as we’ll see the performance gains on real world applications are not going to be quite as potent.

What we do know about Series6XT is that Imagination has made some changes to the structure of the USCs themselves. Series6XT still uses a 16-wide SIMD design, but in each pipeline they have added another set of medium/half-precision (FP16) ALUs specifically to improve FP16 performance. Now instead of 2x3 (6) FP16 ALUs, Series6XT bumps that up to 4x2 (8) FP16 ALUs. This is the only outright increase in shader hardware when you compare Series6 to Series6XT, and on paper it improves FP16 performance by 33% at equivalent clock speeds.

The focus on FP16 is interesting, though for iOS it may be misplaced. These half-precision floating point operations are an excellent way to conserve bandwidth and power by not firing up more expensive FP32 ALUs, but the tradeoff is that the numbers they work with aren’t nearly as precise, hence their use has to be carefully planned. In practice what you will find is that while FP16 operations do see some use, they are by no means the predominant type of floating point GPU operation used, so the FP16 increase is a 33% increase only in the cases where performance is being constrained by the GPU’s FP16 performance.

FP32 performance meanwhile remains unchanged. Each USC pipeline contains two such ALUs, for up to four FP32 FLOPS per clock, or to use our typical metric, 128 MADs (Multiply-Adds) per clock.

The rest of Series6XT’s optimizations take place at the front and back ends, where geometry processing and pixel fill take place respectively. Imagination has not told us exactly what they have done here, but both these areas have been targeted to improve sustained polygon rates and pixel fillrate performance. These more generic optimizations stand to be more applicable to general performance, though by how much we cannot say.

One final optimization we want to point out for Series6XT is that Imagination has made some additional under-the-hood changes to improve GPU compute performance. We have not talked about GPU compute on iOS devices thus far, as until now Apple has not exposed any APIs suitable for it (e.g. OpenCL is not available on iOS). With iOS8 Apple is releasing their Metal API, which is robust enough to be used for both graphics and now compute. How developers put this capability to use remains to be seen, but GX6450 should perform even better than G6430.

Mobile SoC GPU Comparison
  PowerVR SGX 543MP2 PowerVR SGX 543MP3 PowerVR SGX 543MP4 PowerVR SGX 554MP4 PowerVR G6430 PowerVR GX6450
Used In iPad 2/iPhone 4S iPhone 5 iPad 3 iPad 4 iPad Air/iPhone 5s iPhone 6/iPhone 6Plus
# of SIMDs 8 12 16 32 4 4
MADs per SIMD 4 4 4 4 32 32
Total MADs 32 48 64 128 128 128
Pixels/Clock N/A N/A N/A N/A 8 8
Texels/Clock N/A N/A N/A N/A 8 8

The one wildcard when talking about performance here is going to be clock speeds. Apple doesn’t expose these and they aren’t easy to test for (yet), though in the long term Metal offers some interesting possibilities for nailing that down, or at least getting a better idea of relative clock speeds.

In any case, we’ll take a look at our GPU benchmarks in depth in a bit, but overall GPU performance compared to A7 and its G6430 is consistently better, but the exact performance gain will depend on the test at hand. Some tests will come very close to reaching 50% while others will be just 15-20%. The dependent factor generally seems to be whether the test is ALU-bound or not; because the USC has not changed significantly from G6430 to GX6450 outside of those additional FP16 ALUs, tests that hit the FP32 ALUs in particular show less of an improvement. Otherwise more balanced tests (or at least tests more defined by pixel fillrate performance) can show greater gains. In general we should be looking at a 30-35% performance improvement.

Why Four Cores?

One thing that admittedly surprised us in the revelation that A8 was using a 4-core PowerVR design was that we figured a 6-core design would be a shoe-in for A8, especially since Apple was on the receiving end of the density improvements from TSMC’s 20nm process. But upon further reflection an additional two cores is likely more than Apple needed nor wanted.

The biggest factor here is that coming from G6430 in the A7, performance has seen a solid improvement despite sticking to only four GPU cores. Due to the combination of performance improvements from the Series6XT architecture and any clock speed increases from Apple, A8 gets quite a bit more GPU performance to play with. The increased resolution of the iPhone 6 screen in turn requires more performance if Apple wants to keep native resolution performance from significantly regressing, which GX6450 is capable of delivering on. Never mind the fact that G6430 also drove the iPad Air and its much larger 2048x1536 pixel display.

PowerVR Series6/6XT "Rogue"
GPU # of Clusters # of FP32 Ops per Cluster Total FP32 Ops Optimization
G6200 2 64 128 Area
G6230 2 64 128 Performance
GX6240 2 64 128 Area
GX6250 2 64 128 Performance
G6400 4 64 256 Area
G6430 4 64 256 Performance
GX6450 4 64 256 Performance
G6630 6 64 384 Performance
GX6650 6 64 384 Performance

These performance improvements in Series6XT have a cost as well, and that cost is suitably reflected in the estimated die sizes for each GPU. The G6430 was 22.1mm2 on the 28nm A7, while the GX6450 is 19.1mm2 on A8. Though GX6450 is smaller overall, it’s nowhere near the roughly 11.1mm2 a pure and perfect die shrink of G6430 would occupy. Limited area scaling aside, GX6450’s additional functionality and additional performance requires more transistors, and at the end of the day Apple doesn’t see a significantly smaller GPU because of this. In other words, the upgrade from G6430 to GX6450 has delivered much of the performance (and consumed much of the die space) we initially expected to be allocated to a 6-core GPU.

