GPU Performance

All of our discussions around the new iPad and its silicon thus far have been in the theoretical space. Unfortunately the state of Android/iOS benchmarking is abysmal at best today. Convincing game developers to include useful benchmarks and timedemo modes in their games is seemingly impossible without a suitably large check. I have no doubt this will happen eventually, but today we're left with some great games and no way to benchmark them.

Without suitable game benchmarks, we rely on GLBenchmark quite a bit to help us in evaluating mobile GPU performance. Although even the current most stressful GLBenchmark test (Egypt) is a far cry from what modern Android/iOS games look like, it's the best we've got today.

We'll start out with the synthetic tests, which should show us roughly a 2x increase in performance compared to the iPad 2. Remember the PowerVR SGX 543MP4 simply bundles four SGX 543 cores instead of two. Since we're still on a 45nm LP process, GPU clocks haven't increased so we're looking at a pure doubling of virtually all GPU resources.

GLBenchmark 2.1—Fill Test

GLBenchmark 2.1—Triangle Test (White)

GLBenchmark 2.1—Triangle Test (Textured, Fragment Lit)

Indeed we see a roughly 2x increase in triangle and fill rates. Below we have the output from GLBenchmark's low level tests. Pay particular attention to how, at 1024 x 768, performance doubles compared to the iPad 2 but at 2048 x 1536 performance can drop to well below what the iPad 2 was able to deliver at 10 x 7. It's because of this drop in performance at the iPad's native resolution that we won't see many (if any at all), visually taxing games run at anywhere near 2048 x 1536.

GLBenchmark 2.1.3 Low Level Comparison
  iPad 2 (10x7) iPad 3 (10x7) iPad 3 (20x15) ASUS TF Prime
Trigonometric test—vertex weighted
35 fps
60 fps
57 fps
47 fps
Trigonometric test—fragment weighted
7 fps
14 fps
4 fps
20 fps
Trigonometric test—balanced
5 fps
10 fps
2 fps
9 fps
Exponential test—vertex weighted
59 fps
60 fps
60 fps
41 fps
Exponential test—fragment weighted
25 fps
49 fps
13 fps
18 fps
Exponential test—balanced
19 fps
37 fps
8 fps
7 fps
Common test—vertex weighted
49 fps
60 fps
60 fps
35 fps
Common test—fragment weighted
8 fps
16 fps
4 fps
28 fps
Common test—balanced
6 fps
13 fps
2 fps
12 fps
Geometric test—vertex weighted
57 fps
60 fps
60 fps
27 fps
Geometric test—fragment weighted
12 fps
24 fps
6 fps
20 fps
Geometric test—balanced
9 fps
18 fps
4 fps
9 fps
For loop test—vertex weighted
59 fps
60 fps
60 fps
28 fps
For loop test—fragment weighted
30 fps
57 fps
16 fps
42 fps
For loop test—balanced
22 fps
43 fps
11 fps
15 fps
Branching test—vertex weighted
58 fps
60 fps
60 fps
45 fps
Branching test—fragment weighted
58 fps
60 fps
30 fps
46 fps
Branching test—balanced
22 fps
43 fps
16 fps
16 fps
Array test—uniform array access
59 fps
60 fps
60 fps
60 fps
Fill test—Texture Fetch
1001483136 texels/s
1977874688
texels/s
1904501632
texels/s
415164192
texels/s
Triangle test—white
65039568
triangles/s
133523176
triangles/s
85110008
triangles/s
55729532
triangles/s
Triangle test—textured
56129984
triangles/s
116735856
triangles/s
71362616
triangles/s
54023840
triangles/s
Triangle test—textured, vertex lit
45314484
triangles/s
93638456
triangles/s
46841924
triangles/s
28916834
triangles/s
Triangle test—textured, fragment lit
43527292
triangles/s
92831152
triangles/s
39277916
triangles/s
26935792
triangles/s

GLBenchmark also includes two tests designed to be representative of a workload you could see in an actual 3D game. The older Pro test uses OpenGL ES 1.0 while Egypt is an ES 2.0 test. These tests can either run at the device's native resolution with vsync enabled, or rendered offscreen at 1280 x 720 with vsync disabled. The latter offers us a way to compare GPUs without device screen resolution creating unfair advantages.

Unfortunately there was a bug in the iOS version of GLBenchmark 2.1.2 that resulted in all on-screen benchmarks running at 1024 x 768 rather than the new iPad's native 2048 x 1536 resolution. This is why all of the native GLBenchmark scores from the new iPad are capped at 60 fps. It's not because the new GPU is fast enough to render at speeds above 60 fps at 2048 x 1536, it's because the benchmark is actually showing performance at 1024 x 768. Luckily, GLBenchmark 2.1.3 fixes this problem and delivers results at the new iPad's native screen resolution:

GLBenchmark 2.1—Egypt (Standard)

GLBenchmark 2.1—Pro (Standard)

Surprisingly enough, the A5X is actually fast enough to complete these tests at over 50 fps. Perhaps this is more of an indication of how light the Egypt workload has become, as the current crop of Retina Display enhanced 3D titles for the iPad all render offscreen to a non-native resolution due to performance constraints. The bigger takeaway is that with the 543MP4 and a quad-channel LP-DDR2 interface, it is possible to run a 3D game at 2048 x 1536 and deliver playable frame rates. It won't be the prettiest game around, but it's definitely possible.

