GPU Performance

On the GPU side of things the iPad Air 2 seems to have a GX6650, which should provide a healthy boost to GPU performance when compared to the GX6450 in the A8. Apple has placed a strong emphasis on gaming for their iPad line, so there are some obvious comparisons to be made between NVIDIA's Tegra K1 and the A8X as well. To test this, we use a suite of benchmarks that can give a good idea of real world gaming performance.

3DMark 1.2 Unlimited - Overall

3DMark 1.2 Unlimited - Graphics

3DMark 1.2 Unlimited - Physics

BaseMark X 1.1 - Overall (High Quality)

BaseMark X 1.1 - Dunes (High Quality, Offscreen)

BaseMark X 1.1 - Hangar (High Quality, Offscreen)

BaseMark X 1.1 - Dunes (High Quality, Onscreen)

BaseMark X 1.1 - Hangar (High Quality, Onscreen)

GFXBench 3.0 Manhattan (Onscreen)

GFXBench 3.0 Manhattan (Offscreen)

GFXBench 3.0 T-Rex HD (Onscreen)

GFXBench 3.0 T-Rex HD (Offscreen)

In practice, while we see that the A8X's GPU is extremely close to Nvidia's single Kepler SMX across the board, with the sole exception of 3DMark which seems to be due to the dependencies present in the physics test that dramatically lower the overall score. NVIDIA's Tegra K1 seemed incredible for its GPU performance earlier this year, so it's just as surprising to see Apple successfully rival NVIDIA in this area. Of course, GPU performance is a function of both peak performance and sustained performance, so we'll have to look at the GFXBench battery rundown test to get the full picture here. If Apple can deliver far superior performance and battery life in such a situation, it's pretty clear that the jump to 20nm will be critical to pushing the limits on what's possible in a mobile device.

NAND Performance

As we've seen before on some tablets, poor storage performance can cause major issues with the overall experience as I/O pauses can far exceed just a few frame drops that one might expect from cases of UI lag induced by insufficient performance elsewhere. In order to attempt to quantify this performance we use a custom utility developed by Eric Patno. While such testing is far from a complete look at performance, this can give a rough idea of what to expect.

Internal NAND - Sequential Read

Internal NAND - Sequential Write

Internal NAND - Random Read

Internal NAND - Random Write

Overall, it seems that Apple does quite well on the storage tests. It seems that the iPad Air 2 shares its storage solution with the iPhone 6. While I don't have an iPad Air on hand for testing, it should match quite closely to the iPhone 5s. This represents a generally high-quality NAND solution, but as mentioned before random I/O could stand to improve a bit. Compared to most of the lower-cost Android tablets it's definitely as good as it gets though.

CPU Performance Battery Life and Charge Time
Comments Locked

226 Comments

View All Comments

  • Speedfriend - Friday, November 7, 2014 - link

    When I read about the A8, it make me wonder about the A7. With the A8 Apple claims to have improved energy efficiency over the A7 by 50%. Now a iPhone 6 Plus driving a 1920x1020 screen has the same 10 hour battery life as a Galaxy Note 3 which also has a 1920 x 1080 screen. But that means that if Apple had tried to build a phablet with the A7, they would have ended up with a battery life of around 6.5 hours, clearly not competitive with Samsung’s offerings.
    So to me it looks like Apple didn’t build a bigger screen phone before not because they didn’t feel there was demand but because they simply wouldn’t have been able to compete on battery life and that is why the whole focus with the A8 was improving efficiency rather than simply performance.
    So was the A7 just very uncompetitive to other ARM designs or is iOS inefficient compared to Android.
    I would love to see someone do some digging on this – Anandtech?
  • dmunsie - Friday, November 7, 2014 - link

    I don't think this has anything to do with either the A7 design or iOS -- there are too many variables in the equation to definitively say. Plus unlike other ARM designs and Android, there is only one source for the A7 and iOS -- Apple. So you can't just take iOS and install it on the same hardware as another Android device and compare.

    The A7 was also used in the iPad and iPad mini last year where it got an advertised 10 hour battery life. If Apple had made a Plus sized iPhone last year, they probably would've had to make it thicker to get to their target battery life, which is probably similar to what Samsung has done with their designs. Apple never likes to go thicker if they can avoid it.

    You can see how Apple values size over battery life because with the move to the A8X, the Air 2 got thinner with the same battery life vs staying the same size but with more battery life. Not saying that valuing battery live over size is better than what Apple chose, but they are clearly making it known what they are optimizing for here.
  • Impulses - Friday, November 7, 2014 - link

    As an Android fan, I'd love to see Apple stop chasing thinness and actually improve battery life by a large degree... They could've done so with the iPhone 6 and chased the claim of "2 day battery life", but they chose thinness instead.

    Having Apple claiming two day battery life on a phone and destroying everything else by a large margin would definitely light a fire under everyone... Over engineering for 7mm thickness vs 8.5 mm seems quite pointless to me, anything under 9 is quite enough on a phone.

    It seems structurally speaking they're better off to, e.g. bendgate...
  • sonicmerlin - Friday, November 7, 2014 - link

    Personally I'd like my phone to be as thin as a credit card.
  • akdj - Thursday, November 27, 2014 - link

    Be state came and went in ten minutes. It's a non issue
    Might check those up times on the 6+ again. They reflect almost identical performance as mine. I could go two days, easily.
  • Speedfriend - Monday, November 10, 2014 - link

    Except the note and the iPhone 6+ have the same size battery, so samsung hasn't had to use a bigger battery to get the same battery life.
  • techconc - Friday, November 7, 2014 - link

    You "analysis" fails to consider the size of the battery in existing devices as part of the equation. Likewise, your conclusion regarding the A7 design not being competitive is completely baseless. What's more, you also fail to consider the manufacturing process as a variable as well. The primary efficiency difference between the A8 and A7 has much more to do with the manufacturing process moving from 28nm to 20nm.
    Finally, if you wish to compare Apple's chips with the competition or iOS vs. Android in terms of efficiency, you should ask yourself why Android phones require more memory to perform the same tasks and why Android devices need such a bigger battery in order to get the same level of usage and/or performance.
  • Speedfriend - Monday, November 10, 2014 - link

    At techconc

    Battery size is almost identical. Manufacturing process has absolutey nothing to do with it. Or the efficiency difference between A8 and A7. It is a fairly simply equation - at same battery size, A8 equipe diPhone 6+ gives smae battery life as Note 3/4. Swap out A8 for A7 and you would get 1/3 less battery life based on Apple's 50% A8 over A7 efficiency claim. Hence why no big iPhone before.
  • tipoo - Friday, November 7, 2014 - link

    Yup, when I saw the teardown with two RAM banks rather than the usual one, I was expecting 25.6GB/sec, with double the pins/bits going into the SoC. And it also makes sense with the huge GPU gains, something has to feed that beast. Crazy, that's now in laptop bandwidth range.
  • cynic783 - Friday, November 7, 2014 - link

    and we made it about 10 comments before the "Anand is an Apple shill" accusation lol. so much Android butt hurt.

Log in

Don't have an account? Sign up now