Overall the choice of GX6450 seems to be one of picking the GPU best for a phone, which is an area the G6430 proved effective with A7. As a step below Imagination’s 6-core PowerVR designs, GX6450 delivers a better balance between performance and power than a larger GPU would, which in turn is clearly a benefit to Apple. On the other hand this means A8 is not going to have the GPU performance to compete with the fastest SoCs specifically designed for tablets, though what this could mean for the obligatory iPad update remains to be seen.

A8’s CPU: What Comes After Cyclone? CPU Performance
Comments Locked


View All Comments

  • Toss3 - Thursday, October 9, 2014 - link

    The browser benchmarks would make more sense if they used the stock browser on all the devices, not just on the iPhone to make it look good. The Note 4 for instance is scoring around 350ms with its own browser, while on Chrome it is only seeing 800ms. The results should also be in a separate "Web-browsing performance" section instead of the CPU performance one.
  • thackr - Thursday, October 9, 2014 - link

    Does anyone else see the green dot lens flare shown here on their iPhone 6? http://www.alternapop.com/2014/10/02/iphone-6-lens...
  • The0ne - Friday, October 10, 2014 - link

    "At this point, it’s not really possible to revolutionize the smartphone..."

    Stopped when I got here. I don't usually cuss but you have got to be shtting me for making such a statement. In your effort to try to write a unbiased review you are already stating that for whatever the reasons the phone may lack it is because nothing can be improve so it's a great phone. I officially hate all your Apple reviews now. This is sickening for any professional engineer to digest.
  • JC86 - Friday, October 10, 2014 - link

    @TheOne: Engineers are constantly tweaking and refining the software and hardware for a better UX and that refinement is great but the bottom line is the modern smartphone as we know it have not had any revolutionary advancements in years. It's a mature product category, plain and simple.
  • tralalalalalala40 - Friday, October 10, 2014 - link

    So you're one of those that thinks cars are changing massively every year. "THE BRAND NEW REVOLUTION IS HERE FOR A LIMITED TIME"
  • sgmuser - Sunday, October 12, 2014 - link

    "and how Apple’s SoC development is now synchronized with the very edge of semiconductor fabrication technology." You are not kidding right! :-) Comparing Intel's 14nm chips, I still believe Mobile phone SoCs are not coping up with the latest tech. m2c. Samsung (with Exynos) atleast jumped a bit...comparing QC SD or Apple Ax series.
  • Pandian - Sunday, October 12, 2014 - link

    Actually, Intel is not in making chips, 14nm or 20nm, for cell phones at large! Such a big company with capacity to supply designer boards to any manufacturer in the handheld 3inch or 12 inch device - and still staying away!
  • Pandian - Sunday, October 12, 2014 - link

    Compare these - Apple, etc. and All Pharma! 2-5% on actual R&D by pharmaceutical companies, (esp., the ones pricing cancer and Hepatitis C drugs) and about 95 % on marketing (read bribing the Medical industry - that includes "respectable life-saving Doctors") - vs 20-50% profit by tech companies (Apple, Samsung, Lenovo, HP, etc.) on products made from R&D from this decade! Without the slave labor of China and such countries, even that profit is not possible! Today's pyramids and Taj Mahals!

    Drugs: Most of these drugs were "discovered" decades ago in govt. research facilities - somehow, they are private intellectual properties today! Even anti-helminths (drugs for cattle parasites) costing ~$1-10 for 1000 pills, suddenly cost up to thousands of dollars each pill, because their anti-cancer capacities were "discovered" as side-effects! Even aspirin, made in third world countries and sold here, costs about ten times from a decade or so ago, due to price fixing!

    Your life or $200,000 - pay-up or die, if you have cancer or Hepatitis C.

    The target is larger with cellphones and computers - hence the bigger market value of the companies!

    Even within the tech industry, the profit of $200-300 for each device is paid once every three years or so - the cost of gasoline for a car is more than that in 2-3 months! The actual leaches that cost the consumer are the cell and cable/satellite companies - thousands of dollars a family in a two year contract! USA still charges the highest fee for cell plans, voice, text and data - taking a bite at each end of the link, i.e., the caller and the recipient!

    And, we whine more about the cost of these hand-held toys - that is the purpose and use of most of these "smart" devices! Truly important communication via voice, or the equivalent of the Morse code or ham-radio, is so small - not worth taking care of while driving a 4000+lb missile at 55 to 80 mph!

    Both Apple and Samsung will take a dive in the next 12 months

    A millionaire on CNBC talked about not being eligible for a phone upgrade for another year - and therefore not having hands-on experience with the recently released phones, Apple, HTC, etc.! That is how you stay rich!

    The post seems irrelevant! No! The basic premise of most of the posts here are about MONEY!
  • xmen77 - Monday, October 13, 2014 - link

    There can not be "ideal 6500k" if the other LCD in this all bad
    this is "ideal 6500k"?
  • thrasher32 - Tuesday, October 14, 2014 - link

    Yeah I'm just gonna say it: Apple is the Bose of mobile electronics, only those who don't know any better buy that junk. Hey it's your money feel free to waste as much as you like.

Log in

Don't have an account? Sign up now