The offscreen results give us the competitive analysis that we've been looking for. With a ~2x die size advantage, the fact that we're seeing a 2-3x gap in performance here vs. NVIDIA's Tegra 3 isn't surprising:

GLBenchmark 2.1—Egypt—Offscreen 720p

GLBenchmark 2.1—Pro—Offscreen 720p

The bigger worry is what happens when the first 1920 x 1200 enabled Tegra 3 tablets start shipping. With (presumably) no additional GPU horsepower or memory bandwidth under the hood, we'll see this gap widen.

The Impact of Larger Memory A5X vs. Tegra 3 in the Real World
POST A COMMENT

234 Comments

View All Comments

  • jjj - Wednesday, March 28, 2012 - link

    Testing battery life only in web browsing ? Maybve that would be ok for a 100$ device.As it is the battery tests are prety poor,you do video playback when every SoC out there has a dedicated decode unit and that test is only representative for vid playback.Here the most important test should have been battery life when both GPU and CPU are loaded and not including that seems like an intentional omission to avoid makiing the device look bad.
    There are a lot of other things to say about the review,too many but one thing has to be said.
    This is a plan B or plan C device.The screen is the selling point,is what had to go in,they didn't had 28/32nm in time and had to go for a heavier,thicker,hotter device with a huge chip (CPU speed is limited most likely by heat not so much power consumption,ofc both are directly related).Apple had to make way too many compromises to fit in the screen,no way this was plan A.
    Reply
  • tipoo - Thursday, March 29, 2012 - link

    I would have liked a gaming battery life test as well. Reply
  • PeteH - Thursday, March 29, 2012 - link

    Beyond even that, I'd like to see a worst-case battery life (i.e. gaming, max brightness, LTE up, etc).

    Also, it'd be really interesting to see how brightness impacts battery life. Maybe the web browsing test at 20%, 40%, 60%, 80%, and 100% brightness. Of course that would probably delay the review by several days, so it might not be worth it.
    Reply
  • Anand Lal Shimpi - Thursday, March 29, 2012 - link

    We did a max brightness test, however a gaming test would be appropriate as well. I will see if I can't run some of that in the background while I work on things for next week :)

    Take care,
    Anand
    Reply
  • SimpleLance - Wednesday, March 28, 2012 - link

    The biggest drain for the battery comes from the display. So, if the iPad will be used for hotspot only (with display turned off), you will get a lot of hours from it because it has such a huge battery.

    But then, using the the iPad just for a hotspot would be a waste of that gorgeous display.

    Very nice review of a very nice product.
    Reply
  • thrawn3 - Wednesday, March 28, 2012 - link

    Am I the only one that feels the max brightness is more important in day to day use of a highly portable device than DPI and color accuracy?
    I absolutely would love to have all of these three be excellent but I think for a tablet or small laptop Max Brightness and DPI are higher priority than color accuracy. This is exactly what the ASUS Transformer Infinity is supposed to be but I would prefer it on a real laptop.
    I care about color accuracy too but I am perfectly fine with needing a desktop monitor and trading brightness there since it is in a stable environment until we hit the technological level that will allow all these elements to be combined. Maybe quantum dot display technology in the future?

    One thing I have to give all these new displays is that they FINALLY have gotten the wide viewing angles thing right and I will be so happy to get this into the rest of the market.
    Reply
  • seapeople - Tuesday, April 3, 2012 - link

    Would you really prefer a bright 1366x768 TN panel with 200 contrast ratio on a 15" laptop over a less bright IPS Ipad screen with much better resolution, DPI, color accuracy, and viewing angle? Reply
  • vision33r - Wednesday, March 28, 2012 - link

    The screen is really gorgeous when you shoot raw with any DSLR and view it in iPhoto. Reply
  • ol1bit - Wednesday, March 28, 2012 - link

    I just bought a Asus Transformer Prime, and your review was spot on with what I decided. I can not live with IOS and using Android for 3 years.

    Just the simple stuff was my decision:
    1. Freedom of Android, file transfers, etc. No Itunes requirement.
    2. MicroSD
    3. Kewl keyboard
    4. Live Wallpaper.
    5. A real desktop, separate from my applications.
    6. 32GB versus 16GB
    7. Gorilla Glass (yes, true. My original droid lived in my pocket 2 years no scratches, my HTC Rezound scratches the first 2 weeks).
    8. Asus (love their MBs)
    9. Nivida (love their GPUs)

    What I will miss:
    1. Ipad 3 Display.
    Reply
  • darkcrayon - Thursday, March 29, 2012 - link

    1. iTunes is no longer ever needed for an iOS device. I consider the option of a first party desktop sync solution to be an advantage now that it's not a requirement.
    7. It seems likely the new iPad uses Gorilla Glass or Gorilla Glass 2...
    9. Odd that you'd love nVidia's GPUs when they've been pretty much the bottom of the performance barrel for ARM device graphics, even excluding Apple's SoCs (which have lately been using the fastest GPUs in the industry by far).
    Reply

Log in

Don't have an account? Sign up now